Investigating Gender Bias in Lymph-node Segmentation with Anatomical Priors

TL;DR

This paper explores how incorporating anatomical priors can improve lymph-node segmentation in radiotherapy, especially reducing gender bias and enhancing accuracy for female patients.

Contribution

It introduces a novel approach using anatomical priors to mitigate gender bias in deep learning-based segmentation models.

Findings

Incorporating priors improves segmentation accuracy in females.

The approach reduces gender bias in abdominal segmentation.

New encoding strategies outperform existing methods.

Abstract

Radiotherapy requires precise segmentation of organs at risk (OARs) and of the Clinical Target Volume (CTV) to maximize treatment efficacy and minimize toxicity. While deep learning (DL) has significantly advanced automatic contouring, complex targets like CTVs remain challenging. This study explores the use of simpler, well-segmented structures (e.g., OARs) as Anatomical Prior (AP) information to improve CTV segmentation. We investigate gender bias in segmentation models and the mitigation effect of the prior information. Findings indicate that incorporating prior knowledge with the discussed strategies enhances segmentation quality in female patients and reduces gender bias, particularly in the abdomen region. This research provides a comparative analysis of new encoding strategies and highlights the potential of using AP to achieve fairer segmentation outcomes.