Deep Learning for Automated Tumor Segmentation of Rectal Cancer on T2-Weighted Magnetic Resonance Images

Clinical Snapshot

Key Findings

• P Value: Correlation with tumor volume: p=0.002 for overlaid rectum model

• Effect Size: DSC 75.52% with overlaid rectum guidance (best performing model)

• Primary Outcome: Dice similarity coefficient for tumor segmentation accuracy

• Nnt Or Sensitivity: DSC 75.52% represents moderate segmentation accuracy; sensitivity and specificity not reported

• Confidence Interval: 74.32-76.62%

Clinical Application

Requires specialized deep learning infrastructure and validation in local populations before clinical implementation Would need validation in Australian populations and integration with existing radiology workflows; potential applications in public hospital systems with high rectal cancer caseloads, but 75% accuracy may be insufficient for clinical decision-making without radiologist oversight Patients with rectal cancer undergoing T2-weighted MR imaging for staging or treatment planning

Abstract

PURPOSE: To develop a deep learning (DL)-based automated segmentation model for rectal cancer on T2-weighted (T2W) magnetic resonance (MR) images. MATERIALS AND METHODS: A total of 458 patients who underwent baseline rectal MR imaging were retrospectively enrolled. An experienced radiologist labeled the tumor on each slice of the selected T2W axial images covering the entire tumor mass, and tumor volume was measured during labeling. Another radiologist labeled the rectum on the same images. Attention U-Net was trained on the T2W images from the training dataset to classify each voxel as tumor or non-tumor. Segmentation with or without rectum guidance was compared using evaluation metrics, including the Dice similarity coefficient (DSC), in the test dataset. RESULTS: The tumor segmentation DSC without rectum guidance was 73.35% (71.97-74.71); that with the predicted rectum was 71.79% (70.53-73.05); and that with the overlaid rectum was 75.52% (74.32-76.62), which was the highest among the three segmentation models. Tumor volume showed a positive correlation with tumor segmentation accuracy with the predicted rectum (r=0.333, p=0.001; overlaid rectum, r=0.319, p=0.002) and without rectum guidance (r=0.219, p=0.036). CONCLUSION: A DL-based automated segmentation model can predict RC with over 70% accuracy, which was further improved with overlaid rectum, and larger tumor volume.

References

1. 1.Seo, M., Lee, Y., & You, M. W. (2026). Deep learning for automated tumor segmentation of rectal cancer on T2-weighted magnetic resonance images. Yonsei Medical Journal. https://doi.org/10.48550/arXiv.1902.09630