Home  | Publications | LKZ+22

Analyzing the Effects of Handling Data Imbalance on Learned Features From Medical Images by Looking Into the Models

MCML Authors

Link to Profile Bernd Bischl PI Matchmaking

Bernd Bischl

Prof. Dr.

Director

Statistical Learning and Data Science

Link to Profile Nassir Navab PI Matchmaking

Nassir Navab

Prof. Dr.

Principal Investigator

Computer Aided Medical Procedures & Augmented Reality

Abstract

One challenging property lurking in medical datasets is the imbalanced data distribution, where the frequency of the samples between the different classes is not balanced. Training a model on an imbalanced dataset can introduce unique challenges to the learning problem where a model is biased towards the highly frequent class. Many methods are proposed to tackle the distributional differences and the imbalanced problem. However, the impact of these approaches on the learned features is not well studied. In this paper, we look deeper into the internal units of neural networks to observe how handling data imbalance affects the learned features. We study several popular cost-sensitive approaches for handling data imbalance and analyze the feature maps of the convolutional neural networks from multiple perspectives: analyzing the alignment of salient features with pathologies and analyzing the pathology-related concepts encoded by the networks. Our study reveals differences and insights regarding the trained models that are not reflected by quantitative metrics such as AUROC and AP and show up only by looking at the models through a lens.

inproceedings

IMLH @ICML 2022

2nd Workshop on Interpretable Machine Learning in Healthcare at the 39th International Conference on Machine Learning. Baltimore, MD, USA, Jul 17-23, 2022.

Authors

A. Khakzar • Y. Li • Y. Zhang • M. Sanisoglu • S. T. Kim • M. Rezaei • B. Bischl • N. Navab

Links

Research Areas

 A1 | Statistical Foundations & Explainability

 C1 | Medicine

BibTeXKey: LKZ+22

Back to Top