Blockchain-Federated-Learning and Deep Learning Models for COVID-19 detection using CT Imaging
share
With the increase of COVID-19 cases worldwide, an effective way is required to diagnose COVID-19 patients. The primary problem in diagnosing COVID-19 patients is the shortage of testing kits, due to the quick spread of the virus, medical practitioners are facing difficulty identifying the positive cases. The second real-world problem is to share the data among the hospitals globally while keeping in view the privacy concern of the organizations. To address the problem of building a collaborative network model without leakage privacy of data are major concerns for training the deep learning model, this paper proposes a framework that collects a huge amount of data from different sources (various hospitals) and to train the deep learning model over a decentralized network for the newest information about COVID-19 patients. The main goal of this paper is to improve the recognition of a global deep learning model using, novel and up-to-date data, and learn itself from such data to improve recognition of COVID-19 patients based on computed tomography (CT) slices. Moreover, the integration of blockchain and federated-learning technology collects the data from different hospitals without leakage the privacy of the data. Firstly, we collect real-life COVID-19 patients data open to the research community. Secondly, we use various deep learning models (VGG, DenseNet, AlexNet, MobileNet, ResNet, and Capsule Network) to recognize the patterns via COVID-19 patients' lung screening. Thirdly, securely share the data among various hospitals with the integration of federated learning and blockchain. Finally, our results demonstrate a better performance to detect COVID-19 patients.
READ FULL TEXT
