A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain

• Published in: IEEE transactions on neural networks 1992-09, Vol.3 (5), p.672-682
• Main Authors: Hall, L.O., Bensaid, A.M., Clarke, L.P., Velthuizen, R.P., Silbiger, M.S., Bezdek, J.C.
• Format: Article
• Language: English
• Subjects: Aerospace Medicine; Applied sciences; Clustering algorithms; Computer networks; Exact sciences and technology; Fuzzy logic; Fuzzy neural networks; Fuzzy sets; Image processing; Image segmentation; Information, signal and communications theory; Intelligent networks; Magnetic resonance; Magnetic resonance imaging; Neural networks; Signal processing; Telecommunications and information theory
• ISSN: 1045-9227; 1941-0093
• DOI: 10.1109/72.159057

Magnetic resonance (MR) brain section images are segmented and then synthetically colored to give visual representations of the original data with three approaches: the literal and approximate fuzzy c-means unsupervised clustering algorithms, and a supervised computational neural network. Initial clinical results are presented on normal volunteers and selected patients with brain tumors surrounded by edema. Supervised and unsupervised segmentation techniques provide broadly similar results. Unsupervised fuzzy algorithms were visually observed to show better segmentation when compared with raw image data for volunteer studies. For a more complex segmentation problem with tumor/edema or cerebrospinal fluid boundary, where the tissues have similar MR relaxation behavior, inconsistency in rating among experts was observed, with fuzz-c-means approaches being slightly preferred over feedforward cascade correlation results. Various facets of both approaches, such as supervised versus unsupervised learning, time complexity, and utility for the diagnostic process, are compared.< >