24 September 2019
learning (artificial intelligence), pattern classification, unsupervised learning, image classification, Boltzmann machines, feature extraction, medical image processing, cancer, convolutional neural nets, deep Boltzmann machine algorithm, accurate medical image analysis, deep learning algorithm, medical domain, healthcare system, deep learning framework, interest pattern, complex hyperspectral medical images, computer-aided diagnosis, hyperspectral image, post-cancerous region classification, deep Boltzmann machine architecture, bipartite structure, unsupervised generative model, deep convolutional neural network architecture, three-layer unsupervised network, backpropagation structure, image patches, discriminative classes, labelled classes, spatial information, spectral-spatial representation, cognitive computation technique, success rate DBM, complex images, traditional convolution network
In this research work, a deep learning algorithm is applied to the medical domain to deliver a better healthcare system. For this, a deep learning framework for classification the region of interest pattern of complex hyperspectral medical images is proposed. The performance of computer-aided diagnosis by verifying the region in hyperspectral image by pre and post-cancerous region classification is enhanced. For this a deep Boltzmann machine (DBM) architecture of the bipartite structure as an unsupervised generative model was developed. The performance of DBM is compared with deep convolutional neural network architecture. For implementation, a three-layer unsupervised network with a backpropagation structure is used. From the presented dataset, image patches are collected and classified into two classes, namely non-informative and discriminative classes as labelled classes. The spatial information is used for classification and spectral-spatial representation of class labels is formed. In the labelled classes, the accuracy, false-positive predictions, sensitivity are obtained for the proposed fully-connected network. By the proposed cognitive computation technique an accuracy of 95.5% with 93.5% sensitivity was obtained. From the obtained classification, accuracy and success rate DBM provide a better classification of complex images compared to traditional convolution network.