BAT-RM: A Boundary-Aware Transformer with Region-Aware Multi-Directional Mamba for Clinically Deployed Cervical Cancer Radiotherapy Auto-Contouring

2026-07-11

AI Summary

This study addresses the challenges in cervical cancer radiotherapy planning—namely, the time-consuming manual contouring of target volumes and organs-at-risk, poor inter-observer consistency, and limited expert availability—by proposing an end-to-end automatic segmentation system. The system integrates a boundary-aware Transformer with a linear-complexity, multi-directional Mamba module for efficient long-range modeling, enhanced by Sobel-gated boundary attention and a boundary-skeleton guided fusion gate to balance accuracy and computational efficiency. Trained and validated on high-quality multicenter data under standardized quality control protocols, the method significantly outperforms existing approaches across seven anatomical structures, achieving IoU scores of up to 0.965 for GTV/CTV and critical organs such as the rectum and bladder, while reducing contouring time by over 80%. The system has been clinically deployed on Varian, RayStation, and Monaco platforms, shortening patient wait times from days to hours.

Abstract

We present a clinically deployed end-to-end auto-contouring system for cervical cancer radiotherapy planning, anchored by the Boundary-Aware Transformer with Region-Aware Mamba (BAT-RM), a hybrid architecture that integrates Sobel-gated boundary attention, a linear-time, multi-directional Mamba module for long-range context, and a boundary-skeleton-guided fusion gate. This design achieves linear-time complexity for long-range context modeling, avoiding the quadratic cost of full spatial self-attention. The full pipeline spans multi-institutional data collection, rigorous inter-rater quality assurance, external validation in an independent cohort, and a web-based clinical interface natively compatible with Varian, RayStation, and Monaco. Against four baselines, BAT-RM achieves superior performance across seven anatomical classes, with statistically significant improvements in target volumes, including GTV and CTV, and in organs at risk such as the rectum and bladder. A prospective multi-center reader study involving 13 radiation oncologists demonstrated that AI assistance elevates junior oncologists' IoU from 0.899 to 0.965, approaching senior-level accuracy, while reducing contouring time by more than 80%. The system also reduced expert consultation rates and improved inter-reader consistency, reflecting gains in both efficiency and quality assurance. Following clinical deployment at a partner hospital, the system reduced patient wait times from days to hours without additional staffing, enabling same-day or next-day initiation of treatment for routine cases. BAT-RM demonstrates that a rigorous research pipeline, from data curation to clinical deployment, can translate directly into measurable patient benefit in resource-constrained settings where the demand for radiotherapy far exceeds specialist capacity.

Problem

• auto-contouring
• cervical cancer
• radiotherapy
• clinical deployment
• organ-at-risk

Innovation

• Boundary-Aware Transformer
• Multi-Directional Mamba
• Linear-Time Long-Range Modeling
• Auto-Contouring
• Clinical Deployment