| Image detection, Image classification, Machine learning, Image pre-processing techniques, Classifiers (SVM, LG, CNN), Python, Modules or Libraries. |
| Machine learning algorithms have the potential to be invested deeply in all fields of medicine, from drug discovery to clinical decision making, significantly altering the way medicine is practiced. In existing work, medical images are an integral part of a patient’s EHR and are currently analyzed by human radiologists, who are limited by speed, fatigue, and experience. Therefore, it is ideal for medical image analysis to be carried out by an automated, accurate and efficient machine learning algorithm. Yet the situation may not be as dire as it seems, as despite the small training datasets, the papers in this review report relatively satisfactory performance in the various tasks. In proposed work, in medical image analysis is an active field of research for machine learning, partly because the data is relatively structured and labelled, and it is likely that this will be the area where patients first interact with functioning, practical artificial intelligence systems. Firstly, in terms of actual patient metrics, medical image analysis is a litmus test as to whether artificial intelligence systems will actually improve patient outcomes and survival. Secondly, it provides a testbed for human-AI interaction, of how receptive patients will be towards health-altering choices being made, or assisted by a nonhuman actor. In medical image analysis, the lack of data is two-fold and more acute. Most of the datasets presented in this review involve fewer than 100 patients. The question of how many images is necessary for training in medical image analysis was partially answered by ascertained the accuracy of a CNN with GoogleNet architecture in classifying individual axial CT images into one of 6 body regions: brain, neck, shoulder, chest, abdomen, pelvis. With 200 training images, accuracies of test were achieved on a test set of 6000 images. An important, non-technical challenge is the public reception towards their health results being studied by a nonhuman actor. |
