Magnetic Resonance Image segmentation using Pulse Coupled Neural Networks

Swathanthira Kumar, Murali Murugavel M

Etd

Magnetic Resonance Image segmentation using Pulse Coupled Neural Networks

Public

The Pulse Couple Neural Network (PCNN) was developed by Eckhorn to model the observed synchronization of neural assemblies in the visual cortex of small mammals such as a cat. In this dissertation, three novel PCNN based automatic segmentation algorithms were developed to segment Magnetic Resonance Imaging (MRI) data: (a) PCNN image â€˜signatureâ€™ based single region cropping; (b) PCNN â€“ Kittler Illingworth minimum error thresholding and (c) PCNN â€“Gaussian Mixture Model â€“ Expectation Maximization (GMM-EM) based multiple material segmentation. Among other control tests, the proposed algorithms were tested on three T2 weighted acquisition configurations comprising a total of 42 rat brain volumes, 20 T1 weighted MR human brain volumes from Harvardâ€™s Internet Brain Segmentation Repository and 5 human MR breast volumes. The results were compared against manually segmented gold standards, Brain Extraction Tool (BET) V2.1 results, published results and single threshold methods. The Jaccard similarity index was used for numerical evaluation of the proposed algorithms. Our quantitative results demonstrate conclusively that PCNN based multiple material segmentation strategies can approach a human eyeâ€™s intensity delineation capability in grayscale image segmentation tasks.

Creator