Hybrid Convolutional Neural Network Method for Robust Brain Stroke Diagnosis and Segmentation

Artificial intelligence with deep learning methods have been employed by a majority of researchers in medical image classification and segmentation applications for many years. In this study, hybrid convolutional neural network insert ignore into journalissuearticles values(CNN); model has been proposed for diagnosing of brain stroke from the dataset consisting of the computed tomography insert ignore into journalissuearticles values(CT); brain images. The model inspired from C-Net consists of multiple concatenation layers of the networks, and prevents the concatenation of convolutional feature maps to evince the mapping process. The structures of the convolutional index and residual shortcuts of the INet model are also integrated into the proposed CNN model. In output layer of the model, it is split into two classes as whether there is a stroke or not in a brain image, and then the region of the stroke in the image is segmented. Tremendous analyzes have been conducted in terms of many benchmarks using Python programming. The proposed method shows better performances rather than some other current CNN-based methods by 99.54% accuracy and 99.1% Matthews correlation coefficient insert ignore into journalissuearticles values(MCC); in the diagnosis of brain stroke. The proposed method can alleviate the work of most medical staffs and facilitate the process of the patient’s remedy.