Logo image
Back
Deep Learning-Based Synthetic Contrast-Enhanced Breast MRI for Monitoring Response to Neoadjuvant Therapy
Journal article   Open access   Peer reviewed

Deep Learning-Based Synthetic Contrast-Enhanced Breast MRI for Monitoring Response to Neoadjuvant Therapy

Suleeporn Sujichantararat, Debosmita Biswas, Anum S. Kazerouni, Edric D. Tsang, Aditi Sathe, Daniel S. Hippe, Vivian Y. Park, Maggie Chung, Jennifer M. Specht, Suzanne M. Dintzis, …
Cancers, Vol.18(11), 1835
06/04/2026
DOI: 10.3390/cancers18111835
PMCID: PMC13256508
PMID: 42279418
url
https://doi.org/10.3390/cancers18111835View
Published (Version of record) Open Access

Abstract

Contrast-enhanced (CE) breast MRI is a highly sensitive technique commonly used to monitor breast cancer treatment response. CE-MRI requires intravenous administration of gadolinium-based contrast agents (GBCA) by trained medical professionals, which is costly, time-consuming, and adds to patient discomfort and health concerns. Emerging artificial intelligence models hold potential to reduce GBCA use by synthesizing CE-MRI from non-contrast MR images. This proof-of-concept pilot study aimed to evaluate the effectiveness of synthesized CE-MRI in measuring tumor volumes and monitoring response to neoadjuvant therapy (NAT). Changes in tumor volume calculated at early treatment (post-1-cycle NAT) and mid-treatment were used to predict final pathological response outcomes. Results showed that synthetic CE-MRI provided numerically similar predictive value to acquired CE-MRI, demonstrating its preliminary feasibility as an early marker of response, while also suggesting the need for further refinement of the model to accurately capture residual tumor volumes and validation in larger and more heterogeneous cohorts. Background/Objectives: Contrast-enhanced (CE) breast MRI is highly sensitive for evaluating breast cancer extent and response to neoadjuvant therapy (NAT) but requires intravenous administration of gadolinium-based contrast agents (GBCA), increasing cost, time, patient discomfort, and health concerns. This study explored the feasibility of reducing GBCA use in treatment monitoring using a deep learning (DL) model to synthesize CE-MRI from non-contrast MRI. Methods: This IRB-approved retrospective pilot study evaluated women with breast cancer enrolled in an ongoing trial using serial MRI to monitor NAT prior to surgery. A pre-trained DL model was used to synthesize CE-MRI from T1-, T2-, and diffusion-weighted MRI. Changes in tumor volume at early (post-1-cycle NAT) and mid-treatment were measured on synthetic and acquired CE-MRI. Performance for predicting residual cancer burden (RCB) class 0/1 was evaluated using AUC and compared with DeLong’s test. Results: 27 women were included in the study (median age, 47 years [range = 28–75]); 14 (52%) achieved RCB class 0 and six (22%) achieved class 1. Synthetic CE-MRI-derived tumor volumes showed strong correlation with those from acquired CE-MRI at pre-treatment (ρ = 0.92, p < 0.001) and early treatment (ρ = 0.83, p < 0.001), but lower agreement at mid-treatment (ρ = 0.57, p = 0.002). Change in tumor volume on synthetic CE-MRI was numerically similar to acquired CE-MRI for predicting RCB class 0/1 vs. 2/3 at both early (AUC = 0.84 vs. 0.86, p = 0.83) and mid-treatment (AUC = 0.73 vs. 0.75, p = 0.80). Conclusions: Synthetic CE-MRI demonstrates preliminary feasibility as a non-contrast surrogate for predicting favorable outcomes (RCB class 0/1) in this pilot study, but inconsistencies in tumor volume measurement vs. acquired CE-MRI warrant further model refinement and validation.
 breast cancer gadolinium treatment response MRI neoadjuvant therapy (NAT) residual cancer burden (RCB) pathologic complete response (pCR) synthetic contrast-enhanced MRI modeling

Details

Metrics

1 Record Views
Logo image