Medical Image and Information Processor

Pulse Coupled Neural Networks PCNN have been extended and modified to suit medical image segmentation applications. Previous research demonstrated the ability of a PCNN to ignore noisy variations in intensity and small spatial discontinuities in images that prove beneficial to image segmentation and image smoothing. This final report describes three research and development projects that relate to PCNN segmentation three different digital image processing applications and a CMOS integrated circuit implementation. The software for the diagnosis of Pulmonary Embolism from VQ lung scans uses PCNN in single burst mode for segmenting perfusion and ventilation images. The second project is attempting to detect cardiac infarct and ischemia by comparing 3-D SPECT Single Photon Emission Computed Tomography images of the heart obtained during stress and rest conditions, respectively. The third application is a study of the full body bone scans for the detection of cancer. This paper also describes the hardware implementation of PCNN algorithm as an electro-optical chip.