Abstract

Medical imaging data is increasing day by day which requires improved applications that perform accurate diagnoses. Secure medical imaging data plays a critical role in current times. Still, today it is a complex task to maintain data privacy, so this study's main objective is to solve this problem. In this research, firstly, secure the medical imaging data using the cryptography Advance Encryption Standard (AES) algorithm. In this process, input images are encrypted and decrypted using public key cryptography and supplied as input to the pre-trained convolutional neural Network such as Alex-net. The model comprises 25 layers such as convolutional, batch-normalization, ReLU and max-pooling, etc. The classification between the tumor and healthy images has been performed using the SoftMax layer. The performance of the proposed model has been tested on the publicly available BRATS-2020 Challenging dataset. The proposed model achieved up to 99.71% accuracy and 97% F1- scores, which are far better as compared to the latest published research work in this domain.
Keywords: Image Classification; Preprocessing; Features extraction; Cryptography; MRI images