Virtual Biomarkers and Simplified Metrics in the Modeling of Breast Cancer Neoadjuvant Therapy: A Proof-of-Concept Case Study Based on Diagnostic Imaging

Abstract

Background: Neoadjuvant chemotherapy (NAC) is a standard preoperative intervention for early-stage breast cancer (BC). Dynamic contrast-enhanced magnetic resonance imaging (CE-MRI) has emerged as a critical tool for evaluating treatment response and pathological complete response (pCR) following NAC. Computational modeling offers a robust framework to simulate tumor growth dynamics and therapy response, leveraging patient-specific data to enhance predictive accuracy. Despite this potential, integrating imaging data with computational models for personalized treatment prediction remains underexplored. This case study presents a proof-of-concept prognostic tool that bridges oncology, radiology, and computational modeling by simulating BC behavior and predicting individualized NAC outcomes.

Methods: CE-MRI scans, clinical assessments, and blood samples from three retrospective NAC patients were analyzed. Tumor growth was modeled using a system of partial differential equations (PDEs) within a reaction-diffusion mass transfer framework, incorporating patient-specific CE-MRI data. Tumor volumes measured pre- and post-treatment were compared with model predictions. A 20% error margin was applied to assess computational accuracy.

Results: All cases were classified as true positive (TP), demonstrating the model's capacity to predict tumor volume changes within the defined threshold, achieving 100% precision and sensitivity. Absolute differences between predicted and observed tumor volumes ranged from 0.07 to 0.33 cm³. Virtual biomarkers were employed to quantify novel metrics: the biological conversion coefficient ranged from 4 × 10^-7 to 6 × 10^-6 s^-1, while the pharmacodynamic efficiency coefficient ranged from 1 × 10^-7 to 4 × 10^-4 s^-1, reflecting intrinsic tumor biology and treatment effects, respectively.

Conclusions: This approach demonstrates the feasibility of integrating CE-MRI and computational modeling to generate patient-specific treatment predictions. Preliminary model training on retrospective cohorts with matched BC subtypes and therapy regimens enabled accurate prediction of NAC outcomes. Future work will focus on model refinement, cohort expansion, and enhanced statistical validation to support broader clinical translation.

Keywords: biomarker; breast cancer; computational prognosis; diagnostic imaging; multidimensional modeling; neoadjuvant therapy; reactive–diffusive modeling.

Figure 1

Tumor volume of a generic patient undergoing BC relapses after the end of therapy. The dynamic evolution of lesion volume V* is generally subdivided in Phases I to III, denoted by dashed lines. The starting time of the basal lesion t_i, the duration of Phase II ∆t_s and the residual tumor volume after NAC ∆$V_s^{*}$, to be removed by surgery, are also indicated.

Figure 2

Baseline CE-MRI of Patient 1: (a) sample axial projection; (b) sample sagittal projection. The lighter areas, on the gray/black background, depict the tumoral ROIs.

Figure 3

Post-NAC CE-MRI of Patient 1: (a) sample axial projection; (b) sample sagittal projection. The lighter areas, on the gray/black background, depict the tumoral ROIs.

Figure 4

Baseline computational volumes of Patient 1’s breast, as reconstructed from the corresponding DICOM stack: (a) axial view; (b) sagittal view. The violet volumes on the pink background represent the tumoral ROIs identified in Figure 2.

Figure 5

Post-NAC computational volumes of Patient 1’s breast, as reconstructed from the corresponding DICOM stack: (a) axial view; (b) sagittal view. The violet volumes on the pink background represent the tumoral ROIs identified in Figure 3.

Figure 6

(a) finite element rendering of Figure 4b; (b) color rendering, reporting a slight rotation about the z-axis, where a filter is applied to computational finite elements to show the inner consistence of the grid. The baseline tumoral ROI is evidenced in color red.

Figure 7

Simulation of Patient 1. (a) therapy modulation function f_j (t), for each j-th drug; (b) progress of computed lesion volume V* and comparison with the associated clinical measurement V, using the metrics reported in Table 1.

Figure 8

Progress of computed lesion volume V* and comparison with the associated clinical measurement V, using the metrics reported in Table 1. (a) Patient 2; (b) Patient 3.