Back to all papers

Impact of MRI sequence heterogeneity on deep learning-based segmentation of brain metastases.

November 20, 2026pubmed logopapers

Authors

Shin DW,Lee CH,Kim HJ,Sung K,Kim YJ,Kim KG,Yee GT

Affiliations (5)

  • Department of Neurosurgery, Gachon University Gil Medical Center, University of Gachon College of Medicine, Incheon, Republic of Korea.
  • Department of Health Sciences and Technology, Gachon Advanced Institute for Health Sciences and Technology, Gachon University, Incheon, Republic of Korea.
  • Department of Radiation Oncology, Gachon University Gil Medical Center, Incheon, Republic of Korea.
  • Gachon Biomedical & Convergence Institute, Gachon University Gil Medical Center, Incheon, Republic of Korea.
  • Medical Devices R&D Center, Gachon University Gil Medical Center, Incheon, Republic of Korea.

Abstract

Brain metastases (BMs) require accurate delineation for treatment planning, yet magnetic resonance imaging (MRI) acquisition protocols vary substantially in clinical practice. Such protocol-level heterogeneity may affect the generalizability of deep learning-based segmentation models. This study evaluated the impact of heterogeneous T1-weighted MRI protocols on BM segmentation performance using two three-dimensional architectures, 3D Attention U-Net and DUCK-Net 3D. A retrospective dataset of 925 contrast-enhanced T1-weighted MRI studies from 720 patients was analyzed. Models were trained under six sequence configurations, including multi-sequence, Black-Blood (BB), Non-Black-Blood (Non-BB), and three single-sequence cohorts. Independent test datasets consisted of three MRI cohorts: MPR Range, MPR Thick Range, and T1 SPACE 3D. Five-fold cross-validation was performed. Performance was evaluated using the Dice similarity coefficient (DSC), volumetric regression, and false discovery rate-corrected statistical comparisons. DUCK-Net 3D demonstrated more consistent performance across independent MRI cohorts, particularly under cross-sequence conditions. Multi-sequence training achieved the most stable cross-sequence performance, whereas single-sequence models showed greater sensitivity to protocol variability. Segmentation accuracy declined for small lesions (<0.4 mL) across both architectures. These findings suggest that MRI protocol heterogeneity affects segmentation performance and that sequence-diverse training may improve cross-sequence robustness in clinical settings.

Topics

Deep LearningMagnetic Resonance ImagingBrain NeoplasmsJournal Article

Ready to Sharpen Your Edge?

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

We respect your privacy. Unsubscribe at any time.