Poster Poster Program Diagnostic and Interventional Radiology Physics

Feasibility of Deep Learning–Based Prognostic Risk Prediction In Rectal Cancer Using Histopathology Images after Neoadjuvant Chemoradiotherapy

Abstract
Purpose

Neoadjuvant chemoradiotherapy (nCRT) improves local control in patients with locally advanced rectal cancer (LARC); however, substantial heterogeneity exists in postoperative recurrence risk. This study aimed to evaluate the feasibility of predicting postoperative recurrence risk by integrating deep learning–extracted features from post-nCRT histopathology whole-slide images with disease-free survival.

Methods

A deep learning–based prognostic model was developed using digitized histopathology whole-slide images acquired after nCRT. A total of 534 slides from LARC patients at a single institution were used for model training. Model performance was evaluated in an independent validation cohort of 229 LARC patients from the same institution. Disease-free survival was used as the clinical endpoint. Survival analysis was performed using Kaplan–Meier analysis with the log-rank test. Prognostic performance was quantified using the concordance index (C-index), and hazard ratios with 95% confidence intervals were estimated using Cox proportional hazards regression.

Results

In the validation cohort, the proposed model stratified patients into high- and low-risk groups with a statistically significant difference in disease-free survival (log-rank p=0.001). The model achieved a C-index of 0.68 for recurrence risk prediction. Univariate Cox regression analysis demonstrated a significant association between model-derived risk stratification and clinical outcomes (hazard ratio=2.27, 95% confidence interval: 1.36–3.79, p=0.001).

Conclusion

This study demonstrates the feasibility of using deep learning–extracted features from post-nCRT histopathology images to predict postoperative recurrence risk in patients with locally advanced rectal cancer. The proposed approach may provide complementary prognostic information to support individualized risk stratification following neoadjuvant chemoradiotherapy.

People

Related

Similar sessions

Poster Poster Program
Jul 19 · 07:00
B-Trac – Breast Tissue Rotation and Compression Apparatus for Calibration

Mammography (compressed 2D) and MRI (uncompressed 3D) capture breast tissue under different conditions, complicating tumor localization across modalities. To bridge this gap, we developed a customizable physical platform to simul...

Dayadna Hernandez Perez
Diagnostic and Interventional Radiology Physics 0 people interested
Poster Poster Program
Jul 19 · 07:00
Comprehensive Medical Physics Assessment of Digital Mammography Equipment: A Three-Year Multi-Site Evaluation of Technical Performance and Radiation Safety at 24 Saudi Arabian Healthcare Institutions (2022–2024)

To conduct a comprehensive multi-center audit evaluating the technical performance, image quality, and radiation safety of digital mammography systems across 24 unique healthcare facilities in Saudi Arabia. This study aims to est...

Sami Alshaikh, PhD
Diagnostic and Interventional Radiology Physics 0 people interested
Poster Poster Program
Jul 19 · 07:00
Starting Small: Implementing a CT Protocol Optimization Program

This talk describes our organization’s CT optimization program, and how we implemented it to make efficient use of limited physicist time.

Robert J. Cropp, PhD
Diagnostic and Interventional Radiology Physics 0 people interested