CT-to-Toxicity: A Proof-of-Concept AI Pipeline for Automatic Segmentation, Dose Estimation, and Toxicity Prediction in Breast Cancer Radiotherapy

Read full text Summarise with VIRAT
Authors: Manal Chakour El Mezali, Fatima-Ezzahraa Ben-Bouazza, Idriss Tafala, Ilyass Emssaad, Bassma Jioudi
Cited by: 0
References: 38

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

In breast cancer radiotherapy, clinicians must deliver an adequate tumor dose while protecting surrounding healthy organs. This balance remains difficult: planning is often limited by manual contours, the loss of spatial information, and simplified toxicity indices that do not fully exploit spatial dose information. To address these gaps, we introduce a proof-of-concept AI pipeline that links three tasks into a single workflow: segmentation of organs-at-risk (OARs), voxel-based dose estimation, and toxicity prediction, all derived from planning computed tomography (CT) scans through intermediate dose and dose–volume representations. The first module performs multi-organ segmentation of the heart, lungs, and clinical target volume (CTV) using a Hybrid Residual Transformer Network (HRTNet). The second module employs a lightweight three-dimensional U-Net (3D U-Net) to reconstruct patient-specific dose distributions. The third module uses a Gated Recurrent Unit–Transformer (GRU- Transformer) model to estimate organ-specific toxicity based on dose–volume histograms (DVHs). Experiments conducted on a retrospective cohort of 52 breast cancer cases using patient-wise five-fold cross-validation demonstrate that the proposed pipeline achieves consistent OAR and target segmentation performance, produces dose distributions that are spatially consistent with clinical reference plans, and enables exploratory toxicity prediction under limited and imbalanced data conditions. Explainability techniques, including Grad-CAM and SHapley Additive exPlanations (SHAP), provide qualitative insight into model attention patterns and learned dose–toxicity relationships within the dataset. These components, when combined, illustrate the viability of an end-to-end pipeline capable of supporting more consistent and spatially informed radiotherapy planning workflows, subject to external validation.

Fields of Study & Subjects

Advanced Radiotherapy Techniques Medical Image Segmentation Techniques Artificial Intelligence in Healthcare and Education

Publication details

Journal / source
IEEE Access
Volume
14
Pages
49267–49284
Publication date
1 January 2026
Language
EN