A Cellular Neural Network methodology for the automated segmentation of multiple sclerosis lesions

• Published in: Journal of neuroscience methods Vol. 203; no. 1; pp. 193 - 199
• Main Authors: Cerasa, Antonio, Bilotta, Eleonora, Augimeri, Antonio, Cherubini, Andrea, Pantano, Pietro, Zito, Giancarlo, Lanza, Pierluigi, Valentino, Paola, Gioia, Maria C., Quattrone, Aldo
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 15.01.2012
• Subjects: Adult; Algorithms; Brain; Brain - pathology; Cellular Neural Network (CNN); Computed tomography; Data processing; Humans; Image Interpretation, Computer-Assisted; Image processing; Learning; Lesion load automated segmentation; Magnetic Resonance Imaging; Magnetic resonance imaging (MRI); Multiple sclerosis; Multiple sclerosis (MS); Multiple Sclerosis, Relapsing-Remitting - pathology; Nervous system; Neural networks; Neural Networks (Computer); Segmentation; Magnetic resonance imaging (MRI); Lesion load automated segmentation; Multiple sclerosis (MS); Cellular Neural Network (CNN)
• ISSN: 0165-0270; 1872-678X
• DOI: 10.1016/j.jneumeth.2011.08.047

► Cellular Neural Networks (CNNs) are computational tools that have found extensive utilization in medical applications. ► CNNs is capable to automatically determine lesion loads in patients with multiple sclerosis. ► CNN-based approach could lead to the development of fully automated brain tissue classification system that can be implemented into imaging systems. We present a new application based on genetic algorithms (GAs) that evolves a Cellular Neural Network (CNN) capable of automatically determining the lesion load in multiple sclerosis (MS) patients from magnetic resonance imaging (MRI). In particular, it seeks to identify brain areas affected by lesions, whose presence is revealed by areas of higher intensity if compared to healthy tissue. The performance of the CNN algorithm has been quantitatively evaluated by comparing the CNN output with the expert's manual delineation of MS lesions. The CNN algorithm was run on a data set of 11 MS patients; for each one a single dataset of MRI images (matrix resolution of 256×256 pixels) was acquired. Our automated approach gives satisfactory results showing that after the learning process the CNN is capable of detecting MS lesions with different shapes and intensities (mean DICE coefficient=0.64). The system could provide a useful support tool for the evaluation of lesions in MS patients, although it needs to be evolved and developed in the future.