Overview

Computational pathology studies how to extract diagnostic and biological information from digitized tissue and cell images, including whole-slide images, biopsies, and cytology. Common approaches include convolutional and vision-transformer models, weakly supervised multiple-instance learning for slide-level labels, and segmentation or graph methods for cells and tissue structure; benchmarks such as CAMELYON and PANDA test detection and grading. Foundation and vision-language models increasingly align image features with reports, clinical records, and molecular data for retrieval, prognosis, virtual staining, and spatial gene-expression prediction. A central challenge is ensuring that models remain reliable across hospitals, scanners, and stains while producing interpretable evidence and demonstrating benefit in prospective clinical workflows.

Latest papers

304 papers35 papers in the last four weeks, up 21% on the four weeks before. 0.2% of all new papers.

Nov 12, 2026

TuMAP: A Dual-View, Morphotype-Aware Pathomics Pipeline for Quantifying Renal Tubular Remodeling

Quantifying disease-associated renal tubular remodeling is challenging because tubular appearances are heterogeneous. We introduce TuMAP (Tubular Morphotype-Aware Pathomics), a pipeline combining (1) dual-view foundation-model representations and provisional morphotype annotation, (2) compositional and within-morphotype pathomics, and (3) patient-level statistical inference. From 456,158 tubules in 358 PAS-stained kidney biopsy slides, TuMAP identified eight image-based morphotypes, seven of which showed stable subsampling assignments. Across 219 patients in six diagnostic groups, diabetic nephropathy (DN) and tubulointerstitial nephritis/acute tubular injury (TIN/ATI) each differed from minimal change disease in seven morphotype proportions, while IgA nephropathy differed in six. DN showed reduced nuclear solidity and increased eccentricity across all eight morphotypes. Area-normalized nuclear density exposed additional within-morphotype differences. TuMAP provides a framework for separating changes in tubular morphotype composition from phenotypic differences within morphotypes.
Nov 12, 2026

Automated PD-L1 Tumor Proportion Scoring with Uncertainty-Guided Triage in Non-Small Cell Lung Cancer

Programmed death-ligand 1 (PD-L1) tumor proportion score (TPS) informs immunotherapy selection in non-small cell lung cancer. Near the 1% and 50% cutoffs, the score should also indicate when closer review is warranted. We designed a three-stage framework to follow the sequence of TPS assessment. Stage 1 identifies tumor regions and excludes macrophage-rich patches. Stage 2, a dual-branch cell counting network (D2Count-Net), counts PD-L1-positive and PD-L1-negative tumor cells in these regions to calculate TPS. Stage 3, TPS-Guard, an uncertainty-guided triage mechanism, reports model uncertainty as the disagreement among independently trained models, refers the most uncertain slides, and flags scores near the 1% or 50% cutoff when model estimates disagree across that cutoff. Flags state the reason for referral or alert the pathologist to possible scoring errors on auto-reported slides. In a retrospective, single-center study, 154 whole-slide images were scored by three pathologists, and the model and each pathologist were compared in turn with the mean of the other two. On the 114 slides unseen in training, model mean absolute error (MAE) was 6.96 percentage points, within the range of the three pathologists (4.24 to 8.29), and model uncertainty correlated with absolute TPS error (Spearman rho = 0.77) and inter-pathologist disagreement (rho = 0.71). After referral of the 15% most uncertain slides, model and pathologist MAE both decreased. Applied without retraining to an external, publicly available dataset, TPS-Guard still directed review to higher-error cases, and referring more uncertain cases raised sensitivity at the 50% cutoff. TPS-Guard provides reasons for reviewing individual automated scores and identifies slides that also produce greater disagreement among pathologists. Prospective reader studies should assess TPS-Guard's effect on TPS reporting.
Nov 11, 2026

CaseScope: A Multi-Field Benchmark for Case-Level Pathology Diagnosis with Multimodal LLMs

Pathologists rarely diagnose from a single image: they scan a section at low power for architecture, zoom into selected fields for cytology, and integrate the evidence across views and scales. Pathology benchmarks for multimodal large language models (MLLMs), however, mostly ask about one image or require whole-slide pipelines, and the few that show several fields draw nested regions from cancer slides of one public cohort. We introduce CaseScope, a benchmark of diagnosis from several curated fields of one lesion: CaseScope-Teaching, 436 cases from a residency-training image library, reconstructed, de-identified, harmonised against a WHO-based ontology and re-examined by a pathologist wherever an automated pre-review raised a doubt, and CaseScope-Atlas, 800 cases from 88 published atlases (387 of them figure series of one disease), labelled from the captions by two LLMs that must agree. They cover 843 entities across 18 organ systems and pose 4,679 items in six tasks, from open-ended and ten-way diagnosis with ontology-guided hard negatives under circular evaluation to the verification and location of morphological findings. Across twenty-eight open and four proprietary MLLMs, diagnoses are unstable -- the best open and proprietary models are correct under all ten option rotations on 17.9% and 61.7% of the teaching cases -- and wrong answers favour the classic look-alike; open models make little use of the additional fields on teaching cases, where the one-line specimen site matters more, although on atlas cases with three or more fields the fields count about as much as the site; and most open models verify findings barely above chance (median 62.0% vs. 50%, best 81.5%), gaining a median +3.4 points from images; proprietary models reach 83.2-93.2%. Rankings broadly replicate between the sources. The evaluation code is available at https://github.com/Wenchuan-Zhang/CaseScope.
Nov 10, 2026

An Asynchronous Federated Learning Platform for Lung Adenocarcinoma Grading via Foundation Models and Structural Pruning

Classification of lung adenocarcinoma into poorly differentiated (PD) and well-to-moderately differentiated (WMD) subtypes plays an important role in patient survival; however, consistent classification is difficult due to inter-observer variability among pathologists. Collecting data from multiple hospitals is also challenging due to patient privacy concerns. This study proposes a web-based federated learning system that shares only locally trained model weights without sharing patient data between institutions. The UNI2 foundation model and CLAM-SB were used to classify pathological whole slide images. A four-client federated learning system was constructed, and the NLST cohort was reserved exclusively for external validation. In centralized evaluation, joint training with CPTAC and TCGA outperformed single-institution training on external validation, confirming the necessity of multi-institutional data integration. FedAvg, FedProx, FedBN, and FedNova were compared as federated learning algorithms under identical experimental conditions. Test AUC ranked as FedBN, FedProx, FedNova, and FedAvg. FedNova showed the most balanced classification performance between PD and WMD. L1-norm structural pruning at 20%, 30%, and 40% sparsity was applied to reduce model transmission size. FedAvg, FedProx, and FedBN showed a tendency of decreasing Test AUC under pruning, while FedNova achieved improved Test AUC across all sparsity levels. A web-based application was developed supporting slide upload, local training, AI classification, and attention heatmap-based visualization. The combination of FedNova and 40% pruning was confirmed as a practical approach that improves communication efficiency and classification performance while protecting patient privacy.
Nov 6, 2026

Health-System-Wide Mapping of Demographic Information in Routine Clinical Histopathology

The extent to which demographic-associated information is detectable across organs and disease states in routine clinical histopathology remains unclear. Here, we analyzed 1.3 million hematoxylin and eosin whole-slide images from 257,322 patients across 25 organs, using pathology foundation-model representations and multiple-instance learning to systematically map information associated with sex, age group, and self-reported race. Across 69 organ-demographic combinations, demographic attributes were broadly recoverable, with pan-organ mean AUROCs of 0.828 for sex, 0.733 for age group, and 0.662 for self-reported race, and substantial variation across organs. Demographic-class balancing produced relatively small changes in performance, while evaluation within diagnosis-text clusters showed modest attenuation. Under training with diagnosis-based grouping, demographic-associated signals remained detectable across multiple organs, including sex in gastric tissue (AUROC 0.865), age group in breast (0.816), and self-reported race in skin (0.728). Literature-guided analysis of these settings generated candidate histomorphological and contextual explanations for further investigation. Together, these findings provide a systematic map of demographic-associated information in routine histopathology, informing investigations of its sources, assessments of potential shortcut learning, and the development of more interpretable computational pathology models.
Nov 6, 2026

Contrastive fine-tuning against stain and scanner bias improves robustness and downstream performance across pathology foundation models

Histopathology foundation models achieve strong performance across diverse downstream tasks, yet their representations have been shown to encode scanner- and site-specific biases, creating generalization gaps and potentially limiting real-world utility. We introduce SPECTRA (Scanner and Pathology Embedding Contrastive Tuning for Robust Alignment), a model-agnostic contrastive learning post-training framework which explicitly encourages scanner- and stain-robust representations, to optimize performance and generalization on downstream applications. Using parameter-efficient LoRA adapters trained on matched multi-scanner and multi-stain whole-slide images sourced from the PLISM dataset, our method aligns spatially corresponding regions across acquisition conditions (scanner, stain), using other locations within each candidate condition as negatives. SPECTRA improved PathoROB robustness index, gene-expression prediction on HEST, slide-level classification AUC on CPTAC, and held-out PLISM retrieval for every model. Overall tile-level classification on THUNDER also improved, with exceptions for segmentation and calibration tasks. We open-source our training and evaluation codebases and release adapters and model weights for selected backbones.
Nov 6, 2026

The APL Doesn't Fall Far From The Tree: Unsupervised Artefact Prototype Learning in Histopathology

Histopathology foundation models provide rich representations of tissue morphology, but technical artefacts in whole slide images introduce noise that may impact diagnostic accuracy. We introduce Artefact Prototype Learning (APL), a novel approach to detecting these artefacts that exploits the geometry of pre-trained embedding spaces without manual labels or fine-tuning. Rather than treating artefacts as isolated outliers, APL computes prototypes of out-of-distribution patches and uses them to distinguish artefact-associated patterns from tissue. Evaluation on a single-centre dataset shows that APL outperforms prior methods GrandQC and HistoART in detecting artefacts such as blur, dark spots, slide edges and pen marks, but struggles with tissue folds and blood. These results show that frozen pre-trained embeddings already carry information that allows artefact detection without expensive labels or vast computational resources.
Nov 5, 2026

Towards Scalable Diagnostic-Driven Whole-Slide Image Retrieval for Pathology Archives

The growing adoption of digital pathology has rapidly expanded collections of hematoxylin-and-eosin whole-slide images, yet efficient navigation through these archives remains challenging, as metadata is often inconsistent or unavailable. Content-based image retrieval addresses this challenge by identifying similar cases directly from visual representations instead of manual annotations or metadata. Existing retrieval systems have demonstrated promising performance but largely rely on handcrafted indexing pipelines and predefined sampling strategies, constraining scalability and generalization. Here, we present CLEAR-WSI (Constant-Length Embedding for Automatic Retrieval of Whole-Slide Images) as a scalable, diagnostic-driven slide-retrieval framework, validated on both public and clinical data. Using a fixed-length slide embedding, CLEAR-WSI refines retrieved candidates with either a predicted diagnostic label or the ground-truth label, depending on the retrieval setting. Newly processed cases are subsequently added to the expanding memory bank, allowing the retrieval archive to grow over time. On a comprehensive benchmark consisting of two public and one private clinical datasets representing four retrieval tasks, CLEAR-WSI improves Precision@5 over the strongest evaluated baseline, with gains on CAMELYON16 (3.10), BRACS-1 (2.75), BRACS-2 (1.95), and X-HER2 (3.75). Additional ablation and latency studies further examine the contribution of each component and highlight its potential for scalable deployment.
Nov 4, 2026

Nanopath: Fast, Fair, Open Experimentation for Pathology Foundation Models

We introduce nanopath, an open-source framework and benchmark for rapidly training and evaluating small-scale pathology foundation models. Using a single H100 GPU, a typical nanopath model trains in a little over an hour on up to one million TCGA pathology tile presentations and evaluates within 25 minutes on a broad suite of tile-level and slide-level tasks. Nanopath enables rapid exploration of research ideas at small scale, so promising training recipes can subsequently be tested with more data and compute. To enable fair comparisons between ideas, we constrain submissions to fixed data and compute budgets while keeping the downstream evaluation protocol fixed. Anyone may clone the codebase, automatically download the data, reproduce or modify existing models, and submit a run to Labless, our public experiment ledger where researchers and AI agents can search through prior attempts. Since its public release in June 2026, nanopath has received 1,269 experiments from 20 contributors. Here, we detail its design and assess how well its rapid evaluation tracks standardized THUNDER, HEST, and PathoBench (CPTAC) benchmarks across six nanopath and 14 reference foundation models. Nanopath's fast evaluation suite strongly tracked these standardized benchmarks, and a few 22M parameter nanopath models even outperformed giant 1.1B parameter models on a subset of downstream tasks. We subsequently discuss how we have since optimized nanopath's evaluation suite to be an even more faithful, quick proxy for external benchmarking. Nanopath provides an accessible testbed for students, researchers, and AI agents to explore pathology foundation modeling through fair, transparent, and directly comparable experiments.
Nov 4, 2026

Agent-Driven Generative Priors for Pathology Image Synthesis and Segmentation

Deep learning methods for pathology are constrained by the limited availability and high cost of large-scale pixel-level annotations. Synthetic data can alleviate this limitation, but existing pipelines often lack reliable quality control and remain weakly connected to downstream analysis. To address these issues, we propose a three-stage framework that integrates automated data screening, generative representation learning, and efficient adaptation to downstream tasks. First, we develop a pathology agent system to assess image quality and filter samples, resulting in TCGA-200K, a dataset containing 217,030 pathology patches selected from the public TCGA repository. Second, we train a generative model on the screened data. In addition to image synthesis, its backbone learns structural and semantic representations that can be transferred to downstream tasks. Third, we adapt the pretrained generative backbone to semantic segmentation using a lightweight task-specific head. We further introduce PathSeg-380K, a semantic segmentation dataset with expert annotations for approximately 380,000 cells across 12 cell types. Experiments on multiple pathology datasets show that the proposed framework achieves state-of-the-art segmentation performance. Our code is publicly available at https://github.com/script-Yang/Agent-GenPath.
Nov 4, 2026

PathoS2VD: From 2D Histopathology to Pseudo Z-Stack Representations

For decades, diagnostic pathology has relied on thin two-dimensional (2D) tissue sections, despite biological tissues exhibiting inherently three-dimensional (3D) morphological organization. Because a single section captures only one focal plane, important morphological cues along the z-axis are inevitably discarded, limiting tissue representation for both human interpretation and computational analysis. In this work, we propose a generative framework that learns z-axis morphological priors from pathology z-stack data, offering a cost-effective alternative to dedicated volumetric imaging, and transfers this knowledge to conventional single-plane histopathology. Specifically, an image-to-video (I2V) latent diffusion model (LDM) is trained to synthesize a pseudo z-stack from a single 2D image, capturing plausible morphological variations across adjacent focal planes rather than reconstructing physical tissue volumes. To enable deployment on large-scale clinical datasets without native z-stack acquisition, we further introduce a prior-preserving mixture fine-tuning strategy that adapts the model to new domains while retaining the learned z-axis morphological prior. Extensive experiments demonstrate that the synthesized pseudo z-stacks exhibit realistic cross-plane morphological continuity and consistently improve downstream prostate cancer classification compared with conventional 2D representations. Our results suggest that learning transferable z-axis priors from limited z-stack data provides a practical way to enrich routine pathology images with complementary morphological information. Code: https://github.com/QuIIL/PathoS2VD.
Nov 4, 2026

3D Banff Glomerulitis Scoring for Kidney Transplant Pathology: Feasibility Study for Volumetric Quantification

Quantifying glomerular inflammation in kidney-transplant biopsies is traditionally performed on single whole-slide sections using the Banff "most-severe section" rule, despite the inherently three-dimensional nature of lesion distribution. This 2D based assessment might lead to instability when inflammation varies across slices. This paper reports a feasibility study examining the technical feasibility and clinical relevance of extending Banff scoring into three dimensions. To this end, we propose a 3D Banff lesion-scoring framework that aligns serial sections, reconstructs glomerular identities across depth, and integrates inflammatory-cell counts in 3D under three scoring strategies: Compatible, Volumetric, and Deduplicated Volumetric. In the experiments, glomerulitis (g-scores) was used as an example Banff metric and applied to multi-section renal allograft biopsies. Our findings indicate that 3D Banff g-scores are more consistent across sections and, under the semi-automatic setting, the Volumetric strategy correlates more strongly with clinical biomarkers than traditional 2D scores. These results show that 3D volumetric quantification offers promising added value, underscoring the potential benefit of 3D-aware Banff scoring for kidney transplant pathology.
Nov 3, 2026

When Cell Crops Share a Parent: Measuring and Isolating Acquisition Leakage in Cervical Cytology Benchmarks

Public cervical cytology benchmarks release many cell crops cut from far fewer microscope fields or slides and are often split at the crop level, so test cells share acquisition parents with training cells. In a preregistered study, crop-level splitting raised SIPaKMeD accuracy by 0.97 percentage points across twelve architectures and twenty seeds (95% CI 0.59-1.39), and CRIC accuracy by 12.08 points (11.16-12.99). On SIPaKMeD, a factorial that fixes training crop and parent counts attributes the gain to sibling exposure (1.73 points, 0.95-2.51), not to the extra parent diversity of crop-level splits (0.00). Parent identity is decodable at about 100 times chance, yet erasing 82% of its above-floor linear recoverability left the gap unchanged, and Grad-CAM did not distinguish leaking from clean models; matching test cells' color statistics to an unseen same-class field removed most of the advantage. Decodability and saliency cannot substitute for a parent-disjoint split.
Nov 2, 2026

Training-Time Domain Transfer for Generator-Free Diagnostics on Novel Modalities in Computational Pathology

Novel imaging modalities promise improved diagnostics, but AI development is constrained by scarce training data. Inference-time domain transfer can address this by mapping novel modalities to established ones, enabling reuse of existing diagnostic models. However, this introduces hallucination risks, computational overhead, and regulatory complexity. Inspired by sim-to-real transfer, we propose training-time domain transfer, generating synthetic target-domain training data from archived routine samples to enable direct diagnosis on real inputs without inference-time generation. Using unstained prostate histopathology as a proof-of-concept, we compare this approach with inference-time virtual staining and conventional H&E-based cancer detection. Training-time transfer achieved higher concordance with the conventional benchmark than virtual staining for both raw (Cohen's κκ=0.59 vs. 0.37; Gwet's AC1=0.73 vs. 0.29) and deparaffinized tissue (κκ=0.66 vs. 0.61; AC1=0.73 vs. 0.64), supporting its potential for emerging diagnostic modalities.
Nov 1, 2026

Deep Learning for Cervical Cytology Screening: Methods, Algorithms, Challenges and Prospects

Cervical cancer remains a leading cause of cancer death among women, with more than 90% of deaths occurring in low- and middle-income countries, where cytology screening is constrained by a shortage of trained cytopathologists. Deep learning has made automated cytology screening increasingly feasible, but the literature is fragmented across cell, patch and whole-slide-image scales, task formulations and supervision regimes, hindering comparison and clinical translation. This Review synthesizes the deep learning literature for cervical cytology screening, organizing the field along three axes---data scale, functional task and supervision---and distinguishing two clinical roadmaps: whole-slide-image confidence aggregation and cell-level detection with Bethesda classification. We examine 16 publicly available or publicly documented cytology datasets alongside the CAISHI histopathology dataset, compare quantitative performance while exposing incomparable metrics and data leakage, and assess commercial systems, regulatory status, HPV-era screening pathways and low-resource deployment. Single-cell accuracy on Herlev and SIPaKMeD has plateaued, but this reflects benchmark saturation rather than clinical readiness; prospective and randomized evidence is emerging but remains limited. We consolidate the evidence into five challenge areas---data and benchmarks, architecture and label-efficient learning, trustworthy AI, clinical translation and health economics, and evaluation and reproducibility---and provide an evidence-to-agenda map and a deployment decision matrix. Progress now depends on multi-center benchmarks, externally validated label-efficient methods, calibrated and fair predictions, and pragmatic clinical trials rather than further gains on saturated single-cell benchmarks.
Oct 30, 2026

From Cross-Section to Cross-Omics: Conditional Cell Nucleus Image Editing in Spatial Transcriptomics

Spatial transcriptomics (ST) platforms simultaneously measure gene expression and capture cell nucleus images at single-cell resolution. A fundamental property of tissue preparation introduces a confounding relationship between the two measurement modalities: sectioning a three-dimensional tissue into a thin slice produces a two-dimensional cross-section whose area depends on the cutting angle. Larger cross-sections expose more cytoplasm, yielding higher mRNA counts, while pathomics features such as nuclear area are measured directly from the same 2D boundary. This sectioning geometry creates an apparent correlation between gene expression and pathomics that reflects the measurement process rather than independent biology. Existing gene-to-image methods generate cell images from gene features but do not support condition-driven editing of existing images across both omics layers. We apply the Manifold-Aware Diffusion (MAD) framework to this dual-omics editing setting, enabling targeted modification of one feature group while preserving the other. Evaluated on podocyte cells from CosMx SMI kidney tissue, MAD achieves MAE=0.6636 and FID=25.19 for pathomics editing, outperforming all compared baselines. A controlled simulation study further confirms that the VAE component in MAD better preserves cross-group independence than CCDM (MAD without VAE).
Oct 30, 2026

TopoHyperClinicalGraph: A Geometry and Topology-Aware Multimodal Framework for Cancer Survival Prediction

We developed TopoHyperClinicalGraph, a multimodal framework combining hyperbolic tissue geometry, persistent topology and clinical graph learning for cancer survival prediction. Pre-extracted UNI2-h features are reduced from 1,536 to 1,024 dimensions using training-fold PCA. A pathology backbone combines hyperbolic neighborhoods with Lorentz-centroid attention pooling. Once frozen, its survival logits are adjusted using persistence descriptors from up to 64 landmarks per slide and sampling controls. A five-node clinical graph then learns a further correction from age, sex, stage, T and N. Five-fold patient-level evaluation covered eight TCGA and CPTAC cohorts with 2,364 patients. Mean validation-selected C-indices for TopoHyperClinicalGraph versus pathology-only spatial PatchGCN were 0.7563 versus 0.7386 in COADREAD, 0.6220 versus 0.5998 in HNSC, 0.6755 versus 0.6535 in BRCA and 0.6409 versus 0.6176 in STAD. CPTAC scores were 0.5984 in HNSC, 0.6060 in PDA, 0.8055 in CCRCC and 0.7192 in LUAD. CPTAC-HNSC used TCGA-initialized adaptation; other CPTAC backbones were trained within their cohorts. Geometry accounted for most pathology-only gains, with smaller persistence effects. Clinical graph fusion exceeded its matched node-wise control in five cohorts, tied in one and scored lower in two; clinical-only prediction exceeded fusion in three CPTAC cohorts. The framework supports separate evaluation of geometric, topological and clinical contributions. All scores were validation-selected; independent testing is needed to establish generalizability.
Oct 30, 2026

Interpretable Multiple-Instance Learning of Glomerular Pathomics and Subtype Ratios for eGFR Classification

Chronic kidney disease is characterized by structural alterations in renal tissue and progressive loss of kidney function. While glomerular subtype ratios provide a compact and clinically meaningful summary of glomerular composition, representing pathomic information using whole-slide image (WSI)-level mean values diminishes glomerulus-level heterogeneity and the contribution of less prevalent patterns. In this proof-of-concept study, we investigated whether modeling individual glomeruli using multiple-instance learning (MIL) could provide complementary information to conventional subtype ratios for estimated glomerular filtration rate (eGFR) classification. We analyzed 162 kidney-biopsy WSIs from 162 patients, categorizing renal function as eGFR < 60 or >= 60 mL/min/1.73 m^2. Quantitative size, shape, intensity, and texture features were extracted from segmented glomeruli, representing each patient as a bag of glomerular instances. An attention-based MIL model was trained to aggregate these heterogeneous pathomic profiles. We evaluated subtype ratios, pathomics, and their combination using ABMIL, with a mean-pooled multilayer perceptron baseline. In five-fold cross-validation, the subtype-ratio-only model achieved an AUC of 0.7262 +/- 0.0596. MIL using pathomics alone achieved an AUC of 0.7362 +/- 0.0788, whereas integrating pathomics with subtype ratios produced the highest mean AUC of 0.7630 +/- 0.0665. SHapley Additive exPlanations (SHAP) were used to examine individual feature contributions. These results demonstrate that MIL-based pathomics can complement established glomerular subtype ratios by capturing additional glomerulus-level information for quantitative kidney-biopsy analysis.
Oct 29, 2026

Sparse Autoencoders for Expert-Assisted Interpretation of Histopathology Foundation Model Embeddings

Histopathology foundation models learn rich embedding representations, but their internal structure remains difficult to inspect. Concept-level interpretability is particularly relevant in computational pathology because pathologists reason through recurring morphological and tissue-level patterns, including tissue architecture, cellular morphology, staining variation, and artifacts. In this work, we investigate whether sparse autoencoders (SAEs) can decompose embeddings from histopathology foundation models into sparse latent features suitable for expert-assisted interpretation. We train vanilla and Batch-TopK SAE variants on NCT-CRC embeddings, using CONCH as the primary foundation model and UNI2-h as an additional robustness evaluation, and characterize the resulting latent features through reconstruction fidelity, sparsity, coherence, label enrichment, and downstream class-signal preservation. The learned sparse representations preserve most downstream tissue-class information, and their latent features retrieve more coherent and label-concentrated patch groups than raw embedding dimensions or PCA components. Discussions with pathology experts further motivated a WSI-level latent visualization workflow that places feature activations into larger tissue context. Overall, the additional UNI2-h evaluation suggests that the observed behavior is not specific to CONCH, supporting the use of sparse autoencoders for expert-assisted analysis of histopathology foundation-model embeddings, while emphasizing that latent features should be treated as candidate concepts requiring pathological assessment rather than automatically validated histopathological concepts.
Oct 29, 2026

Conformal Annotation with Randomized Expert Review: Application to Online Cell-Type Labeling

Artificial intelligence (AI) models can accelerate cell-type annotation in digital pathology, but safely scaling their use requires determining, with error control, which model-generated labels can be accepted without expert review. This is challenging in evolving workflows because cell morphology and type composition may change across tissue regions and slides, making one-time calibration unreliable. We propose Conformal Annotation with Randomized Expert review under Distribution shift (CARED), a distribution-free framework that leverages randomized expert audit to achieve long-run error control for AI-assisted annotation under distribution shift. For each incoming batch, CARED uniformly selects a subset of cases for expert review and uses the acquired labels to calibrate later decisions. Among unreviewed cases, CARED determines a subset of them to safely skip expert labeling, while suggesting candidate labels for the others for downstream resolution. We prove that this workflow provides long-run control of cumulative error over both the full stream and the cells outside of the audit sample, without stationarity or exchangeability assumptions. We further enhance the framework by introducing class-conditional guarantees to ensure error control within important but rare cell types, together with a utility module to target more automatic resolutions, smaller candidate sets, and greater biological coherence, without compromising validity. Experiments on pancreas, lung, and ovary annotation streams, together with a stream constructed from real expert annotations, show that CARED controls the cumulative errors while a substantial fraction of cells (up to 70%) bypass expert review.
Oct 29, 2026

PathCowork: Learning from real-world pathology practice to build AI copilots

Medical AI learns from the answers doctors record, but rarely from how they interpret the evidence to reach them. Here we introduce PathCowork, a framework that turns pathologists' narrated examinations into supervision for visual grounding and procedures that guide diagnostic AI agents. Synchronized gaze, narration and navigation link visual findings to the process of interpreting them. Across 48 sessions from 16 pathologists, the platform captured 1,028 minutes of slide review. Using these data, we trained PathCowork-1T for server deployment and PathCowork-27B for local deployment, with improved visual grounding. Across five organ-specific evaluations, agents combining this grounding with recorded diagnostic procedures achieved primary task scores averaging 17.9 and 24.1 percentage points higher than Claude Code and Codex, respectively, with shorter processing times and lower inference costs. Compared to the state-of-the-art multiple-instance learning AIs, the PathCowork agent-proposed regions achieved higher prostate-grading scores with limited slide labels. PathCowork can also help construct pathology AI benchmarks where questions derived from the recordings identified difficulties in recognizing viewing context and rejecting inapplicable premises. In summary, PathCowork proposes a new paradigm to scale up the data collection and train pathology AI through transparent reasoning from diagnostic sessions, opening a path towards systems that learn directly from routine clinical practice.
Oct 27, 2026

PRISM: Pathology Reliability In Scarce-label Medicine. A Tile-level Benchmark of Pathology Foundation Models

Pathology foundation models are typically benchmarked on classification performance at full label availability and on in-distribution test sets, while calibration, behavior at low label budgets, and robustness under cross-institutional shift are seldom evaluated jointly. We introduce PRISM, a tile-level benchmark that measures the reliability of pathology foundation models along four axes: model choice, label fraction, calibration, and out-of-distribution transfer. PRISM evaluates eight foundation models (CLIP, PLIP, CONCH, UNI, Virchow2, GigaPath, H-Optimus-0, Midnight) on six tile-level datasets at six label fractions (1% to 100%) with three seeds (864 linear probe runs), extended with a five-hospital Camelyon17 study of 20 directed transfer pairs. Four phenomena emerge. (i) Under full supervision, AUROC rank predicts post-temperature calibration rank consistently across datasets (Spearman rho = 0.52, I^2 = 0%), whereas at 1% labels the relationship becomes dataset-specific (rho = -0.24, I^2 = 67%). (ii) On harder datasets the linear probe collapses to a single predicted class below a dataset-specific label fraction. (iii) Whether additional source-domain labels help or harm target calibration tracks how well the probe transfers: below a transfer AUROC of roughly 0.85, more labels worsen target ECE in 86-88% of combinations. (iv) Temperature scaling fails to reduce ECE in 49 of 288 cells, miscalibration is predominantly under-confidence, and a source-fitted temperature is harmful under failing transfer. PRISM is released as a pip-installable package with reference results for all 288 cells. Code and data: https://github.com/alicemkyn/prism-benchmark
Oct 26, 2026

When Slides Met Scans: Cross-Attention for Renal Cancer Prognosis

Histopathology and computed tomography (CT) provide complementary views of renal cancer. We connect these modalities through bidirectional cross-attention between 16 histology prototypes and up to 32 kidney-centered CT tokens from frozen foundation models. In 210 TCGA-KIRC patients with 46 disease-specific survival (DSS) events, 5-fold evaluation yielded a C-index of 0.760±0.0810.760\pm0.081 and 3-year AUROC of 0.773 (95% CI 0.678--0.860), the highest averages among evaluated unimodal and fusion baselines. External testing in 180 CPTAC-CCRCC patients yielded DSS C-index of 0.629 with CT withheld. Attribution analysis linked predictions to image regions while exposing acquisition artifacts. These findings support further study of cross-scale fusion and independent multimodal validation.
Oct 26, 2026

Biology-Guided Context-Aware Residual Propagation for Spatial Gene Expression Prediction from Histology

Spatial transcriptomics provides spatially resolved molecular profiling, but its cost, limited throughput and experimental complexity hinder routine large-scale use. Predicting spatial gene expression from hematoxylin-and-eosin-stained histology images offers a scalable alternative, yet remains challenging because histology provides only an indirect morphological view of molecular activity. Existing methods typically decode expression from visual features in a single stage, even when enhanced with spatial aggregation, retrieval or multi-resolution fusion. This formulation is restrictive because spot-level expression reflects not only local morphology but also cellular identity, neighborhood composition and tissue-level organization. We propose BCARP, a Biology-guided Context-Aware Residual Propagation framework for histology-guided spatial transcriptomics prediction. Instead of directly predicting gene expression from histology embeddings, BCARP treats them as morphology visual priors and progressively refines spot representations in a transcriptomics-oriented latent space. Each refinement step integrates nuclei-guided local cellular context with prototype-guided global context propagation, enabling information exchange across both neighboring and spatially distant spots. A pattern-scale decoder further separates spatial expression into pattern prediction from raw expression with scale calibration. Evaluated on three ST datasets and ten HEST-1k cohorts, BCARP achieves the highest mean correlation-based performance against other baselines. Numerical results support biology-guided local-global residual propagation as an effective alternative to visual decoding for histology-to-transcriptomics prediction.
Oct 23, 2026

PathJev: Decision-Native Vision-Language Modelling for Histopathology

Vision-language models used for decisions in histopathology rarely return calibrated probabilities over the candidates a user cares about. Decision-native models write a question and a candidate set chosen at run time into the input and return a normalised distribution from a small decision head in one forward pass. We build PathJev-P, a decision-native model for histopathology: MedGemma-1.5-4B with LoRA adapters and a decision head, trained on 40,000 patch states from three public collections whose expert labels are turned into typed questions with organ-specific candidate sets and a "none of these" option. In a comparison over 3 seeds with an analysis plan fixed before testing, on test sets without documented overlap with the training data of the backbone, PathJev-P is more accurate than a generative model trained with the same backbone, data and selection rule, the zero-shot pathology model CONCH and a general medical decision model (balanced accuracy 0.541 against 0.492, 0.345 and 0.213); its advantage over the generative model comes from two organs absent from training. The calibration advantage depends on how the generative model's probabilities are read out. With the summed candidate log-likelihood used in previous work, PathJev-P has the lower calibration error (ECE 0.204 against 0.279); with a length-normalised read-out of the same generative model, examined post hoc, the two have similar mean calibration error (0.201) and the generative model is better calibrated on the unseen organs, where PathJev-P remains over-confident. A supervised linear probe on a pathology foundation model is better calibrated in every setting. In a qualitative whole-slide demonstration, PathJev-P labels unsupervised tissue clusters with abstention and separates carcinoma from other tissue while running the model on a fraction of the tiles.
Oct 23, 2026

AutoMIL: Automated Multiple Instance Learning for Whole-Slide Image Classification

Developing multiple instance learning pipelines for the classification of whole-slide images involves many interdependent design decisions and expertise in both pathology and machine learning. We present AutoMIL, an open-source framework that applies principles from the field of automated machine learning to tackle this task by automating integral pipeline steps, such as preprocessing, training and evaluation. In a benchmark evaluation with default settings, AutoMIL reached ROC-AUC scores of 0.94 on UBC-OCEAN, 0.99 on PCam and 0.93-0.96 on a TCGA-NSCLC subset, comparable to specialised pipelines in related work. Ensembling mainly improved performance on imbalanced data, showing that an automated pipeline must adapt to dataset characteristics. AutoMIL thus provides an accessible baseline for whole-slide image classification without manual pipeline configuration.
Oct 22, 2026

Attention-guided classification and tumor localization of combined hepatocellular-cholangiocarcinoma

Combined hepatocellular-cholangiocarcinomas (cHCC-CCA) are a type of cancer that share components of two other primary liver cancers: hepatocellular carcinoma (HCC) and cholangiocarcinoma (CCA). Accurate diagnosis of cHCC-CCA, of which the behavior may resemble that of either HCC or CCA, remains a challenge due to strong intratumoral heterogeneity. Since the prognoses differ between liver cancer types, it is necessary to improve their morphological characterization and recognition in order to accurately identify cHCC-CCA. In this work, we use whole slide images (WSIs) of the two main types of liver cancer (HCC and CCA) and cHCC-CCA, stained with Hematoxylin-Eosin-Safran (HES), to train a classification model that can distinguish between these subtypes and provides a potential solution for localizing different types of tumors in the combined liver cancer images.
Oct 21, 2026

Learning to Reason Like a Cytopathologist:Clinically Grounded Multiscale Evidential Learning for Cervical Cytology

Cervical cytology presents a fundamentally ambiguous diagnostic landscape, where equivocal categories such as Atypical Squamous Cells of Undetermined Significance (ASC-US) occupy a morphological grey zone that is definitional. For clinical decision support, the goal extends beyond assigning a definitive label to every sample: cases must also be distinguished by whether the available evidence supports a confident decision or warrants further consideration, a distinction conventional classification models are not designed to explicitly represent. We propose a multiscale evidential framework that models cervical cytology along an ordinal disease continuum using clinically grounded soft anchors, representing progression from benign reactive changes to precancerous lesions and malignancy. Three biologically motivated spatial contexts--nuclear morphology, cytoplasmic characteristics, and neighbourhood cellular architecture--are independently encoded using a shared frozen DINOv2 backbone, preserving inter-scale disagreement that early fusion may obscure. Calibrated predictions are transformed into Dempster--Shafer belief masses and fused with reliability discounting, allowing conflicting evidence and insufficient support to remain explicitly uncommitted rather than forcing a decision. The fused belief state drives interpretable routing that separates confidently classified cases from those with irreducible evidential insufficiency, enabling clinically meaningful triage. Across two independent publicly available conventional cytology datasets, RIVA and CRIC Cervix, the framework generalises consistently, with uncertainty strongly associated with diagnostic difficulty: incorrect predictions carry 1.94x-4.13x higher uncertainty than correct ones.
Oct 21, 2026

SWIFT-Cell: Segmentation Without Iterative Flow Tracking

Generalist segmenters such as Cellpose-SAM (CPSAM) outline cells accurately across stains but slowly; watershed detectors such as QuPath's are fast but less accurate. In time-critical use, such as interactive retrieval of cells from a user-drawn region, CPSAM at the reference settings takes 58-303 s per measured 8192 x 8192 region on an RTX 4500 Ada GPU, beyond a seconds-scale interactive target. We distil CPSAM into SWIFT-Cell (SWIFT), a 0.63M-parameter U-Net trained only on CPSAM masks of 1,202 H&E and IHC tiles. On three 8192 x 8192 development regions SWIFT takes 2.0-5.2 s on 4 CPU cores in int8, 2.5-5.1x faster than QuPath's detector on the same cores, and 0.36-0.49 s on a GPU. Against human annotations on eight H&E, IHC and ISH sets it keeps 95% of CPSAM's panoptic quality (PQ) on PanNuke (0.593 vs. 0.627) and is level on NuCLS (0.546 vs. 0.540). On Ki-67 IHC masks scored to the outline centre it is 0.205 PQ above QuPath's better mode, 0.079 below CPSAM and 0.027 below InstanSeg (CI includes 0; at the outer edge 0.008 below CPSAM); on 212 pathologist-outlined nuclei in Ki-67 fields of 12 untouched patients its recall is 0.925 (CPSAM 0.920, InstanSeg 0.901; paired difference CIs include 0); one method-blinded pathologist accepted its outlines in 96% of 100 fields (60 from two development tissue patients, 40 hematology; CPSAM 83%, QuPath 53%; tissue 100% for SWIFT and CPSAM); on ER/PR points from 12 patients its detection F1 is 0.882 (CPSAM 0.896, InstanSeg 0.857), and on 4-reader PD-L1 points 0.83 (CPSAM 0.85, readers 0.87). SWIFT is close to CPSAM in accuracy and faster than watershed detection.
Oct 20, 2026

AdaptMIL: Domain Adaptation for Multiple Instance Learning in Digital Pathology

Pathology foundation models (PFMs) support a wide range of histopathology tasks on whole-slide images through multiple instance learning (MIL). Despite recent progress, these models remain sensitive to cross-hospital distribution shifts: performance often degrades when a task head (e.g., classification) is trained on data from one hospital and then used on data from another hospital. To address this challenge, we propose AdaptMIL, a training strategy for integrating domain adaptation into MIL training. AdaptMIL is motivated by our finding that directly applying domain adaptation objectives during MIL training can interfere with MIL aggregation learning, often resulting in performance degradation over standard training. AdaptMIL resolves this by decoupling representation-level domain alignment learning from MIL aggregation learning through a two-stage training procedure. We show that AdaptMIL improves cross-hospital performance and outperforms alternative adaptation methods across experiments spanning multiple WSI datasets, tasks, PFMs, MIL architectures, and domain adaptation objectives. AdaptMIL's code will be released upon publication.