Back to all papers

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

June 4, 2026pubmed logopapers

Authors

Sujichantararat S,Biswas D,Kazerouni AS,Tsang ED,Sathe A,Hippe DS,Park VY,Chung M,Specht JM,Dintzis SM,Rahbar H,Holmes JH,Huang W,Partridge SC

Affiliations (10)

  • Department of Radiology, University of Washington, Seattle, WA 98195, USA.
  • Department of Bioengineering, University of Washington, Seattle, WA 98195, USA.
  • Clinical Research Division, Fred Hutchinson Cancer Center, Seattle, WA 98109, USA.
  • Department of Radiology and Research Institute of Radiological Science, Yonsei University College of Medicine, Seoul 03722, Republic of Korea.
  • Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA 94143, USA.
  • Division of Hematology and Oncology, University of Washington, Seattle, WA 98195, USA.
  • Department of Laboratory Medicine and Pathology, University of Washington, Seattle, WA 98195, USA.
  • Departments of Radiology, Biomedical Engineering, and Electrical and Computer Engineering, University of Iowa, Iowa City, IA 52242, USA.
  • Department of Radiation Oncology, Research Institute, Corewell Health, Royal Oak, MI 48073, USA.
  • Department of Radiation Oncology, Oakland University William Beaumont School of Medicine, Rochester, MI 48309, USA.

Abstract

<b>Background/Objectives</b>: 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. <b>Methods</b>: 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. <b>Results</b>: 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, <i>p</i> < 0.001) and early treatment (ρ = 0.83, <i>p</i> < 0.001), but lower agreement at mid-treatment (ρ = 0.57, <i>p</i> = 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, <i>p</i> = 0.83) and mid-treatment (AUC = 0.73 vs. 0.75, <i>p</i> = 0.80). <b>Conclusions</b>: 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.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.