利用梯度下降极小惯量法的脑中线偏离度算法  

Brain midline deviation algorithm using minimal inertia method of gradient descent

作　　者：刘柱 孔维超 丁长青[1] 王旭光[1] 匡登峰[2] LIU Zhu;KONG Wei-chao;DING Chang-qing;WANG Xu-guang;KUANG Deng-feng(Fengxian People′s Hospital,Jiangsu,221700,China;Institute of Modern Optics,Nankai University,Tianjin,300350,China)

机构地区：[1]丰县人民医院,江苏221700 [2]南开大学电子信息与光学工程学院现代光学研究所,天津300350

出　　处：《光电子．激光》2020年第2期194-198,共5页Journal of Optoelectronics·Laser

基　　金：天津市自然科学基金(18JCZDJC38200);国家科学自然基金(11274186)资助项目。

摘　　要：大脑受到创伤后往往会伴随着结构的移位,而脑中线的移位程度对医生预估脑内压强、脑疝等脑部创伤后并发症的重要标准。本文以两位脑创伤患者在接受治疗期间内的影响资料为对象,研究了用梯度下降的极小惯量法计算大脑的理想对称轴,并与患者的实际脑中线相比较,归一化后脑中线偏离度随时间变化的趋势图与临床的症状完全吻合,因而对医生的临床判断具有重要意义。The brain is often accompanied by structural displacement after trauma,and the degree of displacement of the midline of the brain is an important criterion for doctors to predict post-traumatic complications such as intracerebral pressure and cerebral palsy.Here,Based on the imaging data of a patient within one month after a brain injury,we used the minimum inertia method of gradient descent to calculate the position of the ideal brain line.The trend of brain line deviation curve with time after normalization was consistent with clinical diagnosis.

关 键 词：光学信息处理 临床医学 梯度下降算法 脑中线 电子计算机体层扫描 

分 类 号：R445.3[医药卫生—影像医学与核医学]