Delineation of intracerebral hemorrhage from clinical non-enhanced computed tomography images
We delineated intracerebral hemorrhage (ICH) fromclinical non-enhanced computed tomography (NCT) imagesthrough large grayscale, large grayscale asymmetry with respectto the midsagittal plane (MSP), and large grayscale localcontrast. An adaptive approach is proposed to determinethresholds of the 3 features and adjust the window width for dataconversion. The substantial grayscale variability of ICH for asubject is addressed by finding the bright portion followed byrecovering. Those ICH voxels symmetrical to the MSP arerecovered, partial volume effects are compensated and the non-ICHhigh grayscale regions are excluded. The algorithm is fast,and has been validated (37 cases) to yield a delineation accuracyof 0.915 and qualitatively (altogether 161 cases) with good results.The developed system could be a useful tool to aid quantifyingICH and enhancing stroke therapy.
Qingmao Hu Zhijun Chen Jianhuang Wu Fucang Jia Leping Chen
Shenzhen Institute of Advanced Integration Technology The Chinese University of Hong Kong Shenzhen, Radiology Department Shekou Peoples Hospital Shenzhen, China
国际会议
成都
英文
1-4
2010-06-18（万方平台首次上网日期，不代表论文的发表时间）