文档介绍：Delineation of intracerebral hemorrhage from clinical
non-puted tomography images
Qingmao Hu, Zhijun Chen, Jianhuang Wu, Fucang Jia, Leping Chen
Shenzhen Institute of Advanced Integration Technology Radiology Department
The Chinese University of Hong Kong Shekou People’s Hospital
Shenzhen, China Shenzhen, China
qm.******@siat. lepingc@
Abstract—We delineated intracerebral hemorrhage (ICH) from improve the clinicians’ performance in detecting acute
clinical non-puted tomography (NCT) images intracranial hemorrhage on NCT. At present, the volume and
through large grayscale, large grayscale asymmetry with respect anatomical localization of ICH are approximated manually
to the midsagittal plane (MSP), and large grayscale local from NCT slices. This suffers from being tedious and
contrast. An adaptive approach is proposed to determine laborious, requiring readers of NCT to be an expert in neuro-
thresholds of the 3 features and adjust the window width for data radiology, and inability to control accuracy and to provide
conversion. The substantial grayscale variability of ICH for a accurate 3D shape information of the ICH [7]. It is our
subject is addressed by finding the bright portion followed by objective to devise a robust, fast and validated image analysis
recovering. Those ICH voxels symmetrical to the MSP are system to delineate ICH from c