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

by   Miriam Hägele, et al.

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 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.


page 1

page 8

page 9

page 15

page 16

page 19


Quantitative Impact of Label Noise on the Quality of Segmentation of Brain Tumors on MRI scans

Over the last few years, deep learning has proven to be a great solution...

Multi-domain stain normalization for digital pathology: A cycle-consistent adversarial network for whole slide images

The variation in histologic staining between different medical centers i...

Deep Learning Models for Digital Pathology

Histopathology images; microscopy images of stained tissue biopsies cont...

Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification

Convolutional Neural Networks have demonstrated dermatologist-level perf...

XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models

NLP models are susceptible to learning spurious biases (i.e., bugs) that...

ABC-KD: Attention-Based-Compression Knowledge Distillation for Deep Learning-Based Noise Suppression

Noise suppression (NS) models have been widely applied to enhance speech...

Please sign up or login with your details

Forgot password? Click here to reset