Deep Learning Approaches in Histopathology

Abstract

The revolution of artificial intelligence and its impacts on our daily life has led to tremendous interest in the field and its related subtypes: machine learning and deep learning. Scientists and developers have designed machine learning- and deep learning-based algorithms to perform various tasks related to tumor pathologies, such as tumor detection, classification, grading with variant stages, diagnostic forecasting, recognition of pathological attributes, pathogenesis, and genomic mutations. Pathologists are interested in artificial intelligence to improve the diagnosis precision impartiality and to minimize the workload combined with the time consumed, which affects the accuracy of the decision taken. Regrettably, there are already certain obstacles to overcome connected to artificial intelligence deployments, such as the applicability and validation of algorithms and computational technologies, in addition to the ability to train pathologists and doctors to use these machines and their willingness to accept the results. This review paper provides a survey of how machine learning and deep learning methods could be implemented into health care providers' routine tasks and the obstacles and opportunities for artificial intelligence application in tumor morphology.

Keywords: artificial intelligence; deep learning; image analysis; machine learning; pathology; tumor morphology.

Figure 1

An overview of the deep learning process in pathology. Firstly, the whole-slide images (WSIs) were obtained from the original specimen slides. Then, the ongoing Artificial Neural Network (ANN) analysis process. Finally, the output of diagnosis or prognosis was based on the classification and selected features.

Figure 2

Different types of Neural Networks Architecture [65]: (a) Fully-Connected Neural Network (FCNN); (b) AlexNet is a Deep Neural Network [66]; and (c) LeNet refers to LeNet-5 and it is a simple CNN [67].