An Automated Radiomics Framework for Postoperative Survival Prediction in Colorectal Liver Metastases using Preoperative MRI

2026-03-10

AI Summary

This study addresses the high heterogeneity in postoperative survival among patients with colorectal cancer liver metastases by proposing a fully automated, preoperative MRI–based AI framework to avoid futile surgery and support personalized treatment. Methodologically, it introduces the novel SAMONAI algorithm for 3D point-prompt–driven, anatomy-aware segmentation and develops the SurvAMINN network to jointly learn radiomic feature dimensionality reduction and high-risk metastasis–oriented survival prediction. Experimental results demonstrate strong performance, with Dice coefficients of 0.96 and 0.93 for liver and spleen segmentation, respectively, 0.78 for liver metastasis segmentation, an F1 score of 0.79 for lesion detection, and a C-index of 0.69 for survival prediction, collectively validating the model’s efficacy and clinical potential.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Segmentation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Security and privacy of machine learning and AI applications
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

While colorectal liver metastasis (CRLM) is potentially curable via hepatectomy, patient outcomes remain highly heterogeneous. Postoperative survival prediction is necessary to avoid non-beneficial surgeries and guide personalized therapy. In this study, we present an automated AI-based framework for postoperative CRLM survival prediction using pre- and post-contrast MRI. We performed a retrospective study of 227 CRLM patients who had gadoxetate-enhanced MRI prior to curative-intent hepatectomy between 2013 and 2020. We developed a survival prediction framework comprising an anatomy-aware segmentation pipeline followed by a radiomics pipeline. The segmentation pipeline learns liver, CRLMs, and spleen segmentation from partially-annotated data, leveraging promptable foundation models to generate pseudo-labels. To support this pipeline, we propose SAMONAI, a prompt propagation algorithm that extends Segment Anything Model to 3D point-based segmentation. Predicted pre- and post-contrast segmentations are then fed into our radiomics pipeline, which extracts per-tumor features and predicts survival using SurvAMINN, an autoencoder-based multiple instance neural network for time-to-event survival prediction. SurvAMINN jointly learns dimensionality reduction and survival prediction from right-censored data, emphasizing high-risk metastases. We compared our framework against established methods and biomarkers using univariate and multivariate Cox regression. Our segmentation pipeline achieves median Dice scores of 0.96 (liver) and 0.93 (spleen), driving a CRLM segmentation Dice score of 0.78 and a detection F1-score of 0.79. Accurate segmentation enables our radiomics pipeline to achieve a survival prediction C-index of 0.69. Our results show the potential of integrating segmentation algorithms with radiomics-based survival analysis to deliver accurate and automated CRLM outcome prediction.

Problem

• colorectal liver metastases
• postoperative survival prediction
• preoperative MRI
• radiomics
• hepatectomy

Innovation

• automated radiomics
• SAMONAI
• SurvAMINN
• 3D promptable segmentation
• survival prediction