After completing a pre-test and a brief atlas review, students were alternately assigned to study either CT images alone or CT images plus patient-specific 3D-printed models for 10 minutes. The researchers then administered the same written test covering normal abdominal anatomy and two congenital anomalies: choledochal cysts and anorectal malformations. A satisfaction survey followed the post-test. In the reported gain scores, the CT-plus-3D-printing group improved by 11.5%, compared with 7.2% in the CT-only group, a difference with a reported P value of 0.018.

Questions concerning the congenital anomalies showed greater improvement in the group that also used 3D-printed models, with a reported P value of 0.021. The abstract also reports that the additional 3D-printing assistance was particularly beneficial among students with lower baseline performance. Students rated the combined CT-plus-3D-printing module more highly for usefulness and overall satisfaction. These findings describe measured associations in this comparative study rather than demonstrating that 3D printing alone caused the improvements.

The results have important boundaries. The cohort was limited to 48 third-year medical students, and the groups did not differ significantly in their absolute post-test scores. In addition, the combined group received a greater volume and variety of learning material, including both CT images and 3D-printed models, while the comparison group used CT images alone. The authors therefore attribute the observed benefit to the combined multimodal approach rather than to 3D printing in isolation. The reported findings support further consideration of combined CT and 3D-printing materials in surgical clerkships, but the abstract does not establish the effectiveness of 3D printing independently or across other student populations and educational settings.

Subject of Research: Comparative evaluation of combined CT and 3D-printed abdominal anatomy teaching for medical students

Article Title: Application of 3D printing in medical anatomy education and its potential impact on student achievement

Article References: Yang, J., Youn, J. K., Ko, D., Yoon, H. B., & Kim, H.-Y. (2026). Application of 3D printing in medical anatomy education and its potential impact on student achievement. BMC Medical Education. https://doi.org/10.1186/s12909-026-10469-3

Image Credits: AI Generated

DOI: 10.1186/s12909-026-10469-3

Keywords: medical education, abdominal anatomy, 3D printing, computed tomography, medical students, congenital anomalies, multimodal learning, student achievement, Application, printing, medical, anatomy

The findings support technical feasibility under controlled conditions, but the study did not test real fractures or establish clinical benefit. The study addresses a demanding part of computer-assisted mandibular fracture planning, where three-dimensional CT can show the relationship among bone fragments but segmentation, separation, alignment and selection of a reduction target still depend substantially on manual work and surgical judgment. Contralateral mirroring can supply an anatomical reference in some cases, but it is unsuitable when the opposite side is affected or markedly asymmetric.

The new approach instead uses population-derived information to estimate a patient-adaptive target while simultaneously estimating the relative positions of multiple fragments. For this single-center retrospective methodological study, investigators at Tokai University Hospital in Japan collected maxillofacial CT scans acquired between January 2021 and March 31, 2024. The broader cohort contained 289 patients aged 18 to 63 years: 178 males and 111 females, with a mean age of 34.54 ± 13.85 years.

Patients were excluded if they had mandibular fractures, deformities, pathological osseous lesions, severe metal artifacts or extensive tooth loss, because the investigators required intact mandibular geometry. Ten cases—five male and five female, with a mean age of 38.20 ± 16.56 years—were reserved for pseudo-fracture evaluation. The remaining 279 cases, comprising 173 males and 106 females, were used to train the statistical models.

The institutional review committee approved the study, and written consent was waived under an opt-out policy for anonymized, pre-existing data. The researchers first converted the CT data into three-dimensional mandibular surface meshes. A previously reported automated deep-learning model performed segmentation, after which the results were manually refined in 3D Slicer and exported as STL files.

Separate male and female statistical shape models were constructed, along with a combined-sex model used as an exploratory baseline. Non-rigid registration with Bayesian coherent point drift established corresponding points across the jaw surfaces, while repeated atlas updating reduced dependence on the initial template. Principal component analysis then represented population variation around a mean shape through a mean configuration, eigenvectors, eigenvalues and principal component scores.

The number retained for each model was the minimum required to explain 95% of cumulative variance. Left–right mirrored shapes were included during model construction to balance morphology in the two directions and reduce directional bias in atlas and principal component analysis. This augmentation produced 346 male shapes from 173 original training mandibles and 212 female shapes from 106 originals.

The combined-sex model contained 558 shapes derived from 279 training cases. It was important to note that mirroring increased the number of shape configurations but did not increase the number of independent patients. The minimum numbers of principal components required to reach 95% cumulative explained variance were 28 for the male model, 32 for the female model and 29 for the combined-sex model.

Their template meshes contained 34,830, 33,026 and 34,830 vertices, respectively. To create the controlled evaluation dataset, the researchers divided each of the 10 intact validation mandibles into three fragments using two manually defined planar osteotomies. The cut planes were positioned with reference to clinically common fracture regions while avoiding extremely small pieces that would be unsuitable for algorithmic assessment.

The fragments were then separated and displaced with case-specific rigid translations and rotations. Each pseudo-fracture configuration was processed with the corresponding sex-specific statistical shape model and with the combined-sex model. Because the original intact mandible remained available for each case, it could serve as subject-specific ground truth and permit direct measurement of reconstruction error.

During reduction, each fragment mesh was converted into a point cloud, with points allocated in proportion to fragment surface area and 30,000 points sampled across the three fragments. Global and fragment-level iterative closest point registration provided an initial alignment with the model’s mean shape. The covariance matrix adaptation evolution strategy, a gradient-free stochastic method designed for nonconvex objective functions, then jointly optimized 18 rigid parameters—three rotations and three translations for each of the three fragments—together with the statistical model’s shape coefficients.

This joint search estimated both the candidate anatomical target and the configuration of the fragments. It did not use an individual patient’s unaffected jaw as a direct mirrored template, although its objective function did not explicitly enforce physical contact, collision avoidance, occlusion, condylar position or fracture-surface correspondence. Symmetric chamfer distance was defined as the mean of bidirectional nearest-neighbor distances between the reconstruction and ground truth.

Symmetric root-mean-square error was calculated as the average of the two directional root-mean-square nearest-neighbor errors. The sex-specific models produced mean symmetric chamfer distances of 0.712 ± 0.210 mm and mean symmetric root-mean-square errors of 0.855 ± 0.231 mm. For male cases, the corresponding mean chamfer and root-mean-square values were 0.635 ± 0.111 mm and 0.769 ± 0.127 mm; for female cases, they were 0.788 ± 0.268 mm and 0.942 ± 0.293 mm.

Qualitative comparisons assessed whether the reductions reproduced the mandibular body, ramus, condylar regions and overall contour. The combined-sex model yielded numerically larger mean errors: 0.778 ± 0.309 mm for symmetric chamfer distance and 0.937 ± 0.358 mm for symmetric root-mean-square error. Sex-specific models produced lower errors in six of the 10 cases for chamfer distance and seven of 10 for root-mean-square error.

The paired mean difference between the combined and sex-specific approaches was 0.067 mm for chamfer distance, with a bootstrap 95% confidence interval of −0.011 to 0.148 mm, and 0.082 mm for root-mean-square error, with an interval of −0.008 to 0.180 mm. Exact two-sided Wilcoxon signed-rank tests gave p = 0.232 and p = 0.193, respectively. Because only five validation cases were assigned to each sex-specific subgroup and the analysis was exploratory, the numerical differences did not demonstrate a statistically significant advantage for modeling the sexes separately.

Fixed-scale surface-distance maps showed that reduced models generally reproduced the broad shape of the mandible, while also revealing local shortcomings. Some cases retained gaps between fragments or showed interpenetration despite an anatomically plausible overall outline. The distance-based optimization could therefore reward a coherent global contour without guaranteeing that fragment surfaces met appropriately or did not overlap.

The investigators proposed adding collision penalties, contact-aware distance terms and constraints based on fracture surfaces, occlusion and condylar positioning. They also identified possible computational improvements, including early stopping, coarse-to-fine optimization, better initial registration, GPU-accelerated nearest-neighbor calculation and adaptive point sampling. The current system required approximately 23 minutes for each reduction run, which is more consistent with offline planning than with time-critical intraoperative use.

Several limitations prevent the surface-distance results from being interpreted as evidence of accuracy in real fractures. The pseudo-fractures consisted of three pieces separated by two straight cuts and did not reproduce irregular fracture geometry, comminution, bone loss, metal or dental artifacts, restorations or different fragment counts. No fracture patient in the available cohort had suitable pre-trauma CT data that could provide an intact ground truth, so the framework was not evaluated with real injuries.

The models also did not explicitly incorporate age, ethnicity, dentition status, mandibular atrophy, occlusal relationships, condylar position, biomechanical stability or fracture-interface constraints. The retrospective design came from one institution, and larger external cohorts, predefined test sets or cross-validation are needed to assess robustness and generalizability. The study therefore demonstrates a promising computational method for aligning fragments in controlled pseudo-fractures, but it does not show that the method can improve fixation planning, occlusal restoration or patient outcomes in clinical care.

Subject of Research: Proof-of-concept evaluation of statistical shape models for automated virtual reduction of pseudo-fractured mandibles

Article Title: Automated virtual reduction of pseudo-fractured mandibles using sex-specific statistical shape models: a proof-of-concept study

Article References: Morita, D., Nemoto, H., Otake, Y., Tsunoda, Y., Hanai, U., & Kono, T. (2026). Automated virtual reduction of pseudo-fractured mandibles using sex-specific statistical shape models: a proof-of-concept study. International Journal of Computer Assisted Radiology and Surgery. https://doi.org/10.1007/s11548-026-03806-w

Image Credits: AI Generated

DOI: 10.1007/s11548-026-03806-w

Keywords: mandibular pseudo-fractures, statistical shape models, virtual fracture reduction, computed tomography, three-dimensional reconstruction, CMA-ES optimization, principal component analysis, computer-assisted surgery, maxillofacial imaging, fragment alignment, Automated, virtual

The patient was a pillion passenger in a road traffic accident involving posterior impact. He arrived at the emergency department conscious, fully oriented and maintaining his own airway, with a Glasgow Coma Scale of 15. His principal symptoms were abdominal pain and persistent tachycardia that did not resolve after intravenous crystalloid resuscitation. Although systolic blood pressure was maintained and he was otherwise hemodynamically stable, the continuing tachycardia prompted urgent cross-sectional imaging. Abdominal examination showed mild diffuse tenderness, most marked in the epigastrium, without guarding, rigidity, rebound tenderness or clinical signs of peritonitis. Bowel sounds were audible, and there was no seat-belt sign, flank bruising or external abdominal wall injury. Examination of the chest, pelvis and limbs was also unremarkable, with no clinical evidence of concomitant extra-abdominal injury.

Initial laboratory testing showed hemoglobin of 11.8 g/dL, a total leukocyte count of 9.6 × 10^3/μL and platelets of 138 × 10^3/μL. Serum amylase was elevated at 597 U/L, while total bilirubin was 2.25 mg/dL, alanine aminotransferase was 19 U/L and alkaline phosphatase was 86 U/L. The international normalized ratio was 1.32, while prothrombin and activated partial thromboplastin times were within acceptable limits; arterial blood gas analysis showed no acidosis. Renal function and electrolytes were within normal limits. The elevated amylase was compatible with pancreatic injury but could not establish or exclude main pancreatic duct disruption because its diagnostic sensitivity and specificity are limited in the early hours after blunt abdominal trauma. Persistent tachycardia despite fluid resuscitation was therefore the principal clinical signal that significant internal injury might be present despite the relatively benign abdominal examination.

Portal venous phase CT revealed hypodense linear defects in the pancreatic tail, focal parenchymal discontinuity, peripancreatic fat stranding and a localized fluid collection measuring approximately 4.8 × 3.7 cm, interpreted as hematoma. Mild haemoperitoneum was present, but no active contrast extravasation was identified. The liver, spleen, kidneys, bowel loops and major abdominal vessels appeared unremarkable. These findings supported a provisional AAST Grade III injury involving the pancreatic tail, with suspected disruption of the main pancreatic duct. Importantly, CT did not directly demonstrate the duct or prove that it had been transected. Its diagnostic contribution was indirect: focal disruption of pancreatic tissue combined with an adjacent collection suggested that the injury extended into the main duct. The distinction is important because ductal integrity is a major determinant of management in pancreatic trauma, and the sensitivity of CT for directly visualizing duct disruption can vary, particularly early after injury.

The diagnostic assessment also considered a Grade I or II pancreatic contusion or laceration without ductal involvement, which might have permitted nonoperative management. Other possibilities included injury to the liver, spleen or kidneys, hollow-viscus or mesenteric damage, and a retroperitoneal hematoma of vascular origin. The apparently normal appearances of the other abdominal organs, bowel loops and major vessels made several alternatives less likely, while the pancreatic findings supported the working diagnosis of isolated distal pancreatic injury with suspected ductal disruption. Dedicated assessment with magnetic resonance cholangiopancreatography or endoscopic retrograde cholangiopancreatography could have provided direct evidence of duct continuity. Neither was undertaken because the clinical circumstances did not permit those procedures without delaying operative exploration. The authors therefore characterize the CT interpretation as a well-founded suspicion rather than a confirmed diagnosis. Concordance between one CT examination and one laparotomy cannot establish the sensitivity or specificity of the imaging signs used.

At operation, the surgical team found approximately 30 mL of haemoperitoneum and fat saponification involving the omentum and bowel loops. Exploration confirmed complete transection of the pancreatic tail with disruption of the main pancreatic duct, corresponding to the category of injury suspected before surgery. The spleen was viable and uninjured, and the splenic artery and vein were intact. Initial consent and operative planning had allowed for distal pancreatectomy with or without splenectomy because treatment of distal pancreatic injury may require removal of the spleen when the splenic vessels are involved. Direct inspection instead permitted spleen-preserving distal pancreatectomy, avoiding the lifelong risk of overwhelming postsplenectomy infection and the associated need for vaccination and prophylaxis in an otherwise healthy adolescent. A closed-suction drain was placed in the pancreatic bed, intravenous antimicrobial prophylaxis was administered at induction, multimodal analgesia was provided, and pharmacological venous thromboembolism prophylaxis began on the first postoperative day.

Definitive surgery was performed under general anesthesia through an upper midline laparotomy on the day of admission, without an intervening period of nonoperative observation. Intraoperative blood loss was otherwise minimal, and no blood products were required. Somatostatin analogue therapy was not administered. Intravenous crystalloid was continued after surgery, oral intake was reintroduced early and tolerated, and the drain was removed on postoperative day 5, when the patient was discharged. His postoperative course was uneventful: drain output was minimal, pain was mild and controlled with standard analgesia, and there was no fever, surgical-site infection, respiratory compromise or sepsis. The report records no postoperative pancreatic fistula by International Study Group of Pancreatic Surgery criteria, intra-abdominal collection, pseudocyst, wound complication or readmission. At the two-week outpatient review, the wound was healing satisfactorily, the patient had no abdominal symptoms and his repeat serum amylase had normalized.

Follow-up extended through six months, with the patient attending scheduled appointments and remaining asymptomatic. He had resumed his studies and ordinary activities without limitation, and no clinical signs of endocrine or exocrine pancreatic insufficiency were observed. Surveillance consisted of symptom review, clinical examination and biochemical testing; no formal dynamic endocrine or exocrine function tests were performed, so subclinical insufficiency cannot be excluded. Six months is also a relatively short period for ruling out late pseudocysts or delayed pancreatic insufficiency, and longer surveillance remains necessary. The absence of complications was therefore an observed outcome in this case, not proof that immediate resection or preoperative CT suspicion prevented them. No causal inference is possible from a single case without comparison groups, and the management described was consistent with established guideline-based care rather than a new treatment strategy.

The report’s educational value lies in showing how indirect CT signs can support a consequential preoperative decision. Focal parenchymal discontinuity and peripancreatic fluid did not conclusively demonstrate a disrupted main pancreatic duct, but together they provided a credible basis for expecting a high-grade distal injury. That interpretation was considered alongside persistent tachycardia and the inability to obtain dedicated ductal imaging without delaying surgery, allowing operation to proceed directly to definitive assessment. The approach also carries a trade-off: relying on suspicion can lead to surgery for an injury that dedicated ductal imaging might show to be lower grade. In this patient, however, operative findings confirmed the anticipated ductal disruption, and spleen-preserving distal pancreatectomy was followed by discharge after five days and an uncomplicated six-month course. The case therefore illustrates a distinction that matters in trauma imaging: indirect abnormalities can inform surgical planning while remaining less than definitive. The operative findings retrospectively supported the preoperative suspicion, but one successful correlation cannot establish that CT alone predicts ductal transection or that the timing of surgery produced the observed recovery.

Subject of Research: Preoperative CT suspicion and operative confirmation of main pancreatic duct injury in isolated blunt pancreatic trauma

Article Title: Preoperative CT Suspicion of Main Pancreatic Duct Injury in Isolated Blunt Pancreatic Trauma: A Case Report With Operative Correlation

Article References: Kazmi, S. S., Qamar, S. Z., Ali, A., Fatani, M. S., Haider, S. A., Farhan, M., Raza, A. A., & Samadi, A. (2026). Preoperative CT Suspicion of Main Pancreatic Duct Injury in Isolated Blunt Pancreatic Trauma: A Case Report With Operative Correlation. Clinical Case Reports, 14(10), Article e73760. https://doi.org/10.1002/ccr3.73760

Image Credits: AI Generated

DOI: 10.1002/ccr3.73760

Keywords: pancreatic trauma, main pancreatic duct, computed tomography, blunt abdominal injury, duct transection, distal pancreatectomy, spleen preservation, case report, Preoperative, Suspicion, Main, Pancreatic

The research team set out to answer a deceptively simple question: once a clinician knows a child’s age, Pediatric Appendicitis Score, and C-reactive protein level, how much additional diagnostic value does an appendicitis-compatible initial ultrasound report actually provide? This question matters because ultrasound is widely used as the first-line imaging modality in children with suspected appendicitis, particularly given concerns about radiation exposure from computed tomography in young patients. Yet the incremental value of the initial ultrasound report, considered alongside established clinical variables, has remained surprisingly unclear in the literature. Prior studies have integrated ultrasound findings with clinical scores, refined sonographic criteria using age-based appendiceal measurements and secondary signs, and explored the meaning of partial appendix visualization, but few prospective cohorts have directly measured the statistical gain that ultrasound adds to a baseline clinical model.

To address this gap, the investigators conducted a prospective single-centre cohort study enrolling children aged 3 to 17 years who were evaluated for suspected acute appendicitis between May 2025 and March 2026. The primary outcome was histopathologically confirmed appendicitis, a rigorous standard that anchors the diagnostic analysis in tissue-level truth rather than clinical impression alone. The study design compared two statistical models. The first, a clinical model, included age, the total Pediatric Appendicitis Score, and log2-transformed C-reactive protein values. The second, an ultrasound-extended model, added an appendicitis-compatible initial ultrasound report to those same variables. Model performance was assessed using the area under the receiver operating characteristic curve, known as the AUC, along with the Brier score, likelihood-ratio testing, and the DeLong method for comparing correlated receiver operating characteristic curves.

The cohort comprised 135 children evaluated through an ultrasound-first pathway. Of these, 81 had histopathologically confirmed appendicitis, while 54 formed the comparison group of children in whom appendicitis was ultimately excluded. The clinical model alone demonstrated moderate apparent discrimination, achieving an AUC of 0.771 with a 95 percent confidence interval spanning 0.689 to 0.852, and a Brier score of 0.188. These figures describe a model that performs meaningfully above chance but still leaves substantial diagnostic uncertainty in individual cases, a familiar reality for clinicians who know that scores and inflammatory markers can overlap considerably between children who need surgery and those who do not.

The headline result emerged when ultrasound entered the equation. Among the 132 children whose initial ultrasound reports could be classified, the addition of an appendicitis-compatible ultrasound report increased the AUC from 0.772 to 0.912 and reduced the Brier score from 0.187 to 0.113. In practical terms, the AUC jump represents a substantial improvement in the model’s ability to separate children with confirmed appendicitis from those without it, moving discrimination from the moderate range toward levels typically associated with highly reliable diagnostic tools. The Brier score, which measures the mean squared difference between predicted probabilities and actual outcomes, fell by nearly 40 percent, indicating that the ultrasound-extended model produced not only better ranking of patients but also better-calibrated probability estimates. The likelihood-ratio framework confirmed that the improvement was statistically meaningful rather than a product of chance variation within the sample.

These numbers carry weight for anyone who has followed the evolution of pediatric appendicitis diagnostics. The Pediatric Appendicitis Score, originally described by Samuel in 2002, combines clinical findings such as migration of pain, anorexia, fever, and rebound tenderness into a structured assessment. C-reactive protein, an acute-phase reactant measurable within hours, has been validated through systematic reviews and meta-analyses as a useful but imperfect marker of inflammation in pediatric appendicitis. Previous work by Bachur and colleagues in 2015 demonstrated the value of integrating ultrasound findings with clinical scores, and subsequent studies have refined sonographic criteria by combining age-based appendiceal size thresholds with secondary findings such as periappendiceal fluid and echogenic fat. The new study extends this lineage by prospectively quantifying, within a single cohort, the exact statistical increment that a clear ultrasound report delivers on top of those established variables.

The study also examined the role of post-ultrasound computed tomography within the same ultrasound-first pathway. CT was performed in 52 of the 135 children, representing 38.5 percent of the cohort. Among those children, 29 had appendicitis, while 23 did not undergo appendectomy. This figure illustrates a persistent tension in pediatric imaging strategy: ultrasound is favored as the initial modality because it avoids ionizing radiation, but equivocal or negative ultrasound findings in children with persistent clinical suspicion often prompt a second-line CT examination. The ACR Appropriateness Criteria for suspected appendicitis in children endorse this staged approach, and prior implementation studies have shown that ultrasound and fast magnetic resonance imaging pathways can reduce CT utilization. The new data suggest that when the initial ultrasound report is clearly appendicitis-compatible, its diagnostic contribution is strong enough to anchor clinical decisions, while the residual group with inconclusive imaging continues to require careful escalation.

Methodologically, the choice of log2-transformed C-reactive protein reflects the skewed distribution typical of inflammatory markers, where a small number of children with very high values would otherwise dominate a linear model. The use of the DeLong comparison, a standard method for testing whether two correlated AUCs differ significantly, strengthens the inference that the ultrasound-extended model genuinely outperforms the clinical baseline rather than merely appearing to do so in this particular sample. The Brier score decomposition further distinguishes discrimination from calibration, two properties of a predictive model that can diverge: a model may rank patients correctly yet assign probabilities that are systematically too high or too low. The observed reduction from 0.187 to 0.113 indicates improvement on both fronts, which is precisely what clinicians need when translating a statistical model into bedside decisions about observation, imaging escalation, or surgical consultation.

The authors frame their conclusion carefully: a clear appendicitis-compatible initial ultrasound report provided substantial incremental diagnostic information when added to age, Pediatric Appendicitis Score, and C-reactive protein, supporting the role of ultrasound as an integrated component of the diagnostic assessment rather than a standalone test. This framing resists the common temptation to treat any single test as definitive. Appendicitis in children remains a condition in which history, physical examination, laboratory data, and imaging each contribute partial information, and the art of diagnosis lies in combining them coherently. The study’s prospective design, histopathological gold standard, and formal statistical comparison give its central claim unusual solidity for a single-centre cohort.

The implications reach beyond the radiology suite. For emergency physicians and pediatric surgeons, the results support protocols in which ultrasound findings are interpreted in the context of validated scores and inflammatory markers, rather than in isolation. For health systems weighing imaging investments, the data quantify the value of maintaining high-quality pediatric ultrasound services as the backbone of an ultrasound-first pathway. And for researchers, the study provides a template for measuring incremental diagnostic value with the rigor that the field increasingly demands. As pediatric appendicitis diagnostics continue to evolve, with standardized reporting templates, refined sonographic criteria, and alternative second-line modalities all under active investigation, this prospective cohort from Kütahya offers a clear quantitative answer to a question that clinicians have long asked in qualitative terms: ultrasound matters, and now the size of its contribution can be stated with confidence.

Subject of Research: Diagnostic value of ultrasound in pediatric suspected acute appendicitis

Article Title: Incremental diagnostic value of ultrasound in children with suspected acute appendicitis

Article References: Ibrahimoglu, H., & Sahin, S. (2026). Incremental diagnostic value of ultrasound in children with suspected acute appendicitis. Pediatric Radiology. https://doi.org/10.1007/s00247-026-06812-x

Image Credits: AI Generated

DOI: 10.1007/s00247-026-06812-x

Keywords: acute appendicitis, ultrasound, pediatrics, Pediatric Appendicitis Score, C-reactive protein, diagnostic accuracy, computed tomography, pediatric radiology, AUC, emergency medicine, histopathology, ultrasound-first pathway

Coronary artery calcium, or CAC, is one of the most reliable markers available for predicting future cardiovascular events. Calcium deposits build up in the walls of the coronary arteries over years, and the amount present, quantified by the well-established Agatston score on a non-contrast computed tomography scan, correlates closely with the likelihood of heart attack and stroke. Despite this diagnostic power, dedicated cardiac CT for calcium scoring is not performed universally, largely because it is costly, involves radiation exposure, and is generally reserved for patients already considered at intermediate risk. The vast reservoir of cardiovascular information embedded in images already being acquired, the chest X-rays gathering dust in hospital archives, remains largely untapped.

The research team set out to test whether a general-purpose, vision-capable large language model could bridge that gap. Their retrospective, single-center diagnostic accuracy study included 349 patients who had undergone both a non-contrast cardiac CT for calcium scoring and a chest radiograph within a six-month window. Using the CT-derived Agatston classification as the reference standard, the researchers divided the cohort into two clinically meaningful groups: those with a score of 100 or below, and those exceeding 100, the threshold generally regarded as indicating clinically significant coronary calcification that warrants aggressive risk management. Of the 349 patients, 131 fell into the high-calcium category.

The technical approach was striking in its simplicity. Rather than training a bespoke neural network on thousands of labeled images, as is typical for medical AI studies, the team fed preprocessed chest radiographs to GPT-5.5 in a zero-shot setting, meaning the model received no task-specific training whatsoever. Each image passed through a preprocessing pipeline that included contrast-limited adaptive histogram equalization, a technique that enhances local image contrast and can make faint calcific densities more visible. The model was given a structured prompt instructing it to estimate the probability that clinically significant calcification was present, assign a binary classification, and describe any visible calcification findings, mimicking the reasoning process of a human reader.

The results were cautiously encouraging. Using the model’s native binary output, the system correctly classified 292 of the 349 patients, for an overall accuracy of 83.7 percent. Sensitivity, the ability to detect patients who truly had high calcium burden, reached 72.5 percent, while specificity, the ability to correctly clear patients with low calcium, was higher at 90.4 percent. The positive predictive value stood at 81.9 percent and the negative predictive value at 84.5 percent. Perhaps most notably, the area under the receiver operating characteristic curve, a threshold-independent measure of discriminative ability, was 0.771, a figure comparable to some dedicated deep-learning systems developed for similar opportunistic screening tasks after extensive training.

The picture became more complicated, however, when the researchers examined the model’s continuous probability scores rather than its binary judgments. Applying a prespecified threshold of 0.50 to the raw scores yielded dramatically asymmetric performance: sensitivity dropped to 36.6 percent while specificity climbed to 94.0 percent. In other words, when the model did flag a radiograph as suspicious, that flag was very likely to be correct, but it missed the majority of high-calcium patients at that cutoff. The model-generated scores were indeed significantly higher in patients with CT-confirmed CAC above 100, confirming a genuine statistical association, yet the scores overlapped substantially in the intermediate range, blurring the boundary between low and high risk for a meaningful fraction of patients.

Calibration emerged as another significant weakness. A well-calibrated diagnostic score should correspond reliably to actual probability, with a reported risk of 70 percent meaning the finding is truly present in roughly seven of ten such cases. The calibration slope in this study was 2.49, far from the ideal value of 1, indicating that the model’s expressed confidence was poorly aligned with reality. For clinicians accustomed to interpreting validated risk tools, this miscalibration matters enormously, because clinical decisions often hinge not merely on whether a test is positive or negative, but on how much weight the numeric estimate can bear. The authors were transparent about this limitation, framing their results as exploratory and hypothesis-generating rather than clinically actionable.

The concept underlying the study, sometimes called opportunistic screening, has been gaining momentum across medical imaging. The idea is elegant: rather than recruiting patients for dedicated cardiovascular examinations, extract additional diagnostic value from examinations already performed for other reasons. CT scans done for lung screening have been mined for calcium scores, bone density, and fatty liver indicators. Chest radiographs, being the most common imaging examination in medicine, represent perhaps the largest potential reservoir of such incidental information. If an AI system could reliably flag patients with significant coronary calcification from these routine images, those patients could be referred for confirmatory CT calcium scoring, targeted statin therapy, or other preventive interventions years before a first cardiac event.

What makes the use of a zero-shot vision-language model particularly noteworthy is the departure from the conventional AI development paradigm. Building a dedicated medical imaging classifier typically demands curated datasets, expert annotation, fine-tuning, and validation across institutions, investments that slow the translation of algorithms into practice. Foundation models, by contrast, acquire broad visual and linguistic capabilities from web-scale training and can be steered toward new tasks through prompting alone. The Istanbul study offers an early signal that this generality may extend to subtle radiological patterns, such as coronary calcification, that were never explicitly part of the model’s training objectives. It also raises intriguing questions about whether such models perceive image features that resemble human radiological signs or rely on entirely different statistical correlations invisible to human interpretation.

The authors are careful to emphasize the considerable distance between their findings and any bedside application. The cohort was selected, comprising patients who had already undergone cardiac CT, a population very different from the unselected stream of patients whose chest X-rays would be analyzed in a true screening scenario. Human-reader benchmarking was not performed, so it remains unknown how the model compares with radiologists deliberately searching for calcification. Prospective validation in diverse populations, assessment of calibration after refinement, and evaluation of downstream clinical outcomes would all be required before opportunistic AI flagging could enter practice. Still, the central result stands: a general-purpose vision-capable large language model, without a single example of task-specific training, produced image-derived scores significantly associated with CT-defined coronary artery calcium category on plain chest radiographs. That a conversation-ready AI can glance at a decades-old imaging technology and detect the chemical fingerprints of atherosclerosis hints at how much diagnostic potential remains hidden in the world’s existing medical images, waiting for the right tools to reveal it.

Subject of Research: Using a vision-capable large language model to classify coronary artery calcium on chest radiographs

Article Title: Association between a vision-capable large language model’s image-derived score and CT-defined coronary artery calcium category on routine chest radiographs: a single-center retrospective study

Article References: Ayyildiz, H., Banaz, T., Kazanbas, M. F., Gunes, S. T., Arslan, A., Kartal, Y. C., & Ozkok, S. (2026). Association between a vision-capable large language model’s image-derived score and CT-defined coronary artery calcium category on routine chest radiographs: a single-center retrospective study. BMC Medical Imaging. https://doi.org/10.1186/s12880-026-02757-7

Image Credits: AI Generated

DOI: 10.1186/s12880-026-02757-7

Keywords: coronary artery calcium, chest radiograph, large language model, GPT-5.5, zero-shot learning, diagnostic accuracy, opportunistic screening, cardiovascular risk, Agatston score, medical imaging AI, computed tomography, BMC Medical Imaging

HER2, short for human epidermal growth factor receptor 2, is a protein that drives growth in some cancers and has become a critical therapeutic target. In bladder cancer, HER2 overexpression or amplification identifies patients who may respond to antibody-drug conjugates such as disitamab vedotin, a drug that has shown promise in HER2-positive urothelial tumors. The problem is that determining HER2 status currently requires immunohistochemistry or fluorescence in situ hybridization on tissue samples obtained through transurethral resection or biopsy. These procedures are invasive, carry procedural risks, sample only part of a heterogeneous tumor, and cannot always be repeated easily to track how the molecular profile changes over time.

The research team, led by investigators from Shaoxing University, Shaoxing People’s Hospital, and Zhuji People’s Hospital in Zhejiang Province, took a different approach. They turned to radiomics, a technique that extracts hundreds of quantitative features from medical images, features that are invisible to the human eye but encode information about tumor texture, shape, intensity distribution, and spatial patterns. When these features are fed into machine learning algorithms, they can reveal subtle relationships between image appearance and underlying biology, including molecular characteristics that pathologists normally detect only under the microscope.

The study enrolled 190 patients with pathologically confirmed bladder cancer who had undergone preoperative computed tomography urography, known as CTU, between October 2019 and September 2024. CTU is a multiphase CT scan of the urinary tract that captures images at different time points after contrast injection, including corticomedullary, nephrographic, and excretory phases, each highlighting different tissue characteristics. All patients had known HER2 status determined by standard pathological testing, providing the ground truth against which the imaging models could be validated.

To build the predictive models, the researchers first delineated regions of interest covering the tumors on each CTU phase and extracted a large panel of radiomic features, including those based on gray-level run length matrices, gray-level co-occurrence matrices, and gray-level size zone matrices. These mathematical descriptors quantify patterns such as coarseness, contrast, homogeneity, and directional texture within the tumor image. Features were filtered using the Least Absolute Shrinkage and Selection Operator, or LASSO, a regression method that shrinks less informative coefficients toward zero and effectively selects the most predictive variables while guarding against overfitting.

The cohort was randomly divided into a training set of 133 patients and an independent test set of 57 patients. Five different machine learning classifiers were then trained on the selected features: logistic regression, support vector machine, k-nearest neighbors, extreme gradient boosting, and random forest. Among these, the random forest model built on corticomedullary-phase images emerged as the clear winner, achieving an area under the receiver operating characteristic curve of 0.798 in the training set and 0.734 in the test set. The corticomedullary phase, which captures the early arterial enhancement of renal cortex and tumor vasculature, appears to contain the richest information about tumor biology relevant to HER2 expression.

The researchers did not stop at imaging features alone. They integrated the radiomic signature with clinical parameters to build a combined clinical-radiomics model, and the results were striking. This hybrid model achieved an AUC of 0.876 in the training cohort and 0.763 in the test cohort, outperforming the radiomics-only approach. Model performance was further evaluated using calibration curves, which assess how well predicted probabilities match observed outcomes, and decision curve analysis, which quantifies the clinical net benefit of using the model at various decision thresholds. Both analyses confirmed that the combined model offered meaningful clinical utility.

Among the 190 patients, 118, or 62.1 percent, were HER2-positive, reflecting the substantial proportion of bladder cancers that harbor this targetable alteration. Patient ages ranged from 26 to 90 years, with median ages of 72 in the HER2-positive group and 68 in the HER2-negative group. The relatively high prevalence of HER2 positivity in this cohort underscores why a non-invasive screening approach could have broad clinical impact, since a large fraction of patients might be eligible for HER2-directed therapies if their status could be reliably determined before treatment planning.

The implications of this work extend beyond bladder cancer. Radiomics-based prediction of molecular markers represents a growing frontier in precision oncology, sometimes described as radiogenomics or imaging genomics. If validated in larger, multicenter cohorts, this approach could allow clinicians to triage patients for HER2-targeted therapy using images already acquired for diagnosis, reducing the need for repeated invasive procedures and enabling faster treatment decisions. It could also be applied longitudinally, tracking molecular evolution of tumors over the course of therapy without additional biopsies.

The authors acknowledge that this was a single-center retrospective study, and external validation across diverse populations and scanner platforms will be essential before clinical adoption. Standardization of image acquisition and feature extraction, guided by initiatives such as the Image Biomarker Standardization Initiative, remains a key challenge for the field. Nevertheless, the demonstration that a routine CTU scan, combined with machine learning, can predict HER2 status with acceptable diagnostic performance marks a significant step toward non-invasive molecular profiling of bladder cancer, bringing the promise of personalized, image-guided oncology closer to everyday practice.

Subject of Research: Radiomics-based CT urography machine learning prediction of HER2 status in bladder cancer

Article Title: Radiomics-based computed tomography urography image analysis for prediction of HER2 status in bladder cancer

Article References: Wu, B., Zhou, T., Hou, C., Mao, J., Lu, Z., Zhu, F., & Zhao, Z. (2026). Radiomics-based computed tomography urography image analysis for prediction of HER2 status in bladder cancer. BMC Medical Imaging. https://doi.org/10.1186/s12880-026-02758-6

Image Credits: AI Generated

DOI: 10.1186/s12880-026-02758-6

Keywords: bladder cancer, HER2, radiomics, CT urography, machine learning, random forest, LASSO, medical imaging, precision oncology, non-invasive diagnostics, BMC Medical Imaging, computed tomography

The authors call their framework HDPCBN, short for a hybrid dual attention-based pyramidal deep convolutional network combined with a deep belief network. The design philosophy is straightforward to describe but technically demanding to build. A pyramidal structure lets the network examine a CT image at multiple scales simultaneously, so that both fine local detail and broad anatomical context contribute to the final decision. This multi-scale view matters because liver tumors can appear as small nodules or as large lesions whose boundaries weave through surrounding vasculature, and no single receptive field size captures them all reliably.

The dual attention mechanism is the second pillar of the architecture. It operates along two complementary dimensions of the feature maps: the spatial dimension, which tells the model where in the image to look, and the channel dimension, which tells it which learned feature maps deserve the most weight. By gathering long-range relationships across both dimensions, the network can connect a suspicious texture patch in one region with contextual cues elsewhere in the scan, mimicking in a rough way how an experienced radiologist integrates local appearance with global anatomy. The authors report that this integration leads to precise tumor detection by learning local patterns and edges directly from the images.

Feature engineering still plays a role in the pipeline despite the end-to-end learning trend. The framework incorporates what the researchers term hybrid deep flow feature extraction, which gathers discriminative and textural characteristics of the tumor. The stated purpose is twofold: it reduces training complexity, and it leads to more accurate tumor detection. Texture is a clinically meaningful cue in liver imaging, since malignant lesions often disrupt the normal homogeneous echo or density pattern of hepatic tissue, and explicitly extracting textural features can stabilize learning when training data are limited.

The deep belief network component adds a generative flavor to the hybrid design. Deep belief networks, built from stacked restricted Boltzmann machines, were historically prized for their ability to learn hierarchical representations in an unsupervised manner before fine-tuning. In this framework, the belief network works alongside the pyramidal convolutional backbone, presumably refining the representation learned from the attention-weighted features before the final classification decision. The combination of convolutional feature extraction, attention-based recalibration, and belief-network-based representation learning is what earns the model its hybrid designation.

The reported numbers are the headline result. On the experimental evaluation, HDPCBN achieved a sensitivity of 97.89 percent, meaning it correctly identified nearly 98 of every 100 tumors presented to it. Specificity came in at 93.77 percent, indicating a reasonably low false alarm rate when scanning tissue that is actually healthy. Balanced accuracy, which averages sensitivity and specificity and is often preferred when class distributions are uneven, reached 95.83 percent, and the Macro F1-score, which harmonizes precision and recall across classes, was 96.67 percent. Overall accuracy stood at 96.52 percent. The authors state that these figures outperform the other state-of-the-art methods against which the model was compared.

Why do these particular metrics matter for clinical translation? Sensitivity is arguably the most safety-critical number in tumor screening, because a missed lesion can delay diagnosis and treatment of a life-threatening disease. A sensitivity approaching 98 percent suggests the model rarely lets a tumor slip past. Specificity guards against the opposite failure mode: excessive false positives would flood radiology workflows with unnecessary follow-up scans, biopsies, and patient anxiety. The balance the authors report, with both sensitivity and specificity above 93 percent, indicates the model is not simply trading one error type for the other.

The study also situates itself against the acknowledged limitations of prior approaches. Conventional liver tumor detection, the authors write, struggled with poor robustness, difficulties in identifying complex boundaries, and inconsistent segmentation. These are familiar complaints in the medical imaging literature. Robustness matters because CT scanners, reconstruction protocols, and patient anatomy vary widely, and a model tuned to one imaging distribution can degrade sharply on another. Boundary delineation is difficult when tumor margins fade gradually into surrounding parenchyma, and inconsistent segmentation undermines the quantitative measurements, such as lesion volume, that clinicians use to track disease progression.

The pyramidal and attentional components are aimed squarely at these failure modes. Multi-scale pyramidal processing gives the network redundant views of each structure, so a boundary that is ambiguous at one resolution may become clear at another. Spatial attention suppresses irrelevant background regions, while channel attention amplifies the feature maps that encode tumor-relevant texture and density signatures. Together they encourage the model to learn the intricate patterns of the tumor effectively, in the authors’ phrasing, and to maintain stable performance across the variability that undermines earlier systems.

Published as an open-access article with a permanent DOI, the study arrives as part of a broader wave of artificial intelligence tools moving toward clinical radiology. The authors declare no competing interests and note that the research received no specific funding. As with any reported benchmark, independent validation on external datasets and prospective clinical evaluation will be needed before such a model can assist diagnosis in practice. But the combination of high sensitivity, strong specificity, and an architecture explicitly designed to handle complex tumor boundaries makes HDPCBN a notable entry in the ongoing effort to give liver tumor detection the accuracy that patients with this chronic, life-threatening condition urgently require.

Subject of Research: A hybrid dual-attention pyramidal deep learning model for detecting liver tumors in CT images

Article Title: Hybrid dual attentional-based pyramidal deep learning model for liver tumor detection

Article References: Patil, B., & Veerashetty, S. (2026). Hybrid dual attentional-based pyramidal deep learning model for liver tumor detection. Scientific Reports. https://doi.org/10.1038/s41598-026-76482-0

Image Credits: AI Generated

DOI: 10.1038/s41598-026-76482-0

Keywords: liver tumor detection, deep learning, computed tomography, attention mechanism, medical imaging, segmentation, image processing, pyramidal network, deep belief network, cancer, artificial intelligence, Scientific Reports

The research team, led by Xianglan Zhou and Lei Shi of the hospital’s radiology department, developed a machine learning approach that combines two types of information: standard clinical characteristics and a technique called delta-radiomics, which captures how the texture and appearance of a tumor changes over time on imaging. Their goal was ambitious but practical. Rather than waiting for a tumor to progress and then performing an invasive biopsy to test for the T790M mutation, they wanted to predict the risk of that mutation emerging before first-line EGFR-TKI therapy was ever started.

The study included 285 patients with non-small cell lung cancer whose disease had progressed after first-line treatment with an EGFR tyrosine kinase inhibitor between January 2013 and September 2019. These patients were randomly divided into a training cohort of 213 individuals and a separate test cohort of 72, allowing the researchers to build their predictive models on one group and evaluate them honestly on another. Four distinct models were constructed and compared: one based purely on clinical characteristics, one on radiomics features extracted from non-contrast-enhanced CT scans, one on delta-radiomics features, and a fourth that combined clinical data with delta-radiomics.

Radiomics itself is a rapidly growing field that converts medical images into vast arrays of quantitative data. Rather than simply measuring the size of a tumor, radiomic algorithms extract hundreds of mathematical descriptors that characterize texture, shape, intensity patterns, and spatial relationships within the imaged tissue. Features derived from grey-level co-occurrence matrices, grey-level run-length matrices, and grey-level dependence matrices capture subtle patterns of pixel intensity that the human eye cannot perceive but that may reflect underlying biological properties such as cell density, necrosis, and vascular structure.

What makes delta-radiomics particularly powerful is its temporal dimension. Instead of analyzing a single scan, it computes the difference between radiomic features extracted from two time points, essentially quantifying how a tumor’s imaging phenotype evolves. This change over time may encode information about tumor heterogeneity and treatment response that a static snapshot cannot. In the context of this study, the delta approach allowed the machine learning models to detect imaging signatures associated with tumors that were biologically primed to develop the T790M resistance mechanism.

The results, measured on the independent test set, told a clear story. The clinical model alone achieved an area under the receiver operating characteristic curve, or AUC, of 0.70, with an accuracy of 66.7 percent. The NECT radiomics model performed worse, with an AUC of 0.63 and accuracy of 57.0 percent. The delta-radiomics model improved on both, reaching an AUC of 0.75 and accuracy of 72.2 percent. But the combined model, integrating clinical characteristics with delta-radiomics features, outperformed them all, achieving an AUC of 0.82 and an accuracy of 79.2 percent. Decision curve analysis, which evaluates the clinical net benefit of a predictive model across different threshold probabilities, further supported the combined model as the optimal choice.

One of the most significant contributions of this work lies not in the raw predictive numbers but in the effort to make the machine’s reasoning transparent. The researchers applied the Shapley additive explanations framework, commonly abbreviated as SHAP, to visualize and interpret how the model arrived at its predictions. SHAP, rooted in cooperative game theory, assigns each input feature a contribution value for every individual prediction, revealing which factors pushed the model toward predicting the presence or absence of the T790M mutation. This interpretability is critical in medicine, where clinicians are understandably reluctant to trust black-box algorithms that cannot explain themselves.

Through the SHAP analysis, the team identified ten significant features driving the model’s decisions: two clinical features and eight radiomic features. While the specific identities of these features reflect the particular dataset and modeling choices of this study, the broader implication is that measurable imaging characteristics, particularly those that change over the course of treatment, carry genuine predictive signal about the evolutionary trajectory of the tumor’s resistance mechanisms. This finding aligns with a growing body of evidence suggesting that the radiographic appearance of a tumor is a window into its genomic and microenvironmental state.

The clinical implications, if validated, could be substantial. Patients identified as high risk for developing the T790M mutation might be candidates for closer surveillance, earlier liquid biopsy testing, or alternative treatment sequencing strategies. Conversely, those predicted to be at low risk might avoid unnecessary interventions. The ability to anticipate resistance rather than react to it represents a meaningful shift in the management of EGFR-mutant lung cancer, where the emergence of T790M has historically been discovered only after disease progression has already occurred.

The authors are careful to note that their work represents a preliminary step rather than a finished clinical tool. The retrospective design, the single-center cohort, and the modest size of the test set all warrant caution, and the researchers explicitly state that further prospective multicentre validation is needed before the model can be applied in clinical practice. Nevertheless, the study demonstrates that the fusion of temporal imaging data with clinical variables, interpreted through explainable artificial intelligence, offers a viable path toward anticipating one of the most consequential resistance mechanisms in lung cancer. As radiomics and machine learning continue to mature, the humble CT scan may become not just a diagnostic record but a predictive instrument, reading the future of a tumor before that future arrives.

Subject of Research: Predicting acquired EGFR T790M resistance mutations in non-small cell lung cancer using delta-radiomics and clinical features with SHAP interpretability

Article Title: Predicting acquired T790M mutations in non-small cell lung cancer after EGFR-TKI therapy: integration of delta-radiomics and clinical characteristics with SHAP interpretation

Article References: Zhou, X., Shi, L., Lin, C., Zou, M., Sun, J., Song, Z., Wang, W., Ren, H., & Shi, L. (2026). Predicting acquired T790M mutations in non-small cell lung cancer after EGFR-TKI therapy: integration of delta-radiomics and clinical characteristics with SHAP interpretation. BMC Medical Imaging. https://doi.org/10.1186/s12880-026-02748-8

Image Credits: AI Generated

DOI: 10.1186/s12880-026-02748-8

Keywords: non-small cell lung cancer, EGFR-TKI, T790M mutation, delta-radiomics, machine learning, SHAP, computed tomography, drug resistance, predictive biomarkers, tumor heterogeneity, radiomics, precision oncology

The stakes in this diagnostic dilemma are far from academic. In the study, led by radiologists Lulu Liu, Yuanxin Ye, Fangxiao Lu, and corresponding author Haitao Jiang, the researchers assembled 116 patients whose chest masses were all smaller than 30 millimeters at their widest point. Eighty-six of those patients turned out to have anterior mediastinal cysts, and every single one of those cysts had been misdiagnosed as a thymoma before surgery. That means all 86 people underwent surgical resection of a lesion that, in hindsight, likely never needed to be removed. The remaining 30 patients had pathologically confirmed type B1 or B2 thymomas, subtypes of thymic epithelial tumors that sit in the middle of the WHO classification spectrum and are generally considered to carry a meaningful risk of invasion or recurrence.

Why does this confusion happen so often? Small anterior mediastinal cysts frequently do not behave like textbook cysts. A classic simple cyst should appear as a well-defined, homogeneous structure with fluid-like attenuation, essentially uniform dark gray pixels on a CT image. But many real-world cysts are complicated by hemorrhage, proteinaceous debris, infection, or thickening of their walls, which pushes their CT density values upward into the soft-tissue range where solid tumors live. Meanwhile, small thymomas can be surprisingly uniform and well-circumscribed, mimicking the smooth contours radiologists associate with benign lesions. When a lesion is under three centimeters, there is simply less tissue to interrogate, fewer internal architectural clues, and less room for the subtle enhancement patterns that usually separate fluid from solid tumor. The result is a diagnostic gray zone in which conservative management and surgery both feel risky.

To cut through that ambiguity, the research team turned to quantitative CT analysis, a method that replaces subjective visual assessment with precise measurements of pixel density, expressed in Hounsfield units, the standardized scale of CT attenuation. Three radiologists with 3, 9, and 25 years of experience independently reviewed the scans of every patient. For each lesion, they measured the long diameter and short diameter, and they recorded the mean, maximum, and minimum CT values along with the standard deviation of those values within regions of interest drawn over the nodule. Critically, they also drew regions of interest over the subscapularis muscle on the same image slice, using this muscle as an internal reference standard. Because muscle attenuation is relatively stable across patients and scanners, ratios calculated against it can correct for some of the variability introduced by different scanning protocols and patient body habitus.

From these raw measurements, the team derived a set of normalized parameters with abbreviated names that capture the physics of how tissue takes up iodinated contrast. The Relative Enhancement Ratio of the Nodule, or RERN, compares the change in CT value of the lesion after contrast administration with the enhancement of the reference muscle, quantifying how much blood supply the lesion appears to have. The Relative Heterogeneous Rate of the Nodule, or RHRN, compares the internal heterogeneity of the lesion, measured as the standard deviation of its CT values, against that of the muscle, providing a normalized index of how mixed the tissue composition is. Cysts, being fluid-filled, should enhance minimally and remain internally homogeneous, while solid thymomas typically show greater enhancement and greater internal variability. The Heterogeneous Degree parameters extended the same logic to the lesion and the muscle individually.

The statistical analysis proceeded in two stages. First, univariate analysis compared every measured and derived parameter between the cyst group and the thymoma group, and the results were consistent across all three readers regardless of experience level. Anterior mediastinal cysts showed significantly lower short diameters and significantly lower mean, maximum, and minimum CT values on both unenhanced and contrast-enhanced scans, with all comparisons reaching statistical significance at p less than 0.05. This consistency matters because a diagnostic feature that only one experienced reader can detect is of limited clinical value. Here, the quantitative signal was robust enough that a radiologist three years out of training extracted the same information as a colleague with a quarter century of practice.

Next, multivariate logistic regression identified which parameters carried independent diagnostic information when all variables were considered together. Three emerged as independent predictors: the short diameter of the lesion, the maximum CT value on the contrast-enhanced scan, and the Relative Heterogeneous Rate of the Nodule on enhanced CT. The short diameter finding is intuitive, since cysts in this cohort tended to be more compressed or rounded, while the enhanced maximum CT value reflects the densest enhancing focus within the lesion, a direct probe of vascularity. The RHRN, meanwhile, captures internal texture in a way that is normalized to each patient’s own muscle reference, making it less vulnerable to scanner-to-scanner variation than raw standard deviations.

The headline result concerns diagnostic performance, quantified through receiver operating characteristic analysis. Among all the quantitative parameters tested, the maximum CT value on the enhanced scan delivered the highest diagnostic accuracy, achieving a pooled area under the curve of 0.911. In practical terms, an AUC above 0.9 is generally regarded as excellent, meaning the parameter discriminates cysts from thymomas far better than a coin flip and approaching the performance of near-perfect tests. Equally striking was the reproducibility: the inter-observer intraclass correlation coefficient for this parameter was 0.980, with a 95 percent confidence interval of 0.973 to 0.986, indicating near-perfect agreement among the three readers. Numbers this high suggest that the measurement itself, not the skill of the person drawing the regions of interest, is doing the diagnostic work.

The clinical implications of these findings extend well beyond the radiology reading room. For a patient with a small anterior mediastinal mass, the current default in many centers is surgical resection, often via thoracoscopy, because thymomas cannot be confidently excluded. Surgery, even when minimally invasive, carries risks of bleeding, infection, nerve injury, and prolonged recovery, and it generates substantial cost and anxiety. If quantitative CT parameters can reliably flag a lesion as a benign cyst, clinicians could offer active surveillance instead, reserving intervention for lesions that grow or change. The authors explicitly frame their work as a step toward reducing unnecessary surgical resection of anterior mediastinal cysts, and the fact that all 86 cyst patients in their cohort were preoperatively misdiagnosed underscores how real that problem is.

There are, of course, caveats worth keeping in view. The study was retrospective and conducted at a single institution, and its cyst cohort was enriched by the very fact of misdiagnosis, since only cysts that went to surgery and yielded pathology could be included. Prospective validation in independent, multi-center cohorts will be needed before these thresholds can be confidently embedded into clinical guidelines. Nevertheless, the study adds to a growing movement in radiology toward quantitative, reproducible imaging biomarkers that reduce dependence on subjective pattern recognition. As machine learning and radiomics continue to reshape diagnostic imaging, this work offers a reminder that sometimes the most powerful tools are the simplest ones: a few carefully placed regions of interest, a reference muscle, and the humble Hounsfield unit, measured the same way by every reader who looks.

Subject of Research: Quantitative CT parameters for differentiating small anterior mediastinal cysts from type B1 and B2 thymomas

Article Title: CT quantitative parameters in differential diagnosis of anterior mediastinal cysts and thymomas of types B1 and B2 less than 30 mm

Article References: Liu, L., Ye, Y., Lu, F., & Jiang, H. (2026). CT quantitative parameters in differential diagnosis of anterior mediastinal cysts and thymomas of types B1 and B2 less than 30 mm. BMC Medical Imaging. https://doi.org/10.1186/s12880-026-02739-9

Image Credits: AI Generated

DOI: 10.1186/s12880-026-02739-9

Keywords: computed tomography, anterior mediastinal cyst, thymoma, radiology, medical imaging, Hounsfield units, contrast enhancement, diagnostic accuracy, ROC analysis, thymic epithelial tumors, quantitative imaging, chest surgery

The stakes are higher than they might appear. More than 2,000 amphibian species are listed as endangered, and populations are declining worldwide, making captive breeding and reintroduction programs critical lifelines. Knowing the sex of individual animals is essential for pairing breeders, managing genetic diversity, and timing reintroductions. Yet many amphibians show no external signs of sex until maturity, and even adults can deceive. Body size overlaps substantially between the sexes, offering only about 70 to 75 percent accuracy in adult frogs. Hormone measurements from blood, urine, or feces can be thrown off by seasonal cycles, stress, or captive housing conditions. Nuptial pads on males’ thumbs and other secondary traits often appear only around the breeding season, and the absence of environmental cues in captivity can suppress them entirely.

Genetic testing might seem like the obvious answer, but amphibian genetics complicates rather than simplifies matters. Most amphibians lack distinct sex chromosomes of the kind that make molecular sexing routine in mammals and birds, and polyploidy is common, so researchers must develop species-specific genetic markers before a single swab can be read. Worse, genotypic sex can be overridden by environmental influences during embryonic or larval development, meaning an animal’s chromosomes and its actual, functional sex may not match. For conservation programs that need to know which animals will lay eggs and which will fertilize them, phenotypic sex—the sex written in the gonads—is what truly matters.

That reality has long pushed veterinarians toward direct examination of the gonads, typically through coelioscopy, a surgical technique in which a tiny camera is inserted into the body cavity. Coelioscopy is reliable, but it carries financial costs, health risks, and ethical concerns, particularly for small and delicate species. Non-invasive imaging has shown promise in adult amphibians: ultrasonography has been used to identify gravid females and assess reproductive status, and a handful of studies have used CT and MRI to visualize reproductive organs in mature animals. But no peer-reviewed study had formally tested whether these techniques could work in juvenile amphibians, whose gonads are minuscule and whose bodies are barely larger than a coin.

The Hungarian team, led by Nikolett Ujhegyi and Veronika Bókony of the HUN-REN Centre for Agricultural Research, tackled the question using 19 healthy agile frogs (Rana dalmatina) raised in captivity from eggs collected in the wild. The animals were examined at two ages—1.8 and 2.5 years—spanning the transition to sexual maturity, which in this species arrives around age two in males and age three in females. At the first imaging session the frogs averaged just 6.74 grams in body weight and about 41 millimeters in snout-vent length, with no visible secondary sexual characteristics in any individual. Crucially, every examiner was blind to the sex of the animals being scanned, and all individuals’ gonads were later confirmed by coelioscopy, giving the imaging results a gold-standard benchmark.

The imaging lineup ranged from the everyday to the exotic. Ultrasound was performed with a standard veterinary unit of the kind found in small-animal clinics, using a curved array transducer with a frequency range of 3.0 to 11.0 MHz. CT scans were acquired on a human dental cone-beam machine with 450-micrometer resolution—so generous in field of view that the team built a handmade three-level stand allowing up to nine frogs to be scanned simultaneously. MRI was conducted on a 3-Tesla NanoScan PET/MRI system with a 600 mT/m gradient, using a T1-weighted three-dimensional gradient echo sequence optimized through trial of multiple sequence types. Anesthesia was tailored to each procedure: short baths of buffered MS-222 for CT and coelioscopy, and longer-acting intramuscular alfaxalone for MRI sessions that could run over an hour and a half.

The results drew a sharp line between what each machine could and could not see. Ultrasound clearly revealed eggs in a formalin-preserved gravid female used as a reference, and in the live animals it picked up intestines, lungs, and a beating heart—but parenchymal organs, including gonads, remained indistinct in the juveniles. By autumn, when one female had developed mature eggs, ultrasonography correctly identified her, yet the image of an immature female was indistinguishable from that of a mature male. The dental CT scanner fared worse: bones and air-filled structures were recognizable, but no soft-tissue organs could be distinguished at all, and the method was abandoned for mature animals. The 110-kilovolt tube voltage, suitable for dental work, provided too little contrast between soft tissues to reveal anything as subtle as a juvenile frog’s gonad.

MRI, by contrast, delivered a genuine surprise. In the spring scans, when none of the frogs showed any external sign of sex, the testes were already identifiable in juvenile males—structures roughly two millimeters long that no other modality could resolve. The team could also map the heart, liver, lungs, stomach, gallbladder, kidneys, muscles, vertebrae, and spinal cord. By autumn, MRI correctly sexed a mature male and a mature female whose ovaries had developed, though it failed on a female whose ovaries were still immature. The ovaries of young females remained invisible across every method and every session, a limitation the authors attribute to the fact that undeveloped ovaries offer too little signal and too little size for current clinical resolutions to distinguish.

The comparison with earlier studies is instructive. Previous ultrasound successes in identifying testes involved either much larger animals—African clawed frogs reaching up to 140 millimeters—or high-resolution equipment with transducer frequencies of 17 to 22 MHz, far beyond the 3-to-11 MHz range of typical clinic machines. In those studies, testes resembled kidneys and could be told apart only by position, size, and edge irregularity, distinctions that required an experienced ultrasonographer. The agile frogs in this study had testes of roughly two millimeters at two years of age, growing to about four millimeters by maturity—far below the five-to-ten-millimeter range that made testes visible in larger species. Body size, the authors conclude, may be the decisive constraint on ultrasound sexing in small anurans.

The team’s recommendations are pragmatic. For mature females, ultrasound is the clear winner: it is fast, widely available, requires no sedation, and reliably reveals developed ovaries even in small-bodied frogs. For immature animals, no tested method is fully reliable, though MRI’s ability to detect juvenile testes suggests that optimized protocols—ideally tested on animals of known sex—could push the technology further. The authors also flag welfare concerns that deserve attention: MRI scanning time is limited by anesthesia duration, and the acoustic noise of magnetic resonance imaging, known to harm experimental animals in other taxa, has never been assessed in amphibians whose hearing plays a central role in reproduction. Contrast-enhanced CT, which improved organ visualization in prior studies, was deliberately avoided here because the frogs were part of a long-term experiment and the safety of contrast agents in amphibians is unknown. The path forward, the researchers argue, lies in exploring high-frequency ultrasound—already proven in large, mature frogs of both sexes—as the most accessible and least risky route to cracking the juvenile sexing problem, a capability that could reshape how conservationists manage the thousands of amphibian species now fighting for survival.

Subject of Research: Non-invasive imaging techniques for determining phenotypic sex in juvenile amphibians

Article Title: Testing minimally invasive imaging methods for phenotypic sex determination in immature frogs

Article References: Ujhegyi, N., Bókony, V., Ziszisz, Á., Kovács, N., Horváth, I., Rozsnyik, M. Z., Limboczki, R., Lini, Á. B., Berkei, G., Nemesházi, E., Kásler, A., Mikó, Z., Máthé, D., Szigeti, K., & Balogh, E. (2026). Testing minimally invasive imaging methods for phenotypic sex determination in immature frogs. Frontiers in Veterinary Science, 13, Article 1934243. https://doi.org/10.3389/fvets.2026.1934243

Image Credits: AI Generated

DOI: 10.3389/fvets.2026.1934243

Keywords: amphibians, frogs, sex determination, ultrasound, MRI, computed tomography, veterinary imaging, conservation, Rana dalmatina, gonads, juvenile animals, reproductive biology