Automatic classification of CT images of cerebral hemorrhage in dicom format based on BP neural network. (September 2020)

• Record Type: Journal Article
• Authors: Zhang, Kang; Xu, Shaozhong; Hu, Chenxuan; Zhang, Heling
• Is Part Of: Journal of physics. Volume 1629(2020)
• Publication Date: 2020-09
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1629/1/012009
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: This paper presents a method that can scan all the DICOM format CT images of cerebral hemorrhage in the specified folder and automatically analyze the parameters of the hemorrhage area. The automatic segmentation of cerebral hemorrhage area and brain tissue area is realized by threshold method, and the volume of cerebral hemorrhage area and brain tissue area is calculated according to the layer height and resolution parameters of Dicom format image. The proportion of hemorrhage area to brain tissue is calculated. Then, the position information of hemorrhage area and the percentage of hemorrhage area in brain tissue are used as the input of BP neural network to realize the automatic classification of the severity of cerebral hemorrhage.