Computational Methods in Breast Cancer Diagnostics and Surgery Planning: A Review

Abstract

Breast cancer remains a significant health concern, necessitating advancements in early detection and effective surgical planning. The review explores the integration of computational methods into breast cancer diagnostics and breast-conserving surgery (BCS). Imaging modalities such as mammography (MMG), ultrasound (USG), and magnetic resonance imaging (MRI) form the cornerstone of diagnosis, yet face limitations in sensitivity, specificity, and localization accuracy due to tissue deformation and variable imaging positions. Computational approaches, including finite element analysis (FEA), machine learning (ML), and computer-aided design (CAD), offer promising solutions for overcoming these challenges. By modeling tissue deformation, optimizing tumor localization, and predicting post-surgical outcomes, these methods enhance precision and patient satisfaction in BCS. Emerging techniques in this area, such as 3D scanning, digital image correlation (DIC), and thermal imaging, complement traditional modalities, while innovations in histopathological imaging leverage artificial intelligence for improved diagnostic accuracy. Despite advancements, significant gaps remain in standardizing these tools for clinical application. This review highlights the potential of computational methods to transform breast cancer care through improved diagnostics, surgical planning, and outcome prediction.