Statistical modeling of breast cancer radiomic features and hazard using image registration-aided longitudinal CT data

2026-03-27

AI Summary

This study addresses the challenge of unreliable longitudinal lesion tracking across multiple CT scans in patients with metastatic breast cancer, which has limited the application of radiomics in survival prediction. Leveraging longitudinal chest CT data from the MONALEESA clinical trial, the authors propose the RAMAC algorithm, which integrates image registration with the Hungarian algorithm to enable automatic lesion matching across time points and among multiple annotators. Building upon this, they develop an L1-regularized additive Cox proportional hazards model that incorporates radiomic features extracted at baseline and multiple post-treatment time points, along with demographic variables, for dynamic progression-free survival prediction. The inclusion of longitudinal imaging features significantly improves model performance, increasing the concordance index from 0.58 to 0.64, thereby enhancing both predictive accuracy and interpretability.

Abstract

Patients with metastatic breast cancer (mBC) undergo repeated computed tomography (CT) imaging during treatment to monitor disease progression. Accurate longitudinal tracking of individual lesions across scans from multiple radiologists is essential for reliable radiomic analysis and clinical decision-making. We conducted a retrospective study using serial chest CT scans from the Phase III MONALEESA-3 and MONALEESA-7 trials and developed statistical models for multi-source data integration and survival analysis. First, we introduced a Registration-based Automated Matching and Correspondence (RAMAC) algorithm to establish lesion correspondence across annotations from different radiologists and imaging time points using the Hungarian algorithm. Second, using the RAMAC-processed dataset, we developed interpretable radiomic survival models for progression-free survival prediction by combining baseline radiomic features, post-treatment changes at Weeks 8, 16, and 24, and demographic variables. To address the high dimensionality of longitudinal radiomic data, feature reduction was performed using an L1-penalized additive Cox proportional hazards model and best subset selection followed by Cox modeling. Model performance was evaluated using the concordance index (C-index). Incorporating additional imaging time points improved predictive performance, increasing the mean C-index from 0.58 at baseline to 0.64. Joint modeling further showed significant associations between longitudinal radiomic features and survival outcomes over time.

Problem

• longitudinal radiomic features
• lesion correspondence
• survival prediction
• metastatic breast cancer
• image registration

Innovation

• radiomic longitudinal modeling
• image registration
• lesion correspondence
• survival prediction
• Cox proportional hazards model