Papers for

computational pathology teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Sparse autoencoders reveal interpretable features in pathology image data

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

Abstract: 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.

Thu 29 OctComputer Vision and Pattern Recognition
The gist
Understanding the complex patterns inside AI models that analyze tissue images is hard. The authors explore how a special type of neural network called a sparse autoencoder can break down these complex model outputs into simpler parts that experts can interpret. Their method keeps important tissue information while grouping similar tissue patterns together more clearly than other techniques. Pathologists found this approach helpful for visualizing tissue features in a wider context, but the features still need expert review before being considered definitive. This method works across different foundation models, suggesting it could be broadly useful for pathology AI analysis.
Open → 2610.40905v1

HistoLoop improves gene activity maps from tissue images using iterative context

HistoLoop: Iterative Contextual Inference with a Looped Transformer for Histology-Based Spatial Gene Expression Prediction

Abstract: Predicting spatial gene expression from H&E images offers a scalable complement to experimental spatial transcriptomics. However, despite progress in spatial context modeling, how to construct subsequent context from spot states updated by earlier contextual interactions remains underexplored. We introduce HistoLoop, a looped Transformer that formulates prediction as iterative contextual inference. At each refinement step, HistoLoop aggregates the current spot states into context tokens at the corresponding resolution, processes them with a shared spatial Transformer, and retrieves spot-specific contextual information through cross-attention. A memory-mediated update integrates this information into persistent spot states, which are then used to construct context at the next, finer resolution. Under the HEST-Bench HVG50 evaluation protocol, HistoLoop achieves the highest macro-averaged gene-wise Pearson correlation among the compared methods across six cancer-specific tasks spanning five organs in HEST-1K. Ablation studies support the importance of recurrent state refinement and reconstructing context from updated spot states at progressively finer resolutions. Expression-derived clustering further suggests that HistoLoop better captures spatially organized multigene patterns.

Tue 20 OctComputer Vision and Pattern Recognition
The gist
Figuring out where genes are active in tissue samples helps scientists understand diseases like cancer. The authors created HistoLoop, a computer method that looks at microscope images of tissues and repeatedly improves its guesses about gene activity by considering neighboring spots. This step-by-step approach lets HistoLoop understand complex gene patterns better than previous methods. Their tests show it works well across different cancers and organs.
Open → 2610.28339v1

Prototype-purity method improves instance learning in pathology images

ProtoPur: Prototype-Purity Pseudo-Labeling for Weakly Supervised Instance Learning in Pathology

Abstract: Weak bag-level labels are widely available in computational pathology, whereas reliable instance-level annotations for whole-slide images remain expensive and ambiguous. Weakly supervised multiple instance learning (MIL) achieves strong bag-level classification, but instance-level supervision from attention scores, model predictions, negative bags, or spatial refinement may fail to identify class-specific local evidence. We propose ProtoPur, a prototype-purity pseudo-labeling method for weakly supervised instance-level learning in pathology whole-slide images. ProtoPur estimates class-balanced local purity over prototype regions constructed from frozen foundation-model features, and assigns pseudo-labels to high-purity regions strongly associated with a target class. This purity-first design separates class-specific evidence from negative or shared morphology, with coverage used only to ensure sufficient pseudo-label assignment. We provide a PAC-style analysis showing that the risk of an instance classifier trained with ProtoPur pseudo-labels can be decomposed into a standard uniform-convergence term and a ProtoPur-specific pseudo-label noise term, comprising selected-region mismatch and a coverage residual. Experiments on three public whole-slide image datasets with two pathology foundation encoders show that ProtoPur consistently improves instance-level performance across multiple MIL backbones while maintaining competitive bag-level performance. Pseudo-label quality comparisons on two public datasets further demonstrate that prototype-purity selection provides stronger instance supervision. These results suggest that the foundation-model features contain exploitable instance-level supervision signals, and ProtoPur is a way to reveal and use these signals from weak bag labels without requiring dense instance annotations.

Sun 11 OctComputer Vision and Pattern RecognitionMachine Learning
The gist
Pathology images are very large and detailed, making it hard and expensive to label specific parts needed for diagnosis. The authors propose ProtoPur, a new way to automatically identify small regions in these images that clearly represent a disease class without needing detailed labels. Their method uses pre-existing features to find pure examples of each class and then assigns labels to them for better learning. Tests show ProtoPur improves the accuracy of learning about small image regions while keeping good whole-image classification.
Open → 2610.15669v1

Masked feature encoding improves pathology image analysis accuracy

Masked Feature Encoding for Large-Scale Whole Slide Image Representation

Abstract: Whole slide image (WSI) analysis in computational pathology follows a multiple instance learning (MIL) pipeline where patch embeddings are extracted independently and aggregated for slide-level prediction, but within-slide variance from staining, scanner, and local texture can overwhelm the discriminative signal. We propose Masked Feature Encoding for Multiple Instance Learning (MFE-MIL), a feature-space masking framework that trains a lightweight MLP adapter jointly with a window-based masked reconstruction branch and a MIL classification head. The two objectives are complementary. Classification guides the adapter to suppress within-slide patch variance, while window-based masked reconstruction provides an auxiliary regularizer for the adapted features without using patch coordinates, coordinate graphs, or segmentation preprocessing. The raster patch-extraction order is used only as a weak implicit prior. At inference, the decoder is removed, leaving only the adapter and MIL head. Across CAMELYON16/17, PANDA, and TCGA-BRCA with four diverse encoders, MFE-MIL improves ACC/F1 for nearly all tested aggregator-encoder settings and AUC in most, outperforms coordinate-based spatial methods (CAMIL), and achieves higher AUC than 2DMamba on three of four datasets (UNI). On five TCGA survival cohorts it improves the average concordance index for every aggregator tested, its most consistent gain. Code is available at https://github.com/AtlasAnalyticsLab/MFE-MIL.

Wed 7 OctComputer Vision and Pattern Recognition
The gist
Analyzing large medical images of tissue slides is tricky because small parts can vary a lot due to lighting, stains, or scanners, which confuses computers trying to find disease patterns. The authors propose a new method called MFE-MIL that helps the computer focus on important signals by masking and reconstructing features in small image windows while also learning to classify. This method reduces distracting differences and improves accuracy in many existing slide analysis systems and datasets. Their approach does not rely on exact patch locations or complex preprocessing, making it simpler to use.
Open → 2610.10225v1

Auditing prediction explanations improves reliability in digital pathology

CHARTER: Auditing Reference Substitution in Hierarchical Compact-Evidence Evaluation for Computational Pathology

Abstract: In digital pathology, compact evidence is often used to explain or audit predictions made by whole-slide image multiple instance learning models. In hierarchical compact-evidence pipelines, candidate filtering introduces a strategy-specific candidate-conditioned prediction alongside the original full-bag prediction. If the evaluation reference changes while the intended target remains the original full-bag prediction, however, not only can the measured fidelity of the same compact evidence change, but comparisons between competing candidate strategies can also change. To make this dependence explicit, we introduce CHARTER, a reference-aware evaluation charter that asks researchers to DECLARE the intended target and reference, QUANTIFY candidate-induced prediction shift, and AUDIT the stability of comparative conclusions. Across the 15 comparisons in our main five-seed Random-K audit, 4 showed determinate reversals; in a matched native-ranking stress test, the ACMIL comparison changed from REVERSED to PRESERVED. CHARTER turns otherwise implicit candidate-filtering and reference choices into an auditable evaluation specification, helping distinguish genuine preservation of the intended prediction from apparent gains induced by changing the prediction being explained.

Tue 6 OctComputer Vision and Pattern RecognitionMachine Learning
The gist
In digital pathology, machines analyze many tiny image parts to diagnose disease, and people try to explain their decisions with short summaries called compact evidence. The authors found that how these summaries are evaluated can change depending on which part of the prediction is checked, which can confuse comparisons. They created CHARTER, a new way to clearly state and test which prediction is being explained, making results more trustworthy. This helps make sure that improvements in explanation methods are real and not just due to changing what part of the prediction is looked at.
Open → 2610.07843v1

RestorePath improves tissue image repair for better diagnosis

Patch-to-Global: Random Patch Diffusion for Globally Consistent Megapixel Artifact Inpainting in Whole Slide Images

Abstract: Although deep learning has advanced Whole Slide Image (WSI) Analysis, tissue artifacts like bubbles and folds often cause silent failures by concealing essential morphology. Current pathology image restoration methods are mostly restricted to small patches, struggling to maintain global structural coherence at a megapixel scale. We introduce RestorePath, a framework for globally consistent megapixel scale inpainting that reconstructs diagnostic structures in histological image to prevent incorrect high-confidence predictions and lower error rates. Our model utilizes a Latent Diffusion Model (LDM) conditioned on Pathology Foundation Model (PFM) embeddings, integrating Large Kernel Attention (LKA) to manage long-range dependencies during random patch diffusion. Enhanced by Distance-Weighted Interpolation (DWI) and an Adaptive Guidance Scale (AGS), RestorePath ensures structural consistency and fidelity by modulating information from surrounding patches. Evaluations across TCGA-BRCA, BACH, and Camelyon16 datasets for images ranging from 512 to 4608 pixels demonstrate state-of-the-art performance in maintaining histological consistency. RestorePath significantly improves downstream Computational Pathology (CP) tasks, outperforming both raw artifact images and the conventional Detect-and-Discard (D&D) approach. The code is available at https://github.com/PathfinderLab/RestorePath

Mon 21 SeptComputer Vision and Pattern Recognition
The gist
Tiny bubbles or folds in microscope images of tissue can hide important details needed for medical diagnosis. The authors developed RestorePath, a computer method that fills in missing or damaged parts of large tissue images while keeping the whole picture coherent. Their approach uses advanced techniques to look at large areas and make sure the filled-in parts fit naturally with their surroundings. Tests on several cancer tissue datasets show RestorePath helps medical analysis tools make fewer mistakes compared to ignoring or discarding damaged regions.
Open → 2609.24116v1