Developing Predictive and Robust Radiomics Models for Chemotherapy Response in High-Grade Serous Ovarian Carcinoma

2026-01-13

AI Summary

Approximately 40% of patients with high-grade serous ovarian carcinoma (HGSOC) exhibit poor response to neoadjuvant chemotherapy (NACT), underscoring the urgent need for non-invasive predictive tools. This study proposes a novel approach integrating radiomics and machine learning, leveraging pre- and post-NACT CT imaging to predict treatment response across multiple metrics—comprehensive response score (CRS), RECIST, volume reduction (VolR), and diameter reduction (DiaR)—with models tailored to lesion anatomical locations. A key innovation is the systematic incorporation of an automated randomization algorithm during feature selection to simulate inter-observer variability, thereby enhancing model robustness without compromising predictive performance. In independent external validation, the combined whole-lesion model achieved an AUC of 0.83 for VolR prediction, while omental and pelvic lesions yielded AUCs of 0.77 and 0.76 for CRS and DiaR, respectively, significantly improving clinical generalizability.

Technology Category

• Machine Learning: Other Foundations of Machine Learning
• Computer Vision: Other Foundations of Computer Vision
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Objectives: High-grade serous ovarian carcinoma (HGSOC) is typically diagnosed at an advanced stage with extensive peritoneal metastases, making treatment challenging. Neoadjuvant chemotherapy (NACT) is often used to reduce tumor burden before surgery, but about 40% of patients show limited response. Radiomics, combined with machine learning (ML), offers a promising non-invasive method for predicting NACT response by analyzing computed tomography (CT) imaging data. This study aimed to improve response prediction in HGSOC patients undergoing NACT by integration different feature selection methods. Materials and methods: A framework for selecting robust radiomics features was introduced by employing an automated randomisation algorithm to mimic inter-observer variability, ensuring a balance between feature robustness and prediction accuracy. Four response metrics were used: chemotherapy response score (CRS), RECIST, volume reduction (VolR), and diameter reduction (DiaR). Lesions in different anatomical sites were studied. Pre- and post-NACT CT scans were used for feature extraction and model training on one cohort, and an independent cohort was used for external testing. Results: The best prediction performance was achieved using all lesions combined for VolR prediction, with an AUC of 0.83. Omental lesions provided the best results for CRS prediction (AUC 0.77), while pelvic lesions performed best for DiaR (AUC 0.76). Conclusion: The integration of robustness into the feature selection processes ensures the development of reliable models and thus facilitates the implementation of the radiomics models in clinical applications for HGSOC patients. Future work should explore further applications of radiomics in ovarian cancer, particularly in real-time clinical settings.

Problem

• High-grade serous ovarian carcinoma
• Neoadjuvant chemotherapy
• Radiomics
• Treatment response prediction
• CT imaging

Innovation

• radiomics
• feature selection
• robustness
• neoadjuvant chemotherapy
• ovarian cancer