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

TL;DR

This study develops statistical models for longitudinal radiomic analysis of metastatic breast cancer using CT scans, incorporating lesion matching and survival prediction, with improved accuracy over time.

Contribution

Introduced the RAMAC algorithm for lesion correspondence and developed interpretable survival models integrating multi-timepoint radiomic features.

Findings

Increased C-index from 0.58 to 0.64 by adding imaging time points

RAMAC algorithm effectively matches lesions across radiologists and time points

Longitudinal radiomic features are significantly associated with survival outcomes

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.