Class Visualizations and Activation Atlases for Enhancing Interpretability in Deep Learning-Based Computational Pathology

• URL: http://arxiv.org/abs/2603.07170v2
• Date: Tue, 10 Mar 2026 07:57:54 GMT
• Title: Class Visualizations and Activation Atlases for Enhancing Interpretability in Deep Learning-Based Computational Pathology
• Abstract summary: Class visualizations (CVs) and activation atlases (AAs) were evaluated for a transformer-based foundation model.<n>CVs preserved recognizability for morphologically distinct tissues but showed reduced separability for overlapping cancer subclasses.<n>AAs revealed layer-dependent organization: coarse tissue-level concepts formed coherent regions, whereas finer subclasses exhibited dispersion and overlap.
• Score: 1.5921492981295717
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid adoption of transformer-based models in computational pathology has enabled prediction of molecular and clinical biomarkers from H&E whole-slide images, yet interpretability has not kept pace with model complexity. While attribution- and generative-based methods are common, feature visualization approaches such as class visualizations (CVs) and activation atlases (AAs) have not been systematically evaluated for these models. We developed a visualization framework and assessed CVs and AAs for a transformer-based foundation model across tissue and multi-organ cancer classification tasks with increasing label granularity. Four pathologists annotated real and generated images to quantify inter-observer agreement, complemented by attribution and similarity metrics. CVs preserved recognizability for morphologically distinct tissues but showed reduced separability for overlapping cancer subclasses. In tissue classification, agreement decreased from Fleiss k = 0.75 (scans) to k = 0.31 (CVs), with similar trends in cancer subclass tasks. AAs revealed layer-dependent organization: coarse tissue-level concepts formed coherent regions, whereas finer subclasses exhibited dispersion and overlap. Agreement was moderate for tissue classification (k = 0.58), high for coarse cancer groupings (k = 0.82), and low at subclass level (k = 0.11). Atlas separability closely tracked expert agreement on real images, indicating that representational ambiguity reflects intrinsic pathological complexity. Attribution-based metrics approximated expert variability in low-complexity settings, whereas perceptual and distributional metrics showed limited alignment. Overall, concept-level feature visualization reveals structured morphological manifolds in transformer-based pathology models and provides a framework for expert-centered interrogation of learned representations across label granularities.

Related papers

• MAGE: Color-Invariant and Spatial Knowledge Distillation for Gastric Neoplasm Classification [3.371633041086325]
  We propose a novel framework, Masked Achromatic Guidance Expert (MAGE)<n>During training, we introduce an auxiliary local expert branch trained on masked achromatic views of the neoplasm.<n>By suppressing background context and color, this branch is forced to learn highly discriminative, purely structural features.<n>At inference time, our deployable model operates on images without annotated masks, ensuring real-time deployability.
  arXiv  Detail & Related papers  (2026-07-14T11:45:48Z)
• PulmoSight-XAI: An Explainable Multi-View Attention Ensemble with Gradient Boosting Meta-Learning for Multi-Label Chest X-Ray Classification [1.2744523252873352]
  We propose an explainable hierarchical multi-view ensemble framework for the robust classification of 14 thoracic pathologies.<n>The framework employs view-specific training by independently modeling frontal and lateral radiographs.<n>The framework achieves state-of-the-art macro-average AUROC scores of 0.9319 for frontal and 0.9154 for lateral radiographs.
  arXiv  Detail & Related papers  (2026-07-05T19:50:53Z)
• PathAR: Structure-First Autoregressive Synthesis of Multimodal Pathology Images [51.428093790826814]
  We propose pathology Autorgressive modeling (PathAR) to factorize structure and appearance for modality-label-conditioned pathology generation.<n>PathAR stabilizes morphology under heterogeneous modality-specific appearances and enables spatially aligned image-mask pair generation.
  arXiv  Detail & Related papers  (2026-06-01T01:43:48Z)
• Multi-View Synergistic Learning with Vision-Language Adaption for Low-Resource Biomedical Image Classification [59.24009931000134]
  Multi-View Synergistic Learning (MVSL) is a unified framework that addresses adaptation paradigms, representation granularity, and disease semantic relationships.<n>MVSL decouples the adaptation of visual and textual encoders to respect their distinct representational characteristics.<n>It further introduces multi-granularity contrastive learning to explicitly model both global image semantics and localized lesion-level evidence.<n>MVSL consistently outperforms state-of-the-art methods in few-shot and zero-shot classification settings.
  arXiv  Detail & Related papers  (2026-04-27T02:41:27Z)
• GAFR-Net: A Graph Attention and Fuzzy-Rule Network for Interpretable Breast Cancer Image Classification [0.0]
  We propose GAFRNet, a robust and interpretable Graph Attention and FuzzyRule Network for histopathology image classification.<n>We show that GAFR-Net consistently outperforms various state-of-the-art methods across multiple magnifications and classification tasks.<n>These results validate the superior generalization and practical utility of GAFR-Net as a reliable decision-support tool for weakly supervised medical image analysis.
  arXiv  Detail & Related papers  (2026-02-10T01:25:57Z)
• A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis [82.01597026329158]
  We introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS) for pathology-specific text-to-image synthesis.<n>CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy.<n>This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations.
  arXiv  Detail & Related papers  (2025-12-15T10:22:43Z)
• Proof of Concept for Mammography Classification with Enhanced Compactness and Separability Modules [0.0]
  This study presents a validation and extension of a recent methodological framework for medical image classification.<n>Using a Kaggle dataset that consolidates INbreast, MIAS, and InceptionM mammography collections, we compare a baseline CNN, ConvNeXt Tiny, and InceptionV3 backbones enriched with GAGM and SE modules.<n>Results confirm the effectiveness of GAGM and SE in enhancing feature discriminability and reducing false negatives.<n>In our experiments, however, the Feature Smoothing Loss did not yield measurable improvements under mammography classification conditions.
  arXiv  Detail & Related papers  (2025-12-06T21:36:05Z)
• From Classification to Cross-Modal Understanding: Leveraging Vision-Language Models for Fine-Grained Renal Pathology [9.268389327736735]
  We model fine-grained glomerular subtyping as a clinically realistic few-shot problem.<n>We evaluate both pathology-specialized and general-purpose vision-language models under this setting.
  arXiv  Detail & Related papers  (2025-11-15T01:44:11Z)
• Disentanglement of Biological and Technical Factors via Latent Space Rotation in Clinical Imaging Improves Disease Pattern Discovery [0.4820000447145793]
  We introduce an approach to actively learn the domain shift via post-hoc rotation of the data latent space.<n>Results show that the learned disentangled representation leads to stable clusters representing tissue-types across different acquisition settings.
  arXiv  Detail & Related papers  (2025-09-14T21:16:15Z)
• MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention [57.044719143401664]
  Histopathology and transcriptomics are fundamental modalities in oncology, encapsulating the morphological and molecular aspects of the disease.<n>We present MIRROR, a novel multi-modal representation learning method designed to foster both modality alignment and retention.<n>Extensive evaluations on TCGA cohorts for cancer subtyping and survival analysis highlight MIRROR's superior performance.
  arXiv  Detail & Related papers  (2025-03-01T07:02:30Z)
• The Whole Pathological Slide Classification via Weakly Supervised Learning [7.313528558452559]
  We introduce two pathological priors: nuclear disease of cells and spatial correlation of pathological tiles. We propose a data augmentation method that utilizes stain separation during extractor training. We then describe the spatial relationships between the tiles using an adjacency matrix. By integrating these two views, we designed a multi-instance framework for analyzing H&E-stained tissue images.
  arXiv  Detail & Related papers  (2023-07-12T16:14:23Z)
• Learning disentangled representations for explainable chest X-ray classification using Dirichlet VAEs [68.73427163074015]
  This study explores the use of the Dirichlet Variational Autoencoder (DirVAE) for learning disentangled latent representations of chest X-ray (CXR) images. The predictive capacity of multi-modal latent representations learned by DirVAE models is investigated through implementation of an auxiliary multi-label classification task.
  arXiv  Detail & Related papers  (2023-02-06T18:10:08Z)
• Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective [51.70661197256033]
  We propose ARCO, a semi-supervised contrastive learning framework with stratified group theory for medical image segmentation. We first propose building ARCO through the concept of variance-reduced estimation and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks. We experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings.
  arXiv  Detail & Related papers  (2023-02-03T13:50:25Z)
• G-MIND: An End-to-End Multimodal Imaging-Genetics Framework for Biomarker Identification and Disease Classification [49.53651166356737]
  We propose a novel deep neural network architecture to integrate imaging and genetics data, as guided by diagnosis, that provides interpretable biomarkers. We have evaluated our model on a population study of schizophrenia that includes two functional MRI (fMRI) paradigms and Single Nucleotide Polymorphism (SNP) data.
  arXiv  Detail & Related papers  (2021-01-27T19:28:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.