Unsupervised Fuzzy C-Means-Based Approach for Automatic Breast Tumor Segmentation in DCE-MRI

• Published in: Proceedings / IEEE International Symposium on Computer-Based Medical Systems pp. 49 - 52
• Main Authors: Gonzalez, Paula Puerta, Marcos, Pablo Garcia, Arias, Sara Fernandez, Suarez, Rebeca Oliveira, Lorenzo, Guillermo, Gomez, Hector, del Camino, Covadonga, Villar, Jose R., Rio-Alvarez, Angel, Gonzalez, Victor M.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 18.06.2025
• Subjects: Accuracy; Annotations; Breast cancer; Breast tumors; DCE; Fully-automatic segmentation; Fuzzy C-Means; Magnetic resonance imaging; Manuals; MRI; Pipelines; Reliability; Three-dimensional displays; Training; tumor segmentation
• ISSN: 2372-9198
• DOI: 10.1109/CBMS65348.2025.00019

Breast cancer remains one of the most prevalent and life-threatening diseases worldwide, being the most frequently diagnosed cancer among women and the second leading cause of cancer-related mortality. Precise tumor segmentation is essential for breast cancer assessment, as it enables accurate estimation of tumor size, monitoring of disease progression, and evaluation of treatment effectiveness. Despite the importance of this task, the development of reliable automatic methods is hindered by the scarcity of fully annotated datasets, which makes manual labeling both time-consuming and subject to inter-observer variability. In this study, we propose an unsupervised 3D tumor segmentation method based on Fuzzy C-Means (FCM) clustering, specifically designed for volumetric Dynamic Contrast-Enhanced MRI (DCE-MRI) of the breast. Unlike supervised deep learning approaches, our method does not require manual annotations for training, making it especially valuable in scenarios with limited labeled data. The proposed pipeline combines preprocessing, region-of-interest extraction, and FCM-based clustering to generate accurate segmentation masks with minimal human intervention. We evaluated our approach using clinical data from the ACRIN-6698 dataset, comparing the automatic segmentations against expert manual annotations. The method achieved high performance across multiple metrics, including accuracy, precision, recall, specificity, Dice-Sørensen coefficient (DSC), and Jaccard index (IoU). These results demonstrate the feasibility of unsupervised clustering techniques for volumetric breast tumor segmentation, offering a promising alternative to supervised methods in clinical contexts where annotated data is limited.