Detecting Shortcuts in Medical Images -- A Case Study in Chest X-rays

2022/11/08 by Amelia Jiménez-Sánchez, Jiménez-Sánchez, Amelia, Dovile Juodelyte +5 · 5 citations
Medicine · Computer Science · #COVID-19 diagnosis using AI #Radiomics and Machine Learning in Medical Imaging #AI in cancer detection

paper · pdf · doi:10.48550/arxiv.2211.04279

Abstract

The availability of large public datasets and the increased amount of computing power have shifted the interest of the medical community to high-performance algorithms. However, little attention is paid to the quality of the data and their annotations. High performance on benchmark datasets may be reported without considering possible shortcuts or artifacts in the data, besides, models are not tested on subpopulation groups. With this work, we aim to raise awareness about shortcuts problems. We validate previous findings, and present a case study on chest X-rays using two publicly available datasets. We share annotations for a subset of pneumothorax images with drains. We conclude with general recommendations for medical image classification.

Cited by

• Localising Shortcut Learning in Pixel Space via Ordinal Scoring Correlations for Attribution Representations (OSCAR)
• meval: A Statistical Toolbox for Fine-Grained Model Performance Analysis
• Effect of Demographic Bias on Skin Lesion Classification
• Transparency of medical artificial intelligence systems
• Fairness and Robustness of CLIP-Based Models for Chest X-rays

Related

• Fairness and Robustness of CLIP-Based Models for Chest X-rays
• Augmenting Chest X-ray Datasets with Non-Expert Annotations
• Pneumothorax and chest tube classification on chest x-rays for detection of missed pneumothorax
• Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation
• Chest x-ray automated triage: a semiologic approach designed for clinical implementation, exploiting different types of labels through a combination of four Deep Learning architectures