Deep learning for heterogeneous medical data analysis
- PDF / 602,215 Bytes
- 23 Pages / 439.37 x 666.142 pts Page_size
- 110 Downloads / 340 Views
Deep learning for heterogeneous medical data analysis Lin Yue 1,2,3 & Dongyuan Tian 1 & Weitong Chen 2 & Xuming Han 4 & Minghao Yin 1 Received: 20 February 2019 / Revised: 24 July 2019 / Accepted: 14 November 2019 # Springer Science+Business Media, LLC, part of Springer Nature 2019
Abstract
At present, how to make use of massive medical information resources to provide scientific decision-making for the diagnosis and treatment of diseases, summarize the curative effect of various treatment schemes, and better serve the decision-making management, medical treatment, and scientific research, has drawn more and more attention of researchers. Deep learning, as the focus of most concern by both academia and industry, has been effectively applied in many fields and has outperformed most of the machine learning methods. Under this background, deep learning based medical data analysis emerged. In this survey, we focus on reviewing and then categorizing the current development. Firstly, we fully discuss the scope, characteristic and structure of the heterogeneous medical data. Afterward and primarily, the main deep learning models involved in medical data analysis, including their variants and various hybrid models, as well as main tasks in medical data analysis are all analyzed and reviewed in a series of typical cases respectively. Finally, we provide a brief introduction to certain useful online resources of deep learning development tools. Keywords Medical data analysis . Deep learning . Survey
1 Introduction Big data based information mining has triggered great changes in the medical field. “Big” is not only reflected in scale, but also in storage, processing, analysis of the data. Medical data
* Weitong Chen [email protected]
1
School of Information Science and Technology, Northeast Normal University, Changchun, China
2
School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, Australia
3
Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China
4
School of Computer Science and Engineering, Changchun University of Technology, Changchun, China
World Wide Web
Figure 1 Deaths related to disease, illness and other health factors worldwide in 2016. Non-communicable diseases (NCDs) are as follows: “Dementia” refers to the number of deaths attributed to Alzheimer’s and other forms of dementia. “Cardiovascular disease” refers to rheumatic and ischemic heart diseases. “Respiratory diseases” include deaths from chronic obstructive pulmonary disease (COPD), and pneumoconiosis diseases. “Cancers” include all forms of cancer, also referred to in the GBD database as “neoplasms”. “Digestive diseases” refer to all deaths resultant from ulcer diseases, pancreatitis, gallbladder, bowel disease, gastritis, and intestinal diseases
has also been expanded to more generalized text, images, sound, HTTP text, and sensor information, etc. Medical data mining generally refers to the process of recognizing new patterns o
Data Loading...