Automatic Histogram Specification for Glioma Grading Using Multicenter Data

Autor: Wenyi Gao, Qian Zhang, Yaping Wu, Xi Chen, Yusong Lin, Guohua Zhao, Meiyun Wang
Rok vydání: 2019
Předmět:
lcsh:Medical technology
Article Subject
Databases
Factual
Computer science
Biomedical Engineering
Health Informatics
Sample (statistics)
02 engineering and technology
Sensitivity and Specificity
030218 nuclear medicine & medical imaging
03 medical and health sciences
0302 clinical medicine
Histogram
Image Interpretation
Computer-Assisted
0202 electrical engineering
electronic engineering
information engineering
Range (statistics)
Humans
Sensitivity (control systems)
Selection (genetic algorithm)
lcsh:R5-920
Brain Neoplasms
business.industry
Lift (data mining)
Brain
Pattern recognition
Glioma
Magnetic Resonance Imaging
lcsh:R855-855.5
Hyperparameter optimization
020201 artificial intelligence & image processing
Surgery
Artificial intelligence
Neoplasm Grading
lcsh:Medicine (General)
business
Algorithms
Research Article
Biotechnology
Reference frame
Zdroj: Journal of Healthcare Engineering
Journal of Healthcare Engineering, Vol 2019 (2019)
ISSN: 2040-2309
2040-2295
Popis: Multicenter sharing is an effective method to increase the data size for glioma research, but the data inconsistency among different institutions hindered the efficiency. This paper proposes a histogram specification with automatic selection of reference frames for magnetic resonance images to alleviate this problem (HSASR). The selection of reference frames is automatically performed by an optimized grid search strategy with coarse and fine search. The search range is firstly narrowed by coarse search of intraglioma samples, and then the suitable reference frame in histogram is selected by fine search within the sample selected by coarse search. Validation experiments are conducted on two datasets GliomaHPPH2018 and BraTS2017 to perform glioma grading. The results demonstrate the high performance of the proposed method. On the mixed dataset, the average AUC, accuracy, sensitivity, and specificity are 0.9786, 94.13%, 94.64%, and 93.00%, respectively. It is about 15% higher on all indicators compared with those without HSASR and has a slight advantage over the result of a manually selected reference frame by radiologists. Results show that our methods can effectively alleviate multicenter data inconsistencies and lift the performance of the prediction model.
Databáze: OpenAIRE
Externí odkaz: