A Multidimensional Particle Swarm Optimization-Based Algorithm for Brain MRI Tumor Segmentation

• Published in: Sensors (Basel, Switzerland) Vol. 25; no. 9; p. 2800
• Main Authors: Boga, Zsombor, Sándor, Csanád, Kovács, Péter
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 29.04.2025; MDPI
• Subjects: Accuracy; adaptive number of segments; Algorithms; Automation; Brain - diagnostic imaging; Brain cancer; Brain Neoplasms - diagnostic imaging; brain tumor segmentation; Brain tumors; Clustering; Datasets; Diagnosis; Fractals; Glioma; Humans; Image processing; Image Processing, Computer-Assisted - methods; image segmentation; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Mathematical optimization; Methods; multidimensional particle swarm optimization; Optimization; Particle Swarm Optimization; Radiation therapy; Tumors; Romania; magnetic resonance imaging; random forest classifier; multidimensional particle swarm optimization; brain tumor segmentation; image segmentation; adaptive number of segments; clustering
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s25092800

Particle Swarm Optimization (PSO) has been extensively applied to optimization tasks in various domains, including image segmentation. In this work, we present a clustering-based segmentation algorithm that employs a multidimensional variant of PSO. Unlike conventional methods that require a predefined number of segments, our approach automatically selects an optimal segmentation granularity based on specified similarity criteria. This strategy effectively isolates brain tumors by incorporating both grayscale intensity and spatial information across multiple MRI modalities, allowing the method to be reliably tuned using a limited amount of training data. We further demonstrate how integrating these initial segmentations with a random forest classifier (RFC) enhances segmentation precision. Using MRI data from the RSNA-ASNR-MICCAI brain tumor segmentation (BraTS) challenge, our method achieves robust results with reduced reliance on extensive labeled datasets, offering a more efficient path toward accurate, clinically relevant tumor segmentation.