Diabetic retinopathy (DR) is a complication of diabetic Mellitus, developing retinal lesions that impair vision. The DR detection in the early stages avoids permanent vision loss. The treatments provide relief, and the vision loss due to DR is irreversible. The manual grading of DR is time-consuming and prone to human errors. The other real-time problem is exchanging patient fundus image information with hospitals worldwide while upholding the organisations' privacy concerns. When training a deep learning (DL) network, two critical factors to keep in mind are creating a collaborative platform and protecting patient data privacy. Therefore, an automated DR detection technique is required while protecting patient data and privacy. In this work, we propose a novel DR severity grading technique based on Federated Learning (FL), a recent advancement in DL called DRFL. FL is a new research paradigm that allows DL models to be trained collectively without disclosing clinical information. In DRFL, we combined the Federated averaging (FedAvg) technique and the median of the categorical cross-entropy loss. Since in comparison to FedAvg, the median cross-entropy is better suited for either under-fitted or over-fitted clients. Also, we propose a novel central server that extracts multi-scale features from the fundus images to identify small lesions present in the fundus image. In this work, we consider five clients holding different preprocessed fundus images collected from publicly available databases such as MESSIDOR-2, IDRiD, Kaggle, and a local database collected from Silchar Medical College and Hospital. The proposed model obtained an accuracy of 98.6%, specificity of 99.3%, precision of 97.25%, and an F1 score of 97.5%, which are better results than other techniques.

Diabetic retinopathy (DR) is a complication of diabetes caused by blood leakage into the retinal tissues. DR has become one of the primary causes of visual impairment worldwide, and it is the leading risk factor for poor vision in patients aged 25 to 74. Many symptoms cause retinal degener-ation, resulting in vision loss. Early DR detection helps avoid vision loss. Manual DR grading using fundus images is time-consuming and requires expert ophthalmologists. Therefore, we propose Vision Transformer (ViT) based DR severity classifi-cation method. In this work, the fundus images are initially divided into non-overlapping patches to retain location information. Then, the flattened patches are converted into sequences before going through a linear and positional embedding process. The generated sequence is then fed into several multi-head attention layers, which produce the final representation. The first token sequence is fed into a softmax classification layer in the classification stage, which produces the recognition output. The proposed work is tested on Kaggle, IDRiD databases. The results obtained are better than the convolutional neural networks and state-of-the-art.

The proposed work is focused on COVID-19 classification of cough sounds based on machine learning which is used to differentiate COVID-19 coughs from non COVID-19 and healthy coughs. It follows a non-contact based screening test which is very easy to apply being non-invasive and simply carried out within the boundaries of home so that the medical testing centers are not over flooded with patients and there is an overwhelming pressure because of maintenance of those patients with shortage of adequate infrastructure facilities. The dataset used in this study has been derived from the Coswara database which comprises of around 160 infected and 480 healthy individuals. Therefore, Artificial Intelligence based machine learning classifiers were used as an alternative means of diagnosis. Logistic regression (LR), K- Nearest neighbor (KNN), support vector machines (SVM), decision tree algorithms were used as classifiers in the proposed work. The results of this study show that the SVM classifier turned out to be the best in comparing among the COVID-19 and non COVID- 19 coughs with area under receiver operating characteristic curve (ROC) of 0.98. The novelty in the proposed work includes the collection of dry cough samples which would aid in preliminary diagnosis of the infection. This form of classification can also be implemented in a smart phone after performance evaluation from medical authorities.