ABSTRACT
In recent days, many researchers focus on interdisciplinary research work to solve various research problems. One such interdisciplinary research work is the implementation of deep learning (DL) in biomedical engineering and health informatics. It is mandatory to review various research works by various authors, which are implemented using DL in the above fields in order to understand the problem domain, different DL methods/techniques/ theorems for prediction and analysis. The main intention of this chapter is to review a variety of methods and techniques in the healthcare system using DL. Authors have used a number of DL tools such as K-nearest neighbor (KNN) algorithm, AlexNet, VGG-16, GoogLeNet, and vice versa for implementation. It has been noticed that DL architecture has been formulated for 2medical analysis, such as various cancer prediction, in order to predict the accuracy of results. This DL architecture has three basic layers that help to train and test the model, which are the input layer, multiple hidden layers, and the output layer. The output of various medical analyzes depends on the DL architecture that is used along with a number of convolutional hidden layers. In this chapter, breast cancer analysis, lung tumor differentiation, pathology detection, patient-learning using numerous methods such as similarity learning, predictive similarity learning, and adaptive learning using the DL approach has been described.
