Enhancing Reliability of Medical Image Diagnosis through Top-rank Learning with Rejection Module

TL;DR

This paper introduces a novel top-rank learning approach with a rejection module to improve medical image diagnosis accuracy by effectively handling noisy labels and outliers.

Contribution

It proposes a cooptimized rejection module integrated with top-rank learning to identify and mitigate outliers in medical image diagnosis tasks.

Findings

Enhanced diagnosis accuracy on medical datasets

Effective outlier detection and mitigation

Improved robustness against noisy labels

Abstract

In medical image processing, accurate diagnosis is of paramount importance. Leveraging machine learning techniques, particularly top-rank learning, shows significant promise by focusing on the most crucial instances. However, challenges arise from noisy labels and class-ambiguous instances, which can severely hinder the top-rank objective, as they may be erroneously placed among the top-ranked instances. To address these, we propose a novel approach that enhances toprank learning by integrating a rejection module. Cooptimized with the top-rank loss, this module identifies and mitigates the impact of outliers that hinder training effectiveness. The rejection module functions as an additional branch, assessing instances based on a rejection function that measures their deviation from the norm. Through experimental validation on a medical dataset, our methodology demonstrates its efficacy in detecting and mitigating outliers, improving the reliability and accuracy of medical image diagnoses.