The horse was a stallion used for flat racing and was evaluated in Uruguay from August through November 2023. Its initial history included intermittent low-grade fever, mild inappetence following competitions and subtle weight loss. During the early stages of illness, the horse remained generally bright, retained its appetite and produced feces of normal consistency. Over approximately three months, it experienced recurrent fever, progressive weight loss of about 25 kilograms and persistent hypoalbuminemia, prompting an extensive diagnostic evaluation for the cause of its clinical signs.

Serial complete blood counts and serum biochemical tests showed progressive hypoproteinemia and hypoalbuminemia without leukocytosis. Parasitological examination of feces detected a low burden of strongyle-type eggs, measured at 20 eggs per gram. Thoracic and abdominal ultrasonography revealed transient splenomegaly and mild pleural irregularities, but no abdominal mass or effusion was detected. Cytology of bronchoalveolar lavage fluid showed 59% macrophages, 39% lymphocytes and 2% eosinophils. Activated macrophages and multinucleated giant cells were considered consistent with chronic inflammatory changes, while no intracellular or extracellular bacteria were identified. Urine cultures, head radiographs and repeated viral and hemoparasitic screenings were negative.

Gastroscopy was performed approximately one week before the horse’s death, following a 24-hour fast. The examination documented incomplete gastric emptying, but the gastric mucosa appeared macroscopically normal, without a visible mass, ulceration or active bleeding. The horse was treated with antimicrobial therapy, beginning with ceftiofur and later enrofloxacin and metronidazole, along with supportive care and intravenous flunixin meglumine as needed for pyrexia. On November 16, it developed a higher fever, reaching 40 degrees Celsius, mild depression and decreased feed intake. Thoracic radiographs showed a bronchial-interstitial pattern, bronchiectasis and a large, well-defined structure consistent with a pulmonary abscess. The horse was euthanized and referred for necropsy at the veterinary pathology unit in Montevideo.

At necropsy, the mass was found within ingested feed, protruding from the wall of the nonglandular stomach. It was generally oval and soft, measuring 20 by 11 by 11 centimeters. Its external surface was brown, while the cut surface was grayish white with scattered black areas. Portions of the tumor were necrotic, its base was firmly attached to the stomach wall, and the surrounding wall was thickened. A portion of the specimen was fixed in 10% buffered neutral formalin and processed for routine histological examination. Sections were stained with hematoxylin and eosin, and additional 3-micrometer serial sections were prepared for immunohistochemistry using antibodies against alpha smooth muscle actin and CD117, also called c-Kit.

Microscopic examination showed that the tumor arose in close association with the normal smooth muscle layer. In these areas, the usual smooth muscle architecture was disrupted by neoplastic cell proliferation, connective tissue expansion and interstitial edema. Neoplastic cells accompanied by inflammatory infiltrates and edema extended into the underlying serosal layer, producing serosal thickening. The part of the tumor projecting into the gastric lumen was covered by squamous epithelium, whereas much of its exposed surface showed extensive necrosis and lymphocytic, plasmacytic and histiocytic inflammatory responses. Remnants of ingesta and clusters of bacteria were present in some necrotic areas.

The neoplastic population displayed considerable pleomorphism, including round, pleomorphic and spindle-shaped cells, with cytoplasm ranging from abundant to scant. Nuclei were round, oval or irregular, and mitotic figures were infrequent. Most cells were arranged in interwoven or interlacing fascicles. In several regions, spindle-shaped cells with abundant eosinophilic cytoplasm formed clusters resembling smooth muscle differentiation. Neoplastic cells were also observed within newly formed blood vessels inside the tumor, an observation that supported classification of the lesion as malignant. On serial sections, the tumor cells showed strong cytoplasmic staining for alpha smooth muscle actin. Blood vessels with positive labeling served as an internal positive control, while the neoplastic cells were negative for CD117. Together with the tissue architecture and the tumor’s location, this immunophenotype supported the diagnosis of primary gastric leiomyosarcoma.

Immunohistochemistry was important to the diagnosis because gastrointestinal stromal tumors and smooth muscle tumors can have overlapping appearances under routine microscopy. The source report notes that morphology alone can make these tumors difficult to distinguish, including in canine gastric tumors. CD117 staining detects most gastrointestinal stromal tumors, whereas alpha smooth muscle actin expression supports smooth muscle differentiation. The combination of alpha smooth muscle actin positivity and CD117 negativity in this horse, together with direct involvement of the gastric smooth muscle layer and smooth muscle-like cellular features, supported leiomyosarcoma rather than a gastrointestinal stromal tumor. The malignant designation was based on nuclear atypia and the presence of tumor cells in intratumoral vessels. Despite that vascular finding, pathologists identified no metastatic lesions in the liver, lungs or other organs examined.

The age of the horse makes the case unusual within the limited literature on equine gastric tumors. Gastric neoplasms have a reported incidence of 0.9% in horses, and horses with gastric neoplasms are reported to have a mean age of 18 years. Squamous cell carcinoma is the most frequently diagnosed form, while tumors derived from muscle are exceptionally rare. According to the report, only two cases of gastric leiomyoma and one earlier case of gastric leiomyosarcoma had been described in horses. The other reported gastric leiomyosarcoma occurred in a 12-year-old horse and was diagnosed from morphological findings without immunohistochemical confirmation. The present 4-year-old therefore provides a younger case documented with both histology and immunohistochemistry, but a single report cannot establish that these tumors are more common in young horses or reveal any incidence trend.

Location is another notable feature. The authors report that equine gastric smooth muscle tumors tend to arise in the nonglandular region, consistent with the site of this mass. The report also provides a cautious clinical interpretation: the authors presumed that the tumor was responsible for the horse’s persistent fever, protein-losing state and impaired gastric emptying. That explanation was not established experimentally, and the diagnostic work-up did not identify an abdominal mass on ultrasound or a visible tumor on gastroscopy. The horse’s euthanasia followed the development of a pulmonary abscess and respiratory abnormalities, rather than being an outcome directly demonstrated to result from the gastric tumor. As a single necropsy case with no separate dataset, the work cannot determine the tumor’s population frequency, risk factors or the full mechanism of systemic illness. Its central contribution is a detailed characterization of a rare gastric cancer in a young horse: a 20-centimeter smooth muscle-associated mass with alpha smooth muscle actin positivity, CD117 negativity, histologic evidence of malignancy and no detected distant metastases at necropsy.

Subject of Research: Veterinary case report of histopathological and immunohistochemical confirmation of gastric leiomyosarcoma in a 4-year-old horse.

Article Title: Case Report: Histological study of gastric leiomyosarcoma in a young horse

Article References: Guerrero, H., Varela, B., Morales, A., Larrañaga, C., Yozzi, V., Yamasaki, K., & Verdes, J. M. (2026). Case Report: Histological study of gastric leiomyosarcoma in a young horse. Frontiers in Veterinary Science, 13, 1979698. https://doi.org/10.3389/fvets.2026.1979698

Image Credits: AI Generated

DOI: 10.3389/fvets.2026.1979698

Keywords: equine oncology, gastric leiomyosarcoma, veterinary pathology, histopathology, immunohistochemistry, smooth muscle actin, CD117, horse, gastric tumor, case report, Case, Report

The research team, led by Luke Borst of Antech Diagnostics and collaborators at Mars Petcare Science and Diagnostics, WALTHAM Petcare Science Institute, and Mars digital technology groups, developed and validated a deep learning system called OncoPetNet. The system is an ensemble of three fully convolutional neural networks built on encoder-decoder architectures with skip connections, a design descended from the U-Net family of image segmentation models. Rather than detecting mitotic figures directly as objects, the model frames the problem as segmentation: it predicts a pixel mask marking candidate dividing cells, and deterministic post-processing steps then convert those masks into coordinates. The encoders draw on EfficientNet-b5, EfficientNet-b3, and SE-ResNext backbones pre-trained on ImageNet, allowing the network to leverage general visual features learned from millions of natural images before fine-tuning on tumor histology.

Deploying such a model in a high-volume diagnostic laboratory required more than a clever network. The team built a production pipeline that runs asynchronously on every whole slide image uploaded to the lab. Each slide first passes through a biopsy slide classifier that decides whether mitotic counting is even appropriate. A non-model tissue detection algorithm then maps the foreground tissue and generates coordinates for the mitotic figure detector, which analyzes overlapping tiles across the entire tumor area. Morphological filters sharpen the predicted masks before a k-d tree based algorithm searches all possible placements of a 2.37 square millimeter square and selects the one containing the most mitotic figures. The final output, delivered to pathologists as annotations on the digital slide, includes both the region of interest and circles around each candidate mitosis.

Validation rested on two ground truth datasets. The first comprised 72 soft tissue sarcomas from the lab’s routine caseload, each confirmed by three pathologists, with consensus expert opinion establishing which AI-flagged candidates were true mitoses. On this dataset, OncoPetNet achieved an F1 score of 0.86, with recall, or sensitivity, reaching 0.97. The second benchmark was the MIDOG++ dataset, a publicly available multi-domain collection built specifically to test how well mitosis-detection models generalize across scanners, stains, laboratories, and tumor types. On 100 canine soft tissue sarcoma images from that set, the model scored an F1 of 0.70, with precision of 0.81 but recall dropping to 0.62. The authors attribute the difference partly to domain shift, since their model was trained on their own scanners and staining protocols, and partly to the low mitotic density of many MIDOG++ images, where a single missed mitosis can crater the score.

With the model validated, the team ran two evaluation studies. The first mimicked routine diagnostics: a single pathologist graded all 72 tumors three ways, manually, with AI assistance, and using AI alone. The results were striking. The AI-only condition averaged 19.9 mitotic figures per case, the AI-assisted condition 14, and the manual condition just 6.26. In other words, AI assistance allowed the pathologist to find about 2.24 times as many mitoses as unaided observation. The pathologist’s role shifted from exhaustive searching to verification: rejecting false positives, which the model produced more often than false negatives, and adding back any true mitoses the network missed. Human oversight measurably moderated the AI’s counts, which is precisely the behavior a safety-conscious deployment would want.

Those increased counts rippled through the grading scheme. Mitotic counts are binned into an ordinal MC score from 1 to 3, which is then summed with scores for tumor necrosis and degree of differentiation to produce the final grade. In the first study, AI-assisted scores migrated upward by one level in 29 percent of cases and by two levels in 6 percent compared with manual counts. Tumor grades followed: 18 percent of tumors moved from grade 1 to grade 2, and 7 percent from grade 2 to grade 3. No tumor migrated two full grades, and no tumor moved downward. The second study, in which nine pathologists organized into three cohorts each reviewed 24 cases both manually and with AI assistance, replicated these findings almost exactly. Across 216 paired observations, AI assistance produced an average of 11.6 mitoses versus 5.31 manually, again a roughly 2.2-fold increase, with grade migration of 15.7 percent from grade 1 to 2 and 5.6 percent from grade 2 to 3.

Efficiency gains were equally consistent. Manual counts took an average of 62.8 seconds per case, while AI-assisted counts took 33.7 seconds, nearly a 1.86-fold reduction. In a busy diagnostic laboratory processing thousands of submissions, halving the time spent on one of the most tedious steps in tumor grading represents a substantial operational improvement. Just as importantly, the AI’s pre-screening of every slide and field relieves pathologists of the cognitive burden of an unhurried, exhaustive search, a practice the authors note is technically required for accuracy but impractical under real-world workloads.

The most consequential findings concern agreement between pathologists. Using intraclass correlation coefficients, the team compared how consistently the nine pathologists rated the same tumors under manual versus AI-assisted conditions. For raw mitotic counts, AI assistance significantly improved agreement in two of the three pathologist trios and overall, lifting the overall coefficient from 0.94 to 0.98. Agreement on MC scores also improved significantly overall. Agreement on which slide to select, measured with Fleiss’ Kappa, rose in all three groups and reached statistical significance in two, reflecting the fact that AI effectively removes the guesswork about where to count. Agreement on final tumor grade showed a consistent upward trend, including a substantial jump in one group from 0.48 to 0.72, but these gains did not reach statistical significance. The authors attribute this dilution to the two remaining subjective parameters, percent necrosis and degree of differentiation, which AI does not yet assess and which continue to drive inter-pathologist variability.

The study’s authors are careful about what these results do and do not prove. The clinical significance of the higher, more sensitive counts remains unexplored: it is possible that current MC score thresholds, calibrated on imperfect manual counts, should be adjusted upward now that detection is better, or that AI-assisted grades will ultimately predict biological behavior more accurately. Testing that will require studies correlating AI-assisted grades with patient outcomes, ideally including clinical follow-up and necropsy data. Extending the approach to quantify necrosis and differentiation objectively would complete the standardization picture. There are also inherent limits to ground truth itself, since even expert consensus on what constitutes a mitotic figure carries some subjectivity, and immunohistochemical markers like phosphorylated histone H3 introduce their own interpretive complications.

What the study does establish is a working template for human-AI collaboration in diagnostic pathology. The machine does what machines do best, exhaustively scanning every slide and field without fatigue, while the human does what humans do best, exercising judgment to reject imposters such as apoptotic bodies, pyknotic nuclei, and inflammatory cells that mimic mitoses. The result is a count that is more sensitive, faster, and more reproducible than either party achieves alone. For veterinary oncology, where soft tissue sarcomas are among the most common canine tumors and grading decisions directly guide surgery and follow-up, that combination could mark the beginning of a genuine standardization of tumor grading, one algorithm-assisted count at a time.

Subject of Research: AI-assisted mitotic counting for standardizing histologic grading of canine soft tissue sarcomas

Article Title: Artificial intelligence-assisted mitotic counts improve efficiency, accuracy, and inter-pathologist agreement: a method toward canine soft tissue sarcoma grade standardization

Article References: Borst, L., Bacmeister, C., Yau, W., Aceino, A., Ranck, R., Labelle, P., Ehrensing, G., Oliveira, F., Myers, C., Willcox, J. L., Ellerby, Z., Haydock, R., Taylor, K., Parkinson, M., Fitzke, M., & Gerdin, J. (2025). Artificial intelligence-assisted mitotic counts improve efficiency, accuracy, and inter-pathologist agreement: a method toward canine soft tissue sarcoma grade standardization. Veterinary Oncology, 2(1), Article 19. https://doi.org/10.1186/s44356-025-00034-3

Image Credits: AI Generated

DOI: 10.1186/s44356-025-00034-3

Keywords: artificial intelligence, deep learning, veterinary oncology, soft tissue sarcoma, mitotic count, tumor grading, digital pathology, inter-observer agreement, canine cancer, convolutional neural networks, histopathology, MIDOG++

The corn snake, a captive-bred male weighing around 500 grams, had lived for twelve years in a carefully managed glass terrarium alongside a female conspecific. His owners provided ultraviolet B lighting on a ten-hour cycle, basking areas warmed to 32 degrees Celsius, night-time temperatures of 20 degrees, and humidity between 45 and 70 percent. He was fed two adult mice every two weeks, received no calcium or vitamin supplementation, and was never subjected to winter brumation. Despite this stable routine, the snake had never been examined by a veterinarian, and no prior medical problems had been reported.

The trouble began insidiously. For four months the snake showed progressively generalized lethargy, episodes of uncoordinated winding movements, clumsy climbing attempts, and a weakening righting reflex — the instinctive ability to flip upright when turned over. He had also been anorexic for three months and losing weight. The most striking sign emerged three weeks before presentation: a progressive swelling along the dorsal surface of the middle third of his body. Ten days before the clinic visit, the snake fell from a platform in his terrarium, after which his coordination deteriorated dramatically. When a physical examination revealed an approximately 15-centimeter firm, nodular mass along the back, together with a second firm mass palpable inside the body cavity, the veterinary team knew they were dealing with something serious.

Radiographs taken under manual restraint painted a grim picture. The images revealed segmented fusion of adjacent vertebrae extending over a total length of 20 centimeters, irregular bone contours consistent with osteophyte formation and remodeling, and lysis — destructive breakdown — of vertebral processes. Additional osteolytic lesions appeared in several vertebral processes behind the main lesion, and a longitudinal soft-tissue mass with its own opacity was visible ventral to the spinal damage. In short, something was aggressively eating away at and rebuilding the snake’s backbone from the outside in.

Ultrasound examination added a crucial piece of the puzzle. Using an 11-MHz linear probe with the snake in dorsal recumbency, the clinicians identified a 4 by 1.5 by 2 centimeter irregular, moderately vascularized mass associated with the liver. Doppler imaging quantified the blood supply to the lesion, confirming it was not a simple cyst or abscess but a living, growing structure. The combination of a destructive spinal process and a liver-associated mass strongly suggested that the snake was suffering from a malignant tumor that had already seeded a distant organ.

Given the snake’s cachectic body condition, his flaccid muscle tone, his severely reduced reflexes, and the advanced stage of the spinal disease, the prognosis was judged poor to grave. The owners elected euthanasia and consented to post-mortem sampling of both masses, though they declined to release the entire carcass for a full necropsy. That decision limited the scope of the investigation, but the tissue that was recovered proved diagnostically decisive.

Histopathology revealed a paravertebral neoplasm infiltrating the adjacent musculature and extending into the vertebral bones, causing multifocal osteolysis. Within the liver, multifocal round masses of varying size showed the same infiltrative growth pattern. The tumor cells were medium-sized spindle shapes, roughly 30 to 40 micrometers long, with indistinct borders, moderate amounts of eosinophilic cytoplasm, and large eccentric nuclei bearing prominent basophilic nucleoli. The cells displayed severe anisocytosis and anisokaryosis — marked variation in cell and nuclear size — and mitotic figures appeared at a rate of two to four per high-power field, with bizarre mitoses and zones of necrosis scattered throughout. Azan trichrome staining confirmed a collagen-containing stroma woven through the neoplasm.

Immunohistochemistry was then deployed to fingerprint the tumor. Antibodies targeting vimentin produced moderate, multifocal to coalescing cytoplasmic staining in both the paravertebral mass and the liver tumors, indicating a mesenchymal origin — the hallmark of a sarcoma. Cross-reactivity controls confirmed that the antibody panel worked reliably on snake tissue: cytokeratin labeled biliary epithelium, desmin labeled skeletal muscle and vessel walls, GFAP labeled spinal cord astrocytes, and periaxin labeled peripheral nerve. Critically, the tumor cells did not express desmin, alpha-smooth muscle actin, GFAP, or periaxin, which ruled out origins from skeletal muscle, smooth muscle, or peripheral nerve sheaths. Taken together, the findings pointed to a poorly differentiated, metastasizing fibrosarcoma — most likely arising in the paravertebral tissue and secondarily invading bone, though the authors acknowledge that a primary vertebral tumor extending outward is also plausible.

The case carries broader significance for reptile medicine. Neoplastic disease in snakes appears to be reported with increasing frequency, a trend attributed to longer captive lifespans, better diagnostic services, and more informed owners bringing animals to clinics. Multi-institutional surveys have found that the vast majority of snake neoplasms — between 78 and 86.6 percent — are malignant, with soft tissue sarcomas among the most common. Musculoskeletal neoplasia, however, remains rare, accounting for only 1.4 to 4.8 percent of all tumors in snakes. Metastatic spread has been documented in reptiles, with one large study detecting metastases in 12.7 percent of reptiles with neoplastic disease, and another reporting detectable metastases in 42.9 percent of snakes with cancer. Yet ante-mortem diagnosis of metastasis is seldom reported, largely because reptile patients tend to arrive at clinics with disease already at an advanced stage, so full cancer staging is rarely performed. The authors suggest that this practice likely underestimates the true rate of metastatic tumors in snakes.

The Hannover team also emphasizes a practical lesson for clinicians: neoplasia deserves a place on the differential diagnosis list for common vertebral disorders in snakes, alongside the infectious, nutritional, and traumatic causes that are more routinely considered. Radiography and ultrasonography, they note, can be genuinely useful in detecting possible metastatic spread before death, and advanced imaging such as computed tomography or magnetic resonance imaging could offer even greater clarity in future cases. Treatment options — surgery, radiotherapy, chemotherapy — exist in the literature, but standardized cancer protocols are not yet established for any reptile species, and one survey found that only about 27 percent of snakes with neoplastic disease received any treatment at all, often because they were presented too late. For this corn snake, euthanasia was the humane endpoint. But the detailed documentation of his illness adds a valuable data point to a small but growing body of knowledge, and the authors call for more published case reports to deepen understanding of disease processes and treatment regimens in snakes — animals whose cancers, like their biology, remain full of surprises.

Subject of Research: Malignant paravertebral sarcoma with hepatic metastases in a corn snake

Article Title: Malignant paravertebral sarcoma with concurrent hepatic metastases in a corn snake (Pantherophis guttatus)

Article References: Hetterich, J., Puff, C., & Pees, M. (2025). Malignant paravertebral sarcoma with concurrent hepatic metastases in a corn snake (Pantherophis guttatus). Veterinary Oncology, 2(1), Article 32. https://doi.org/10.1186/s44356-025-00046-z

Image Credits: AI Generated

DOI: 10.1186/s44356-025-00046-z

Keywords: corn snake, Pantherophis guttatus, sarcoma, spindle cell tumor, metastasis, vertebral disease, reptile oncology, fibrosarcoma, veterinary pathology, immunohistochemistry, herpetology, liver tumors

Lymphoma is one of the most common malignancies in dogs, and its diagnosis typically begins with fine needle aspiration of an enlarged peripheral lymph node. Cytology, the microscopic examination of cells harvested in this minimally invasive way, is fast and generally reliable, but it is not always definitive. Confirming a diagnosis of lymphoma and characterizing it as B-cell or T-cell disease usually requires histopathology with immunophenotyping through PCR for antigen receptor rearrangement, flow cytometry, or immunohistochemistry. Those ancillary tests add cost, time, and logistical complexity, and they are not uniformly available across veterinary practices. Because microscopic evaluation demands trained pathologists, high-quality optics, and consistent staining reagents, diagnostic delays can affect clinical decisions and outcomes for canine patients.

The Florida team asked whether a convolutional neural network, the class of deep learning architecture that has transformed medical image classification, could shoulder part of this diagnostic burden. They selected ResNet-50, a fifty-layer residual network pretrained on the ImageNet database, and fine-tuned it through transfer learning on cytological photomicrographs captured at 1,000-fold magnification with immersion oil. The researchers assembled their dataset from cases submitted between 2017 and 2024 to the University of Florida Small Animal Hospital, drawing on the archive of the Clinical Pathology Service and cross-checking electronic medical records to verify each diagnosis.

Strict inclusion and exclusion criteria shaped the final cohort. Lymphoma cases required a cytological diagnosis of intermediate or large-cell lymphoma confirmed by PARR or flow cytometry, while reactive lymphoid hyperplasia cases required a predominance of small mature lymphocytes with plasma cells and no concern for a neoplastic population. Three board-certified clinical pathologists independently reviewed every selected slide to ensure consensus. The resulting dataset comprised 260 lymph node slides from 184 dogs, from which 2,600 images were captured: 1,070 images of B-cell lymphoma from 72 dogs, 490 images of T-cell lymphoma from 35 dogs, and 1,040 images of reactive lymphoid hyperplasia from 77 dogs. Most slides were stained with Wright-Giemsa, with a small number stained with Diff-Quick to reflect real-world staining variation.

A critical design decision was that the dataset was partitioned at the patient level rather than the image level. This meant that no images from a dog in the test set ever appeared in the training or validation pools, preventing information leakage from inflating performance. Approximately 20 percent of patients were held out for final testing, while the remaining 80 percent were used for 10-fold cross-validation, with hyperparameter tuning and early stopping applied within each fold. Images were standardized to 1920 by 1080 pixels, normalized using ImageNet channel statistics computed without reference to the validation or test data, and augmented on the fly with random horizontal and vertical flips during training.

The first task was binary classification: lymphoma versus reactive lymphoid hyperplasia. Across ten independently trained models, test accuracy ranged from 85.4 percent to 95.4 percent, with a mean of 90.3 percent, and the area under the receiver operating characteristic curve ranged from 0.943 to 0.988. The best-performing model achieved an accuracy of 0.954 with a Matthews correlation coefficient of 0.904, sensitivity of 0.950, specificity of 0.958, and an F1 score of 0.957. The authors note that this level of sensitivity matches or slightly exceeds the roughly 93 percent sensitivity reported for clinical pathologists distinguishing lymphoma from non-lymphoma in cytology, and it clears the 94 percent threshold proposed for decision-rule validation in this domain. Training, validation, and test performance remained closely aligned across folds, suggesting minimal overfitting.

The second task was far harder: distinguishing B-cell from T-cell lymphoma using cytological appearance alone. This is notoriously difficult even for experienced pathologists, because both immunophenotypes often present as morphologically similar populations of large or intermediate lymphocytes, with only subtle clues such as occasional uropods in some T-cell cases. Unsurprisingly, the models performed more modestly here, with test accuracies between 66.2 percent and 79.8 percent, a mean of 74.3 percent, and area under the curve values between 0.653 and 0.748. The representative model achieved an accuracy of 0.743, though confidence intervals were wide given the limited number of T-cell patients. The authors point out that some discordance may stem from the reference standards themselves, since PARR and flow cytometry do not always agree, especially in samples with low tumor burden.

The study also carries important caveats that the authors address directly. The entire dataset came from a single veterinary teaching hospital, raising questions about geographic and equipment-related bias. Images were manually captured from representative fields chosen by pathologists rather than from whole-slide imaging, confirming high image quality but simplifying the task relative to real diagnostic workflows. Cases of small-cell lymphoma, which account for fewer than two percent of canine lymphomas and are extremely difficult to separate from reactive hyperplasia on cytology alone, were deliberately excluded, meaning the model’s scope is limited to the most cytologically distinct presentations. Class imbalance and the predominance of one imaging system may also have influenced performance, and the researchers emphasize that robust external validation on prospectively collected, multi-institutional data is essential before any clinical deployment.

Transparency was a stated priority throughout. Unlike conventional practice, where a hold-out test set is evaluated once, the team reported results from all ten cross-validation folds and identified the best-performing model, providing a detailed suite of metrics including confidence intervals derived from patient-level bootstrapping with 1,000 iterations. The source code for preprocessing, training, and evaluation will be released publicly on GitHub, and the anonymized image dataset is available from the corresponding author upon reasonable request under a data use agreement. The authors argue that this openness stands in contrast to the proprietary opacity that often surrounds commercial AI diagnostic tools, such as the cytology-triage platforms already entering veterinary practice.

Looking forward, the researchers frame their models as triage and decision-support tools rather than replacements for pathologists, insisting that a board-certified clinical pathologist must retain final diagnostic responsibility and interpret model outputs alongside clinical history and ancillary tests. Future work will explore whole-slide imaging pipelines that could mirror the way pathologists actually examine slides, explainable AI techniques such as Gradient-weighted Class Activation Mapping to reveal which cellular features drive predictions, other CNN architectures, and multi-institutional datasets spanning diverse stains, scanners, and patient populations. The moderate success of B-cell versus T-cell classification, despite the well-known morphological overlap between these immunophenotypes, hints that deep networks may be extracting genuinely subtle cytomorphological patterns. For now, the study establishes a careful, reproducible performance baseline and an explicit methodological roadmap for bringing AI-assisted cytology from the research bench toward the veterinary clinic, where faster answers could mean earlier treatment for dogs with lymphoma.

Subject of Research: Deep learning classification of canine lymphoma in lymph node cytology images

Article Title: Deep learning-assisted cytological image analysis for canine lymphoma

Article References: Shum, C., Lee, D., Jo, H., Kim, J., Heo, H., Gilor, S., Lanier, C., Hall, K., Dark, M., Kim, J. H., & de Souza, C. (2026). Deep learning-assisted cytological image analysis for canine lymphoma. Veterinary Oncology, 3(1), Article 5. https://doi.org/10.1186/s44356-026-00056-5

Image Credits: AI Generated

DOI: 10.1186/s44356-026-00056-5

Keywords: canine lymphoma, deep learning, cytology, ResNet-50, veterinary pathology, convolutional neural networks, B-cell lymphoma, T-cell lymphoma, reactive lymphoid hyperplasia, image classification, veterinary oncology, artificial intelligence

The study, published in the journal Veterinary Oncology, was led by Ingrid Marie Moberg and colleagues at the Norwegian University of Life Sciences, Oslo University Hospital, and the University of Oslo. The team analyzed RNA sequencing data from 179 canine mammary tumors, drawn from a cohort of naturally occurring tumors removed from companion dogs during routine surgery. Their goal was twofold: to define molecular subgroups of canine mammary tumors without reference to histology, and then to ask whether tumors from the same dog share those molecular identities. The answer to the second question, in most cases, was no.

To classify the tumors, the researchers first reduced their high-dimensional gene expression data using principal component analysis, then applied unsupervised consensus clustering, an algorithm that groups samples based purely on expression similarity and stability across repeated resampling. This revealed five robust transcriptomic clusters. Crucially, the clusters did not map cleanly onto histological diagnosis. Each cluster contained a mixture of benign and malignant tumors, confirming that the microscopic appearance of these tumors tells only part of the story of their underlying biology.

Gene set enrichment analysis then revealed that the five clusters bear a remarkable resemblance to molecular subtypes long recognized in human breast cancer. Three of the clusters showed enrichment of hormone-related gene programs, including estrogen response, and were found to harbor the transcription factor GATA3, a classic marker of luminal breast cancer in humans. One cluster combined cell-cycle proliferation with immune and interferon signaling, evoking the aggressive basal-like or triple-negative phenotype, while a fifth cluster was defined by epithelial-mesenchymal transition, angiogenesis, and inflammatory modules, reminiscent of the claudin-low subtype. The parallel with human breast cancer taxonomy is not merely cosmetic; it strengthens the case for dogs as a comparative model in which the biology of mammary cancer can be studied in a spontaneously arising disease.

Beyond clustering, the team constructed a gene co-expression network using the hCoCena framework, identifying ten modules of genes that are expressed together and that encode distinct biological processes. One module captured hormone signaling, two captured immune and interferon responses, three reflected metabolism and proliferation through glycolysis, PI3K-AKT-mTOR signaling, oxidative phosphorylation, and MYC targets, and others traced epithelial differentiation through WNT signaling, epithelial-mesenchymal transition, cell-cycle regulation through E2F targets and the G2M checkpoint, and tumor microenvironment features such as angiogenesis. Transcription factor enrichment within the modules pointed to GATA3 as a regulator of the hormonal program and E2F1 as a driver of the proliferative module, providing candidate master switches behind the observed phenotypes.

The heart of the study, however, lies in its analysis of synchronous tumors. The researchers focused on 45 dogs that each carried exactly two tumors, yielding 90 paired samples classified as benign-benign, malignant-benign, or malignant-malignant. When they compared cluster assignments within each pair, concordance was low. Only about 45 percent of tumor pairs landed in the same transcriptomic cluster overall, with malignant-malignant pairs showing the highest agreement at 56 percent, benign-benign pairs at 44 percent, and mixed malignant-benign pairs at just 36 percent. In other words, the majority of dogs carried two tumors with fundamentally different molecular identities.

To quantify this divergence at the level of individual genes, the team calculated intraclass correlation coefficients for every gene across the paired samples. Genes were scored as low, moderate, or high in correlation between a dog’s two tumors. The results were unambiguous: between roughly 76 and 90 percent of genes showed low correlation across all diagnostic categories, and fewer than one percent of genes were highly correlated within any category. This pattern of widespread discordance held regardless of whether both tumors were benign, both malignant, or one of each, indicating that molecular independence between synchronous tumors is the norm rather than the exception.

A small set of exceptions proved informative. The analysis identified a handful of genes, including OMD and EN1, whose expression is strongly correlated within certain categories of synchronous tumor pairs and which have been reported as prognostic markers in human cancers. The authors suggest that these genes may point to shared disease processes or protective mechanisms against malignant transformation, and that they deserve further investigation, potentially at the DNA level, to uncover any genetic factors underlying their coordinated behavior. Meanwhile, examination of module-level variation showed that programs linked to cell-cycle activity, hormone signaling, and immune responses fluctuated most between paired tumors, while modules tied to epithelial differentiation and metabolism remained comparatively stable within individuals.

The clinical implications of this work reach in two directions at once. For veterinary medicine, the findings suggest that each tumor in a multi-tumor patient should be evaluated as a biologically independent lesion rather than assumed to be representative of its neighbors. Because molecular subtypes in human breast cancer drive dramatically different treatment decisions, from endocrine therapy for hormone receptor-positive disease to chemotherapy and PARP inhibitors for triple-negative tumors, a biology-driven approach could eventually refine the limited therapeutic options currently available for canine patients. The authors note, for instance, that identifying hormone-positive subtypes could inform whether ovariohysterectomy offers real benefit at the time of tumor removal, a decision veterinarians currently make without molecular guidance.

For comparative oncology, the study reinforces the value of the canine model in a way that human cohorts cannot easily replicate. Synchronous bilateral breast cancer occurs in only around one percent of human patients, whereas synchronous mammary tumors affect the majority of affected dogs. Studying these paired tumors within the same genetic background eliminates many host-specific confounders, offering a natural experiment in tumor evolution and inter-individual heterogeneity. The authors acknowledge limitations inherent to bulk RNA sequencing, which averages expression across all cells in a tissue and may reflect tissue composition as much as tumor biology, and they caution that a single RNA sample may not represent an entire tumor. Even so, their conclusion stands firm: histopathology alone does not capture the molecular reality of canine mammary tumors, and expression-based profiling offers a more faithful map of the biological terrain that clinicians and researchers alike will need to navigate.

Subject of Research: Transcriptomic heterogeneity of synchronous canine mammary tumors and their molecular resemblance to human breast cancer subtypes

Article Title: High molecular heterogeneity in synchronous canine mammary tumors detected by transcriptomic analysis

Article References: Moberg, I. M., Murphy, S. L., Hansen, N., Borge, K. S., Gunnes, G., Sørlie, T., Lingaas, F., Bergholtz, H., & Solbakken, M. H. (2026). High molecular heterogeneity in synchronous canine mammary tumors detected by transcriptomic analysis. Veterinary Oncology, 3(1), Article 11. https://doi.org/10.1186/s44356-026-00066-3

Image Credits: AI Generated

DOI: 10.1186/s44356-026-00066-3

Keywords: canine mammary tumors, transcriptomics, RNA sequencing, tumor heterogeneity, synchronous tumors, breast cancer subtypes, gene co-expression network, consensus clustering, comparative oncology, veterinary pathology, High, molecular