Contextual Regularization-Based Energy Optimization for Segmenting Breast Tumor in DCE-MRI

• Published in: IEEE access Vol. 13; p. 1
• Main Authors: Babu, Priyadharshini, Asaithambi, Mythili, Suriyakumar, Sudhakar Mogappair
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Adaptation models; Algorithms; Breast; Breast tumor segmentation; Breast tumors; Complexity; Computational modeling; Contextual Regularization-Based Energy Optimization (CRBEO); Cost function; Data models; DCE-MRI; Decision support systems; Delineation; Diagnosis; gradient optimization; Hessian; Huber criteria; Image segmentation; Magnetic resonance imaging; Optimization; Real time; Refining; Regularization; Tumors
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2025.3553035

Accurate breast tumor segmentation is crucial for precise diagnosis, effective treatment planning, and the development of automated decision-support systems in clinical practice. The imprecision of trending segmentation models in differentiating tumors from surrounding tissues, particularly in weighing the boundary pixels across tumor regions, poses a significant challenge in precise tumor delineation. Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) effectively captures tumor vascularity and perfusion dynamics and serves as a reliable modality to extract the region of interest (ROI). However, capturing intricate intensity variations and heterogeneous tumor morphology in DCE-MRI requires a robust segmentation model. Accordingly, this manuscript presents a Contextual Regularization-Based Energy Optimization (CRBEO) model that effectively captures the intensity variations in terms of energy contributed by fidelity and regularization terms. This non-linear energy-based convex optimizer is adaptively tuned by a variational Minimax principle to achieve the desired solution. An iterative gradient descent algorithm is engaged to minimize the energy functionals, ensuring stable convergence towards the optimal solution. The extensive relative analysis of CRBEO on heterogeneous breast DCE-MRI datasets including QIN breast DCE-MRI, TCGA-BRCA, BreastDM, RIDER, and ISPY1 has recorded significant dice improvements of 30.16%, 11.48%, 20.66%, 1.012%, and 28.107%, respectively. The complexity analysis of CRBEO with time and space has justified its extension to real-time clinical diagnosis.