Bridging the Applicator Gap with Data-Doping:Dual-Domain Learning for Precise Bladder Segmentation in CT-Guided Brachytherapy

TL;DR

This paper presents a dual-domain learning approach that combines limited applicator-inserted CT scans with more abundant non-applicator scans to improve bladder segmentation accuracy in CT-guided brachytherapy, addressing covariate shift challenges.

Contribution

It introduces a data-doping strategy that effectively leverages limited shifted domain data to enhance segmentation performance, demonstrating significant improvements with only 10-30% applicator data.

Findings

Achieved Dice scores up to 0.94 and IoU scores up to 0.92.

Doping 10-30% of shifted domain data yields comparable results to using only shifted domain data.

Improves robustness and generalizability of segmentation models under covariate shift.

Abstract

Performance degradation due to covariate shift remains a major challenge for deep learning models in medical image segmentation. An open question is whether samples from a shifted distribution can effectively support learning when combined with limited target domain data. We investigate this problem in the context of bladder segmentation in CT guided gynecological brachytherapy, a critical task for accurate dose optimization and organ at risk sparing. While CT scans without brachytherapy applicators (no applicator: NA) are widely available, scans with applicators inserted (with applicator: WA) are scarce and exhibit substantial anatomical deformation and imaging artifacts, making automated segmentation particularly difficult. We propose a dual domain learning strategy that integrates NA and WA CT data to improve robustness and generalizability under covariate shift. Using a curated assorted dataset, we show that NA data alone fail to capture the anatomical and artifact related characteristics of WA images. However, introducing a modest proportion of WA data into a predominantly NA training set leads to significant performance improvements. Through systematic experiments across axial, coronal, and sagittal planes using multiple deep learning architectures, we demonstrate that doping only 10 to 30 percent WA data achieves segmentation performance comparable to models trained exclusively on WA data. The proposed approach attains Dice similarity coefficients of up to 0.94 and Intersection over Union scores of up to 0.92, indicating effective domain adaptation and improved clinical reliability. This study highlights the value of integrating anatomically similar but distribution shifted datasets to overcome data scarcity and enhance deep learning based segmentation for brachytherapy treatment planning.