Resolving challenges in deep learning-based analyses of histopathological images using explanation methods

Abstract

Deep learning has recently gained popularity in digital pathology due to its high prediction quality. However, the medical domain requires explanation and insight for a better understanding beyond standard quantitative performance evaluation. Recently, explanation methods have emerged, which are so far still rarely used in medicine. This work shows their application to generate heatmaps that allow to resolve common challenges encountered in deep learning-based digital histopathology analyses. These challenges comprise biases typically inherent to histopathology data. We study binary classification tasks of tumor tissue discrimination in publicly available haematoxylin and eosin slides of various tumor entities and investigate three types of biases: (1) biases which affect the entire dataset, (2) biases which are by chance correlated with class labels and (3) sampling biases. While standard analyses focus on patch-level evaluation, we advocate pixel-wise heatmaps, which offer a more precise and versatile diagnostic instrument and furthermore help to reveal biases in the data. This insight is shown to not only detect but also to be helpful to remove the effects of common hidden biases, which improves generalization within and across datasets. For example, we could see a trend of improved area under the receiver operating characteristic curve by 5% when reducing a labeling bias. Explanation techniques are thus demonstrated to be a helpful and highly relevant tool for the development and the deployment phases within the life cycle of real-world applications in digital pathology.

References in corpus (8)

• Deep Learning in Neural Networks: An Overview
• A Survey on Deep Learning in Medical Image Analysis
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Methods for Interpreting and Understanding Deep Neural Networks
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• Computational Pathology: Challenges and Promises for Tissue Analysis
• Automatic brain tumor grading from MRI data using convolutional neural networks and quality assessment

Cited by in corpus (13)

• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• Explainable artificial intelligence (XAI) in deep learning-based medical image analysis
• Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning
• Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma
• GANterfactual - Counterfactual Explanations for Medical Non-Experts using Generative Adversarial Learning
• From Modern CNNs to Vision Transformers: Assessing the Performance, Robustness, and Classification Strategies of Deep Learning Models in Histopathology
• Deep learning in biomedical optics
• Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
• Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces
• Analysis and Validation of Image Search Engines in Histopathology
• Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks
• Interpretation of Disease Evidence for Medical Images Using Adversarial Deformation Fields
• ProtoP-OD: Explainable Object Detection with Prototypical Parts