paper-with-me

홈 › Papers

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

2026-03-07 · Marco Gustav, Fabian Wolf, Christina Glasner, Nic G. Reitsam, Stefan Schulz, Kira Aschenbroich, Bruno Märkl, Sebastian Foersch, Jakob Nikolas Kather arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.07170

Code (0)

등록된 구현이 없습니다.

Tasks

Cancer Classification

Similar Papers 제목 키워드 기반

How Well do Feature Visualizations Support Causal Understanding of CNN Activations?

2021-06-23 · NeurIPS 2021 12 · Roland S. Zimmermann, Judy Borowski, Robert Geirhos, Matthias Bethge 외

A precise understanding of why units in an artificial network respond to certain stimuli would constitute a big step towards explainable artificial intelligence. One widely used approach towards this goal is to visualize…

Explainable artificial intelligence

Enhancing Deep Neural Network Saliency Visualizations with Gradual Extrapolation

2021-04-11 · Tomasz Szandala

In this paper, an enhancement technique for the class activation mapping methods such as gradient-weighted class activation maps or excitation backpropagation is proposed to present the visual explanations of decisions f…

Exemplary natural images explain CNN activations better than synthetic feature visualizations

2021-01-01 · ICLR 2021 1 · Judy Borowski, Roland Simon Zimmermann, Judith Schepers, Robert Geirhos 외

Feature visualizations such as synthetic maximally activating images are a widely used explanation method to better understand the information processing of convolutional neural networks (CNNs). At the same time, there a…

Informativeness

Feature CAM: Interpretable AI in Image Classification

2024-03-08 · Frincy Clement, Ji Yang, Irene Cheng

Deep Neural Networks have often been called the black box because of the complex, deep architecture and non-transparency presented by the inner layers. There is a lack of trust to use Artificial Intelligence in critical …

Classificationimage-classificationImage Classification

Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization

2020-10-23 · Judy Borowski, Roland S. Zimmermann, Judith Schepers, Robert Geirhos 외

Feature visualizations such as synthetic maximally activating images are a widely used explanation method to better understand the information processing of convolutional neural networks (CNNs). At the same time, there a…

Informativeness