1. Application of Radiomics in Central Nervous System Diseases: a Systematic literature review
- Author
-
Yanghua Fan, Renzhi Wang, and Ming Feng
- Subjects
Feature extraction ,Clinical Decision-Making ,Machine learning ,computer.software_genre ,Multimodal Imaging ,03 medical and health sciences ,0302 clinical medicine ,Radiomics ,Region of interest ,Central Nervous System Diseases ,Predictive Value of Tests ,Medicine ,Humans ,Segmentation ,Grading (tumors) ,Prognostic models ,business.industry ,General Medicine ,Prognosis ,Systematic review ,030220 oncology & carcinogenesis ,Surgery ,Neurology (clinical) ,Artificial intelligence ,business ,computer ,030217 neurology & neurosurgery - Abstract
Central nervous system (CNS) diseases are associated with complexity and diversity; as a result, it is urgent to search for a simple approach for effectively improving the clinical decision-making ability and precise treatment currently. Radiomics can collect plenty of quantitative features based on the massive medical image data; meanwhile, related diagnosis and prediction can be performed through quantitative analysis. The main steps of radiomics analysis include image collection as well as reconstruction, segmentation of the region of interest (ROI), feature extraction as well as quantification, and establishment of the predictive as well as prognostic models. Compared with traditional imaging features, radiomics allows to transform the visual image data to the in-depth features, so as to carry out quantitative research. Our findings suggest that radiomics has broad application prospects in the early screening, accurate diagnosis, grading and staging, treatment and prognosis, and molecular characteristics of CNS diseases, which can improve the capacities to diagnose and predict CNS diseases prognosis through complementing and combining with traditional imaging.
- Published
- 2019