Find the papers that actually matter

Computational pathology relies on effective representation learning to support cancer research and precision medicine. Although self-supervised learning has driven major progress at the patch and whole-slide image levels, representation learning at the single-cell level remains comparatively underexplored, despite its importance for characterizing cell types and cellular phenotypes. We introduce LEMON (Learning Embeddings from Morphology Of Nuclei), a self-supervised foundation model for scalable single-cell image representation learning. Trained on millions of cell images from diverse tissues and cancer types, LEMON learns robust and versatile morphological representations that support large-scale single-cell analyses in pathology. We evaluate LEMON on five benchmark datasets across a range of prediction tasks and show that it provides strong performance, highlighting its potential as a new paradigm for cell-level computational pathology. Model weights are available at https://huggingface.co/aliceblondel/LEMON.

Early screening via colonoscopy is critical for colon cancer prevention, yet developing robust AI systems for this domain is hindered by the lack of densely annotated, long-sequence video datasets. Existing datasets predominantly focus on single-class polyp detection and lack the rich spatial, temporal, and linguistic annotations required to evaluate modern Multimodal Large Language Models (MLLMs). To address this critical gap, we introduce Colon-Bench, generated via a novel multi-stage agentic workflow. Our pipeline seamlessly integrates temporal proposals, bounding-box tracking, AI-driven visual confirmation, and human-in-the-loop review to scalably annotate full-procedure videos. The resulting verified benchmark is unprecedented in scope, encompassing 528 videos, 14 distinct lesion categories (including polyps, ulcers, and bleeding), over 300,000 bounding boxes, 213,000 segmentation masks, and 133,000 words of clinical descriptions. We utilize Colon-Bench to rigorously evaluate state-of-the-art MLLMs across lesion classification, Open-Vocabulary Video Object Segmentation (OV-VOS), and video Visual Question Answering (VQA). The MLLM results demonstrate surprisingly high localization performance in medical domains compared to SAM-3. Finally, we analyze common VQA errors from MLLMs to introduce a novel "colon-skill" prompting strategy, improving zero-shot MLLM performance by up to 9.7% across most MLLMs. The dataset and the code are available at https://abdullahamdi.com/colon-bench .

Prediction of genetic biomarkers, e.g., microsatellite instability in colorectal cancer is crucial for clinical decision making. But, two primary challenges hamper accurate prediction: (1) It is difficult to construct a pathology-aware representation involving the complex interconnections among pathological components. (2) WSIs contain a large proportion of areas unrelated to genetic biomarkers, which make the model easily overfit simple but irrelative instances. We hereby propose a Dictionary-based hierarchical pathology mining with hard-instance-assisted classifier Debiasing framework to address these challenges, dubbed as D2Bio. Our first module, dictionary-based hierarchical pathology mining, is able to mine diverse and very fine-grained pathological contextual interaction without the limit to the distances between patches. The second module, hard-instance-assisted classfier debiasing, learns a debiased classifier via focusing on hard but task-related features, without any additional annotations. Experimental results on five cohorts show the superiority of our method, with over 4% improvement in AUROC compared with the second best on the TCGA-CRC-MSI cohort. Our analysis further shows the clinical interpretability of D2Bio in genetic biomarker diagnosis and potential clinical utility in survival analysis. Code will be available at https://github.com/DeepMed-Lab-ECNU/D2Bio.

In a dataset of 423 patients who had had radical prostatectomy for localised prostate cancer we estimated the apparent Shannon information (ASI) about time to biochemical recurrence in various subsets of the available pre-op variables using a Bayesian Gamma-power-mixture survival regression model. In all the subsets examined the ASI was positive with posterior probability greater than 0.975 . Using only age and results of pre-operative blood tests (PSA and biomarkers) we achieved 0.232 (0.180 to 0.290) nats ASI (0.335 (0.260 to 0.419) bits) (posterior mean and equitailed 95% posterior confidence intervals). This is more than double the mean posterior ASI previously achieved on the same dataset by a subset of the current authors using a log-skew-Student-mixture model, and is greater than that previous value with posterior probability greater than 0.99 . Additionally using pre- or post-operative Gleason grades, operative findings, clinical stage, and presence or absence of extraprostatic extension or seminal vesicle invasion did not increase the ASI extracted. However removing the blood-based biomarkers and replacing them with either pre-operative Gleason grades or findings available from MRI scanning greatly reduced the available ASI to respectively 0.077 (0.038 to 0.120) and 0.088 (0.045 to 0.132) nats (both less than the values using blood-based biomarkers with posterior probability greater than 0.995). A greedy approach to selection of the best biomarkers gave TGFbeta1, VCAM1, IL6sR, and uPA in descending order of importance from those examined.

This study assesses whether self-supervised learning (SSL) improves knee osteoarthritis (OA) modeling for diagnosis and prognosis relative to ImageNet-pretrained initialization. We compared (i) image-only SSL pretrained on knee radiographs from the OAI, MOST, and NYU cohorts, and (ii) multimodal image-text SSL pretrained on hospital knee radiographs paired with radiologist impressions. For diagnostic Kellgren-Lawrence (KL) grade prediction, SSL yielded mixed results. While image-only SSL improved accuracy during linear probing (frozen encoder), it did not outperform ImageNet pretraining during full fine-tuning. Similarly, multimodal SSL failed to improve grading performance. A likely explanation is mismatch between the hospital pretraining corpus and the downstream diagnostic task: the hospital image-text dataset was restricted to knees from patients with clinically identified OA in routine care, rather than a cohort spanning the full spectrum from normal to severe disease needed for balanced KL grading. In addition, radiology impressions do not explicitly encode KL grade, limiting supervision for learning KL-specific decision boundaries. In contrast, this same multimodal initialization significantly improved prognostic modeling. It outperformed ImageNet baselines in predicting 4-year structural incidence and progression, including on external validation (MOST AUROC: 0.701 vs. 0.599 at 10\% labeled data). Overall, these results suggest that our hospital image-text data may be less effective for diagnostic grading when the pretraining cohort is limited to OA knees, but can provide a strong signal for prognostic modeling when the downstream task is better aligned with the pretraining data distribution.

Accurate surgical phase recognition is essential for analyzing procedural workflows, supporting intraoperative decision-making, and enabling data-driven improvements in surgical education and performance evaluation. In this work, we present a comprehensive framework for phase recognition in pituitary tumor surgery (PTS) videos, combining self-supervised representation learning, robust temporal modeling, and scalable data annotation strategies. Our method achieves 90\% accuracy on a held-out test set, outperforming current state-of-the-art approaches and demonstrating strong generalization across variable surgical cases. A central contribution of this work is the integration of a collaborative online platform designed for surgeons to upload surgical videos, receive automated phase analysis, and contribute to a growing dataset. This platform not only facilitates large-scale data collection but also fosters knowledge sharing and continuous model improvement. To address the challenge of limited labeled data, we pretrain a ResNet-50 model using the self-supervised framework on 251 unlabeled PTS videos, enabling the extraction of high-quality feature representations. Fine-tuning is performed on a labeled dataset of 81 procedures using a modified training regime that incorporates focal loss, gradual layer unfreezing, and dynamic sampling to address class imbalance and procedural variability.

Recent advances in multimodal large language models enable new possibilities for image-based decision support. However, their reliability and operational trade-offs in neuroimaging remain insufficiently understood. We present a comprehensive benchmarking study of vision-enabled large language models for 2D neuroimaging using curated MRI and CT datasets covering multiple sclerosis, stroke, brain tumors, other abnormalities, and normal controls. Models are required to generate multiple outputs simultaneously, including diagnosis, diagnosis subtype, imaging modality, specialized sequence, and anatomical plane. Performance is evaluated across four directions: discriminative classification with abstention, calibration, structured-output validity, and computational efficiency. A multi-phase framework ensures fair comparison while controlling for selection bias. Across twenty frontier multimodal models, the results show that technical imaging attributes such as modality and plane are nearly solved, whereas diagnostic reasoning, especially subtype prediction, remains challenging. Tumor classification emerges as the most reliable task, stroke is moderately solvable, while multiple sclerosis and rare abnormalities remain difficult. Few-shot prompting improves performance for several models but increases token usage, latency, and cost. Gemini-2.5-Pro and GPT-5-Chat achieve the strongest overall diagnostic performance, while Gemini-2.5-Flash offers the best efficiency-performance trade-off. Among open-weight architectures, MedGemma-1.5-4B demonstrates the most promising results, as under few-shot prompting, it approaches the zero-shot performance of several proprietary models, while maintaining perfect structured output. These findings provide practical insights into performance, reliability, and efficiency trade-offs, supporting standardized evaluation of multimodal LLMs in neuroimaging.

MRI-based medical imaging has become indispensable in modern clinical diagnosis, particularly for brain tumor detection. However, the rapid growth in data volume poses challenges for conventional diagnostic approaches. Although deep learning has shown strong performance in automated classification, many existing solutions are confined to closed technical architectures, limiting reproducibility and further academic development. PhyDCM is introduced as an open-source software framework that integrates a hybrid classification architecture based on MedViT with standardized DICOM processing and an interactive desktop visualization interface. The system is designed as a modular digital library that separates computational logic from the graphical interface, allowing independent modification and extension of components. Standardized preprocessing, including intensity rescaling and limited data augmentation, ensures consistency across varying MRI acquisition settings. Experimental evaluation on MRI datasets from BRISC2025 and curated Kaggle collections (FigShare, SARTAJ, and Br35H) demonstrates stable diagnostic performance, achieving over 93% classification accuracy across categories. The framework supports structured, exportable outputs and multi-planar reconstruction of volumetric data. By emphasizing transparency, modularity, and accessibility, PhyDCM provides a practical foundation for reproducible AI-driven medical image analysis, with flexibility for future integration of additional imaging modalities.

Medical imaging benchmarks often evaluate VLMs on pre-selected 2D images, slices, crops, or patches, making evaluation closer to visual recognition. Real clinical workflows impose a different burden: readers must search through complete studies, operate imaging software, navigate across slices and magnifications, and document visual evidence that can be audited. We argue that this evidence-producing workflow is a critical missing evaluation axis for medical imaging agents. To study it, we introduce MedFlowBench, a full-study benchmark for VLM agents, together with MedOpenClaw, a controlled and replayable runtime in which agents operate medical imaging viewers such as 3D Slicer and QuPath. In each episode, an agent inspects a complete radiology study or whole-slide pathology image, returns a task answer, and submits structured evidence, including key slices, coordinates, regions of interest, or lesion-state fields. This evidence is automatically checked against withheld masks, annotations, and labels. Across evaluated models, final answer-only scoring gives an overly optimistic picture: when answers must also be supported by correct evidence, performance drops substantially on complex workflows. We further find that adding image-analysis tools does not by itself solve the problem. Tools help when they make a complex procedure simple and reliable, but agents still struggle when they must choose inputs, manage viewer state, and verify intermediate outputs over multiple steps. MedFlowBench exposes whether medical imaging agents can produce auditable evidence from complete studies, rather than plausible answers from selected images.

Automated detection and classification of cervical cells in conventional Pap smear images can strengthen cervical cancer screening at scale by reducing manual workload, improving triage, and increasing consistency across readers. However, it is challenged by severe class imbalance and frequent nuclear overlap. We present our approach to the RIVA Cervical Cytology Challenge (ISBI 2026), which requires multi-class detection of eight Bethesda cell categories under these conditions. Using YOLOv11m as the base architecture, we systematically evaluate three strategies to improve detection performance: loss reweighting, data resampling and transfer learning. We build an ensemble by combining models trained under each strategy, promoting complementary detection behavior and combining them through Weighted Boxes Fusion (WBF). The ensemble achieves a mAP50-95 of 0.201 on the preliminary test set and 0.147 on the final test set, representing a 29% improvement over the best individual model on the final test set and demonstrating the effectiveness of combining complementary imbalance mitigation strategies.