显微高光谱成像的皮肤黑色素瘤浅表扩散深度识别方法  

Identification and measurement of cutaneous melanoma superficial spreading depth using microscopic hyperspectral imaging technology

作　　者：王健生 李庆利[1,2,3] 周梅 孙力[1,2] 胡孟晗[1,2] 吕岳[1,2] 褚君浩[1,3] WANG Jian-Sheng;LI Qing-Li;ZHOU Mei;SUN Li;HU Meng-Han;LYU Yue;CHU Jun-Hao(Shanghai Key Laboratory of Multidimensional Information Processing,East China Normal University,Shanghai 200241,China;Engineering Center of SHMEC for Space Information and GNSS,Shanghai 200241,China;Engineering Research Center of Nanophotonics&Advanced Instrument,Ministry of Education,East China Normal University,Shanghai 200241,China)

机构地区：[1]华东师范大学上海市多维度信息处理重点实验室,上海200241 [2]华东师范大学空间信息与定位导航上海高校工程研究中心,上海200241 [3]华东师范大学纳光电集成与先进装备教育部工程研究中心,上海200241

出　　处：《红外与毫米波学报》2020年第6期749-759,共11页Journal of Infrared and Millimeter Waves

基　　金：Supported by National Natural Science Foundation of China(61975056);Shanghai Natural Science Foundation(19ZR1416000);the Science and Technology Commission of Shanghai Municipality(20440713100,19511120100).

摘　　要：研究了基于显微高光谱图像的皮肤黑色素瘤浅表扩散深度检测方法.首先使用核最小噪声分割、形态滤波和边缘检测实现颗粒层的分割,然后使用基于特征谱监督的最小二乘支持向量机实现恶性黑色素细胞的检测,最后定量化计算了皮肤黑色素瘤的扩散深度.实验结果表明,可以为皮肤黑色素瘤的浅表扩散提供定量化的参考指标,有利于皮肤黑色素瘤的病理诊断.This paper presents an automatic approach for measurement of the superficial spreading depth of cuta⁃neous melanomas based on microscopic hyperspectral imaging technology.To extract the skin granular layer,an edge detection method combined with kernel minimum noise fraction is proposed.Then least squares support vec⁃tor machine based on characteristic spectrum supervision is used to identify malignant melanocytes.The measure⁃ment of tumor superficial spreading depth depends on the vertical distance from the skin granular layer to the deep⁃est malignant melanocytes.Experimental results illustrate that the proposed method is possible to provide an effec⁃tive reference for the diagnosis and treatment of cutaneous melanoma.

关 键 词：图像处理 肿瘤浅表扩散深度 机器学习 显微高光谱成像 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]