A multi model ensemble based deep convolution neural network structure for detection of COVID19.

The year 2020 will certainly be remembered for the COVID-19 outbreak. First reported in Wuhan city of China back in December 2019, the number of people getting affected by this contagious virus has grown exponentially. Given the population density of India, the implementation of the mantra of the test, track, and isolate is not obtaining satisfactory results. A shortage of testing kits and an increasing number of fresh cases encouraged us to come up with a model that can aid radiologists in detecting COVID19 using chest Xray images. In the proposed framework the low level features from the Chest X-ray images are extracted using an ensemble of four pre-trained Deep Convolutional Neural Network (DCNN) architectures, namely VGGNet, GoogleNet, DenseNet, and NASNet and later on are fed to a fully connected layer for classification. The proposed multi model ensemble architecture is validated on two publicly available datasets and one private dataset. We have shown that our multi model ensemble architecture performs better than single classifier. On the publicly available dataset we have obtained an accuracy of 88.98% for three class classification and for binary class classification we report an accuracy of 98.58%. Validating the performance on private dataset we obtained an accuracy of 93.48%. The source code and the dataset are made available in the github linkhttps://github.com/sagardeepdeb/ensemble-model-for-COVID-detection.

Medical image encryption using fractional discrete cosine transform with chaotic function.

In this advanced era, where we have high-speed connectivity, it is very imperative to insulate medical data from forgery and fraud. With the regular increment in the number of internet users, it is challenging to transmit the beefy medical data. This (medical data) is always reused for different diagnosis purposes, so the information of the medical images need to be protected. This paper introduces a new scheme to ensure the safety of the medical data, which includes the use of a chaotic map on the fractional discrete cosine transform (FrDCT) coefficients of the medical data/images. The imperative FrDCT provides a high degree of freedom for the encryption of the medical images. The algorithm consists of two significant steps, i.e., application of FrDCT on an image and after that chaotic map on FrDCT coefficients. The proposed algorithm discusses the benefits of FrDCT over fractional Fourier transform (FRFT) concerning fractional order α. The key sensitivity and space of the proposed algorithm for different medical images inspire us to make a platform for other researchers to work in this area. Experiments are conducted to study different parameters and challenges. The proposed method has been compared with state-of-the-art techniques. The results suggest that our technique outperforms many other state-of-the-art techniques. Graphical Abstract Overview of the proposed algorithm.