A novel method for detection and classification of multiple disesases using trasfer learning based deep learning techniques with improved performance

Abstract A disease is a distinct abnormal state that significantly affects the functioning of all or part of an individual and is not caused by external harm. Diseases are frequently understood to be medical conditions that are connected with distinct indications and symptoms. According to a fairly wide categorization, diseases can also be categorised as follows –mental disorders, deficient diseases, genetic diseases, degenerative diseases, self-inflicted diseases, infectious diseases, non- infectious diseases, social diseases, physical diseases. Prevention of the diseases are of multiple instances. Primary prevention seeks to prevent illness or harm before it ever happens. Secondary prevention tries to lessen the effect of an illness or damage that has already happened. This is done through diagnosing and treating illness or injury as soon as feasible to stop or delay its course, supporting personal ways to avoid recurrence or reinjury, and implementing programmes to restore individuals to their previous health and function to prevent long-term difficulties. Tertiary prevention tries to lessen the impact of a continuing sickness or injury that has enduring repercussions. Diagnosis of the disease at the earlier stage is important for the treatment of the disease. Hence here in this study deep learnming algorithms such as VGG16, EfficientNetB4, ResNet, etc.., are utilized to diagnose various diseases such as Alzheimer, Brain tumors, Skin diseases, lung diseases, etc..,.Chest X-Rays, MRI scans, CT scans, skin lesions are used for the diagnosis of the mentioned diseases. Transfer learning algorithms VGG16, VGG19, ResNet, InceptionV3 and EfficientNetB4 are utilised to categorise various diseases. EfficientNetB4 with the learning rate annealing having obtained an accuracy of 94.04% on the test dataset. As a consequence, we observed that every network has unique particular skills on the Multi Disease dataset which includes the chest x-rays, MRI scans, etc.