The study, published in BMC Medical Imaging, was led by Jun Liao, Mengting Xu and Ruimin Li, with corresponding author Hongna Tan, at the People’s Hospital of Zhengzhou University and Henan Provincial People’s Hospital, together with collaborators at Fudan University Shanghai Cancer Center. The researchers set out to tackle a long-standing blind spot in breast cancer care: the axillary lymph nodes, the first and most common destination for breast cancer cells leaving the tumor, are notoriously difficult to assess with imaging alone. Yet knowing whether chemotherapy has eradicated the disease there — a state clinicians call pathological complete response, or pCR — is exactly the information that determines whether a patient can safely avoid a full axillary lymph node dissection, an operation that removes most of the lymph nodes under the arm and is a leading cause of lifelong arm swelling, known as lymphedema.

Neoadjuvant chemotherapy — drugs given before surgery to shrink the tumor — has transformed breast cancer treatment over the past two decades. When it works completely, obliterating both the breast tumor and any nodal metastases, patients with node-positive disease can often be managed with far less invasive surgery. The problem is verification. Sentinel lymph node biopsy, the standard minimally invasive check, can miss residual disease, and many centers still default to full axillary dissection for patients who had node-positive disease at diagnosis, precisely because they cannot confidently rule out remaining cancer. The result, the authors note, is a substantial rate of unnecessary operations: in their retrospective simulation, a conventional approach would have led to axillary lymph node dissection in roughly 40.7 percent of patients who did not actually need it.

The researchers’ answer was to build a deep learning system that looks at more of the picture than previous attempts. Their model ingests dynamic contrast-enhanced MRI — the workhorse breast imaging technique in which a gadolinium contrast agent reveals how blood flows through tissue over time — from multiple regions simultaneously: the primary tumor in the breast and the involved axillary lymph nodes. Crucially, they compared two architectural philosophies. A 2D model processes each MRI slice in isolation, treating every cross-section as a separate image. A 2.5D model stacks adjacent slices together, feeding the network a thin slab of tissue at a time so it can perceive features that only make sense in three dimensions — the way contrast washes in and out of a lesion, the shape of a node’s cortex, the texture of its interior across depth.

The difference proved decisive. In a validation set of 91 patients held out from training, the 2.5D tumor-only model achieved an area under the receiver operating characteristic curve, or AUC, of 0.797, comfortably ahead of the 0.706 posted by its 2D counterpart. When the model was given both the tumor and the lymph nodes as separate input channels, performance climbed further: the 2.5D tumor-plus-node model reached an AUC of 0.834, versus 0.815 for the 2D version. The AUC is a standard measure of diagnostic discrimination — a value of 1.0 means perfect separation between patients who achieved pCR and those who did not, while 0.5 is equivalent to a coin flip. Values in the low 0.80s represent clinically meaningful predictive power.

The team then went a step further, fusing the imaging-derived features with clinicopathological data — estrogen receptor status, HER2 status and tumor grade, the three molecular and cellular characteristics that emerged from their statistical analysis as independent predictors of nodal response. The combined model, which the researchers call the 2.5D tumor–ALN–clinicopathologic model, delivered the best performance of anything they tested: an AUC of 0.861 in the validation cohort. Feature selection was rigorous, using the Mann–Whitney U test, Spearman correlation, a max-relevance and min-redundancy filter, and the least absolute shrinkage and selection operator, a technique known as LASSO that prunes variables down to the most informative subset while guarding against overfitting.

Perhaps the most striking result is not the raw accuracy but what it could mean in practice. The researchers ran a retrospective simulation: if the model’s predictions had been used to guide axillary management, the estimated rate of unnecessary axillary lymph node dissection would have fallen from 40.7 percent to 8.8 percent, while the estimated overall benefit rate — patients correctly spared an operation or correctly flagged for one — would have risen from 59.3 percent to 74.7 percent. Those are modeled estimates, not outcomes from a prospective trial, and the authors are careful to frame them as such. But the direction of the effect is hard to ignore: a tool that reads images already being acquired in routine care could, in principle, prevent the majority of avoidable node dissections.

The study cohort comprised 305 patients with invasive breast cancer and confirmed metastasis to the ipsilateral axillary lymph nodes, randomly split into a training set of 214 and a validation set of 91. Among them, 46.6 percent — 142 patients — achieved pathological complete response in the nodes after neoadjuvant chemotherapy, a proportion consistent with modern regimens in biologically favorable disease. The retrospective design, approved by the ethics committee of Henan Provincial People’s Hospital under Declaration of Helsinki protocols with informed consent waived, means the model has not yet been tested prospectively on patients whose treatment decisions were actually influenced by its output. That step — a validation study where the algorithm’s prediction is available to surgeons before they operate — is the necessary next chapter.

The work also reflects a broader shift in oncology imaging. Rather than asking a radiologist to eyeball whether a lymph node looks smaller or less bright on a follow-up scan, deep learning models can extract quantitative signatures of treatment response — patterns of enhancement kinetics, texture heterogeneity, spatial relationships between tumor and node — that are invisible or ambiguous to the human eye. Multichannel architectures, which feed different anatomical regions or image sequences into the same network as parallel inputs, are particularly well suited to this problem because nodal response and primary tumor response are related but not identical phenomena; a patient’s breast tumor may melt away while microscopic disease persists in the nodes, and vice versa. By modeling both regions jointly, the network can learn the interplay that single-region models miss.

For patients, the near-term significance is straightforward. Axillary lymph node dissection carries real, lasting costs: lymphedema, numbness, restricted shoulder mobility and increased infection risk in the affected arm. Any tool that can reliably identify which node-positive patients have achieved complete nodal clearance — without putting them under the knife to find out — would change the calculus of post-chemotherapy surgery. The 2.5D multichannel model described here is not yet that tool, but it is a credible step toward it, built on imaging that most breast cancer patients already receive as part of standard care. If prospective validation confirms the retrospective numbers, the algorithm could move from research code to clinical decision support, giving surgeons the confidence to offer less invasive nodal management to the patients who no longer need the more radical option.

Subject of Research: Deep learning prediction of axillary pathological complete response after neoadjuvant chemotherapy in breast cancer using multiregional DCE-MRI

Article Title: Multichannel deep learning using multiregional DCE-MRI to predict axillary pathological complete response after neoadjuvant chemotherapy in breast cancer

Article References: Liao, J., Xu, M., Li, R., Li, S., Cao, Z., Wang, D., Li, Y., Wang, M., & Tan, H. (2026). Multichannel deep learning using multiregional DCE-MRI to predict axillary pathological complete response after neoadjuvant chemotherapy in breast cancer. BMC Medical Imaging. https://doi.org/10.1186/s12880-026-02736-y

Image Credits: AI Generated

DOI: 10.1186/s12880-026-02736-y

Keywords: breast cancer, deep learning, DCE-MRI, axillary lymph nodes, pathological complete response, neoadjuvant chemotherapy, artificial intelligence, radiology, lymph node dissection, medical imaging, oncology, predictive modeling

The clinical problem the researchers tackled is deceptively simple to state but stubbornly difficult to solve. When a woman is diagnosed with invasive breast cancer, determining whether the disease has reached the regional lymph nodes is central to staging, adjuvant therapy planning, and surgical strategy. The current standard for patients whose nodes feel normal and look normal on ultrasound is the sentinel lymph node biopsy, a technique that identifies and removes the first draining node or nodes so they can be examined under the microscope. Yet even this minimally invasive procedure carries real costs: lymphedema, seroma formation, numbness, restricted shoulder mobility, and the anxiety of a second operation when metastases are found. For a substantial fraction of patients, that biopsy ultimately confirms no nodal involvement at all, meaning the procedure was, from a purely diagnostic standpoint, avoidable.

The Madrid cohort comprised 540 consecutive patients with invasive HR+/HER2- breast cancer treated between January 2019 and June 2024, all of whom underwent breast surgery with formal axillary staging. This tumor subtype is the single largest biological category of breast cancer, driven by estrogen or progesterone signaling rather than HER2 amplification, and typically managed with endocrine therapy, chemotherapy in selected cases, and surgery. Because these tumors often behave in a more indolent fashion than triple-negative or HER2-positive disease, the question of which patients can safely forgo parts of the axillary workup is particularly pressing. In this cohort, 173 patients, or 32.0 percent, turned out to have nodal disease despite being classified as clinically node-negative before surgery, a figure that underscores how much microscopic spread evades conventional preoperative assessment.

To build the prediction model, the team assembled a rich set of preoperative variables spanning clinical examination, imaging, and core needle biopsy pathology: tumor size, multifocality or multicentricity, histological type and grade, lymphovascular invasion, perineural invasion, hormone receptor and Ki-67 values, and the findings of axillary ultrasound. Rather than relying on univariate associations, which can be confounded by correlations among variables, the investigators used multivariable logistic regression with LASSO regularization. LASSO, short for least absolute shrinkage and selection operator, is a statistical technique that penalizes model complexity, shrinking weak coefficients toward zero and effectively eliminating predictors that add little independent information. This approach guards against overfitting, the failure mode in which a model memorizes the idiosyncrasies of its development dataset and then performs poorly on new patients.

The variables that survived LASSO selection tell a coherent biological story. By far the strongest predictor was a suspicious axillary ultrasound, which carried an odds ratio of 16.42, meaning patients with abnormal-appearing nodes on imaging had more than a sixteenfold increase in the odds of harboring metastases compared with those whose ultrasound was unremarkable. Lymphovascular invasion on the preoperative biopsy, an indication that tumor cells have already entered lymphatic or blood vessels within the primary tumor, roughly doubled the odds at an odds ratio of 2.61. Each additional millimeter of tumor size increased the odds by about 4 percent, and multifocal or multicentric disease, where multiple tumor foci are present in the breast, raised the odds by 88 percent. Histological grade was retained in the final model for reasons of clinical relevance even though its statistical contribution was more modest.

Performance metrics matter as much as the predictors themselves, and here the nomogram delivered solid numbers. Discrimination, the model’s ability to separate patients who have nodal disease from those who do not, was quantified by the area under the receiver operating characteristic curve, which reached 0.83 with a 95 percent confidence interval of 0.79 to 0.87. In practical terms, an AUC of 0.83 means that if the tool were given one patient with nodal involvement and one without, it would assign the higher risk score to the correct patient roughly 83 percent of the time, a level generally regarded as good for a clinical prediction model built on routine preoperative data. Calibration, which asks whether predicted probabilities match observed frequencies across the risk spectrum, was equally reassuring: the expected-to-observed ratio was 1.002, essentially perfect, and the Brier score, a composite measure combining discrimination and calibration, was 0.135, comfortably below the 0.25 that would correspond to uninformative guessing.

A nomogram translates these regression coefficients into a visual scoring system that clinicians can use at the bedside. Each predictor is assigned a point value on a scale, the points for all variables are summed, and the total maps onto a predicted probability of nodal involvement. The Madrid team went further by calculating diagnostic performance across multiple probability thresholds, reporting positive and negative predictive values at each cut-off. This threshold analysis is what makes the tool actionable rather than merely descriptive: a hospital could, for example, define a low-risk band below which sentinel biopsy might be omitted or deferred, or a high-risk band above which more intensive axillary evaluation or direct discussion of nodal therapy could be considered. The authors explicitly frame the nomogram as a support for individualized risk stratification within the broader movement toward axillary surgical de-escalation.

That de-escalation movement has been reshaping breast surgery for two decades. Following landmark trials such as ACOSOG Z0011, which showed that many women with limited sentinel node metastases who undergo breast-conserving therapy do not benefit from completion axillary lymph node dissection, guidelines have progressively relaxed the requirement for radical nodal surgery in selected patients. More recently, trials of omitting sentinel biopsy altogether in older, low-risk patients have gained traction. The HR+/HER2- subtype is a natural focus for these efforts because modern systemic therapy, including endocrine treatment and CDK4/6 inhibitors for higher-risk disease, exerts systemic control regardless of nodal status, while the prognostic value of detecting a single micrometastasis has become increasingly debatable. A reliable preoperative risk estimate feeds directly into these shared decision-making conversations between surgeon and patient.

The study’s limitations are the ones that typically attend retrospective, single-institution models, and the authors are candid about them. All 540 patients came from one Madrid hospital, raising the possibility that referral patterns, imaging protocols, or pathology practices specific to that center could limit generalizability. The retrospective design means some variables, such as tumor-infiltrating lymphocytes or molecular assays not routinely ordered preoperatively, could not be incorporated. Most importantly, the model has not yet been tested on patients outside its development cohort. External validation, ideally in prospective multicenter cohorts drawn from different health systems, is required before any clinical implementation, and the authors state this requirement explicitly in their conclusions. History is littered with prediction models that performed beautifully in derivation and faded on external testing, which is why the field increasingly demands validation before publication of clinical tools is celebrated.

Even with those caveats, the contribution is timely and practical. Roughly one in three clinically node-negative HR+/HER2- patients in this cohort had occult nodal disease, and the strongest signal, the axillary ultrasound, is already obtained in most modern breast units, meaning the nomogram requires no new tests, no additional cost, and no delay to surgery. If external validation confirms the Madrid results, the tool could help identify the substantial minority of patients whose probability of nodal involvement is so low that even a sentinel procedure might reasonably be omitted, sparing them the attendant risks of lymphedema and nerve injury. Conversely, it could flag patients whose risk justifies a more thorough preoperative discussion about axillary management. In an era when precision oncology is often equated with genomic sequencing, this study is a reminder that careful statistical modeling of everyday clinical variables can still move the needle on surgical care, one calculated probability at a time.

Subject of Research: Development of a preoperative nomogram predicting axillary lymph node involvement in clinically node-negative HR+/HER2- breast cancer

Article Title: A preoperative nomogram to predict axillary lymph node involvement in clinically node-negative HR+/HER2- breast cancer

Article References: Carrillo-Peña, J., Osorio-Silla, I., Mahillo-Fernández, I., Sánchez De Molina-Rampérez, M. L., Escanciano-Escanciano, M., Pastor-Peinado, P., Guadalajara, H., García-Olmo, D., & Villarejo-Campos, P. (2026). A preoperative nomogram to predict axillary lymph node involvement in clinically node-negative HR+/HER2- breast cancer. BMC Cancer. https://doi.org/10.1186/s12885-026-17128-2

Image Credits: AI Generated

DOI: 10.1186/s12885-026-17128-2

Keywords: breast cancer, axillary lymph nodes, nomogram, sentinel lymph node biopsy, HR+/HER2-, surgical de-escalation, lymphovascular invasion, axillary ultrasound, prediction model, LASSO regression, risk stratification, BMC Cancer

The clinical motivation behind the work is straightforward but sobering. Breast cancer incidence and mortality have risen over the past decade worldwide, and survival improves dramatically when the disease is caught early. Mammography remains the mainstay imaging modality for early detection, and the standard medio-lateral oblique view captures three distinct regions in a single image: the breast region, the pectoral region, and the background. Radiologists, however, frequently face ambiguity when examining the pectoral region because both normal and abnormal masses and lymph nodes can appear there. Normal axillary lymph nodes are typically small and oval shaped, while abnormal ones tend to be dense, round, and larger than two centimeters. Because the parenchyma tissues of the breast and the pectoral muscle look so similar on a mammogram, computerized systems that leave the muscle in the frame often confuse the two, which is precisely why most algorithms simply remove the pectoral muscle and never look at it again.

The new framework refuses to throw that region away. Instead, it begins by suppressing the background of the image and isolating the pectoral muscle using a segmentation strategy built on position information, granular computing, rough set approximation, and an ant colony algorithm, refined in the team’s earlier research. Because these techniques produce only a discontinuous boundary on the CBIS-DDSM dataset, the authors added a line fitting step, essentially a simple linear regression that draws a straight line through the scattered boundary points to reconstruct the characteristic triangular contour of the muscle. The image is scanned from the top left corner, pixel coordinates are collected from the upper three-quarters of the frame, and the equation of a straight line is fitted to produce a clean, continuous segmentation. Once the pectoral muscle is isolated, the pipeline applies a three-by-three median filter to suppress noise, then enhances the contrast of the region using Contrast Limited Adaptive Histogram Equalization and a de-correlation stretch, both of which prepare the image for the more delicate steps that follow.

The enhancement matters because the pectoral muscle is composed of dense tissues with high intensity values, and masses and lymph nodes embedded within it often share those same high intensities with minimal contrast separating them from their surroundings. This ambiguity is where the fuzzy inference system enters. Rather than relying on classical edge detectors, which demand precise gradient calculations and struggle with low-contrast imagery, the fuzzy system embraces uncertainty. The researchers computed gradients in the x and y directions for the segmented muscle, convolved those gradient images with the enhanced image, and then passed the results through a fuzzy logic engine. Pixels were assigned to black and white fuzzy classes using triangular membership functions, chosen for their computational simplicity and their ability to capture smooth transitions between pixels, while Gaussian membership functions maximized intensities at edge regions. Two empirically constructed rules drive the decisions: if both x and y gradient values are zero, the output pixel receives maximum intensity, marking an edge; if either gradient is nonzero, the output receives minimum intensity. The result is a fuzzy edge image in which tissue boundaries inside the muscle stand out clearly despite the noise and imprecision inherent in mammographic data.

With the edges highlighted, the final detection stage hands the fuzzy edge image to the KAZE feature detector, a two-dimensional feature detection method that operates in a nonlinear scale space, in contrast to the linear Gaussian diffusion used by better-known detectors such as SIFT and SURF. KAZE constructs its scale space by solving a nonlinear diffusion equation in which a conductivity function, typically a Perona-Malik formulation, controls how strongly the diffusion acts at each location. This nonlinearity allows the algorithm to preserve well-defined boundaries of masses and lymph nodes, reduce noise, and retain distinctive contours without blurring away the very features that matter. Keypoints are detected by computing the scale-normalized determinant of the Hessian matrix from second-order spatial derivatives, and local maxima across both space and scale identify salient feature points. A rotationally invariant descriptor is then built for each keypoint by estimating its dominant orientation from first-order derivatives and aggregating weighted sums of those derivatives over local patches, normalized to unit length for contrast invariance.

Because the number and distribution of KAZE keypoints vary considerably across images, the researchers filtered them by response strength, retaining only the most significant ones. These strong keypoints reliably correspond to breast masses and axillary lymph nodes located near the pectoral muscle. The team validated the approach on the Curated Breast Imaging Subset of the Digital Database for Screening Mammography, a publicly available benchmark containing 2,620 images of which 292 medio-lateral oblique views contain masses, and on a private organization dataset of 240 medio-lateral oblique images. Ground truth segmentations were not supplied with the datasets for the pectoral muscle, so they were manually marked under the supervision of a consultant radiologist. Detection ground truths came from the dataset’s binary mass masks and, for the lymph nodes, from expert radiologist annotations provided as center-and-radius markings.

The quantitative results are striking. On the CBIS-DDSM dataset, segmentation of the pectoral muscle achieved 95.26 percent accuracy, while the private dataset yielded 92.11 percent. For detection, 38 images from CBIS-DDSM containing masses or lymph nodes in the pectoral region produced a detection accuracy of 97.36 percent, and the 27 relevant images from the private dataset produced 88.88 percent, for an average of roughly 93.12 percent across both. Measured against the total number of individual masses and nodes, accuracy was 86.04 percent on the public dataset and 70.58 percent on the private one. Because no false positives appeared in the detection results, precision reached 100 percent on both datasets, while recall reflected missed detections, yielding F1-scores of 92.50 percent for CBIS-DDSM and 82.80 percent for the private set. The detected locations were verified by comparing the centroid of each detection against its ground truth counterpart, with detections counted as correct when the coordinate differences stayed within a threshold factor of ten.

What makes these numbers particularly notable is the absence of any direct competitor. The authors report that a thorough search of the literature found no baseline algorithms for automatic detection of masses or axillary lymph nodes within the pectoral muscle, because nearly all prior abnormality-detection work deliberately excludes that region. Earlier pectoral muscle research focused almost entirely on removing the muscle cleanly, using methods ranging from thresholding and region growing to active contours, genetic algorithms, polynomial fitting, and single-sided edge marking. Mass detection studies, meanwhile, deployed region growing with neural networks, morphological thresholding, wavelet transforms, particle swarm optimization, and dual-stage adaptive thresholding, but always within the breast region proper. By turning the pectoral muscle from a discarded artifact into a region of clinical interest, the study opens a direction that the existing literature has barely touched, even though mammographic studies have long documented that abnormalities can reside there and that lymph node status is crucial for grading cancer and optimizing treatment.

The authors are candid about the current limitations. The method can detect only one mass and one axillary lymph node at a time, so some lesions are missed when multiple abnormalities share a frame, and the approach requires parameter readjustment to balance performance across datasets with different characteristics. Future work, they write, will involve larger datasets and an extension to multiple simultaneous detections. Even so, the pipeline demonstrates that a combination of classical segmentation, fuzzy edge reasoning, and nonlinear scale-space feature detection can surface clinically meaningful signs where conventional systems see nothing but tissue to be cropped away. If refined and validated at scale, such a tool could give radiologists an automated second look at the pectoral region, supporting earlier grading of breast cancer and helping to catch signs of spread before they are missed between the lines of a standard screening read.

Subject of Research: Automated detection of axillary lymph nodes and masses in the pectoral muscle region of mammograms using fuzzy logic and KAZE feature detection

Article Title: Detection of axillary lymph nodes and masses in pectoral region of mammograms using fuzzy logic and KAZE techniques

Article References: Divyashree, B. V., & Kumar, G. H. (2026). Detection of axillary lymph nodes and masses in pectoral region of mammograms using fuzzy logic and KAZE techniques. Discover Informatics, 1(1), Article 7. https://doi.org/10.1007/s44564-026-00006-1

Image Credits: AI Generated

DOI: 10.1007/s44564-026-00006-1

Keywords: mammography, breast cancer, axillary lymph nodes, pectoral muscle, fuzzy inference system, KAZE feature detector, computer-aided diagnosis, image segmentation, CBIS-DDSM, edge detection, CLAHE, medical imaging