基于光学相干层析技术的甲状腺乳头状癌图像识别  

Optical Coherence Tomography-Based Identification for Papillary Carcinoma of Thyroid

作　　者：李增鸣 赵潮 张旭[1] 毛伟征[2] 赵航 史晓凤[1] 马君[1] Li Zengming;Zhao Chao;Zhang Xu;Mao Weizheng;Zhao Hang;Shi Xiaofeng;Ma Jun(Optics and Optoelectronics Laboratory,Faculty of Information Science and Engineering,Ocean University of China,Qingdao 266100,Shandong,China;Department of General Surgery,Qingdao Municipal Hospital,Qingdao 266071,Shandong,China)

机构地区：[1]中国海洋大学信息科学与工程学部光学光电子实验室,山东青岛266100 [2]青岛市市立医院普外科,山东青岛266071

出　　处：《激光与光电子学进展》2023年第4期397-403,共7页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(41476081);山东省重点研发项目(2019GHY112027);山东省自然科学基金(ZR2020MF121)。

摘　　要：光学相干层析技术(OCT)作为一种实时、无创的高分辨率成像手段,能够使用特征提取算法获得丰富的图像信息,为疾病的诊断提供客观依据。利用OCT对17例甲状腺正常组织与乳头状癌组织进行成像。针对甲状腺组织图像的特点,使用灰度共生矩阵(GLCM)、灰度直方图(GH)、中心对称自相关(CSAC)和Laws纹理测度(LM)4种算法提取图像特征值,并结合支持向量机(SVM)算法定量地评估不同特征组合的识别性能。结果显示,GLCM-GH-LM组合性能最优,能够从多个方面获得图像的纹理和灰度特征信息,灵敏度、特异性和准确度分别高达96.3%、92.2%和94.3%。研究表明,基于特征提取和机器学习的算法对甲状腺乳头状癌OCT图像进行量化分析及识别时不仅可以提供实时的监测图像,还对甲状腺恶性肿瘤临床诊断具有重要的参考价值。As a realtime,noninvasive,and highresolution imaging method,optical coherence tomography(OCT)provides rich image information using feature extraction algorithms and provides basis for the objective diagnosis of diseases.This study imaged 17 normal thyroid tissues and papillary carcinoma tissues using the OCT system.According to the characteristics of thyroid tissue images,a gray level cooccurrence matrix(GLCM),gray level histogram(GH),centersymmetric autocorrelation(CSAC),and Laws’texture measure(LM)were used to extract the image eigenvalues.Similarly,we quantitatively evaluated the identification performance of the different feature combinations using a support vector machine(SVM)algorithm.The results indicate that GLCMGHLM model has the best performance,with a sensitivity,specificity,and accuracy of 96.3%,92.2%,and 94.3%,respectively.Moreover,it can obtain texture and gray feature information from multiple aspects.This study illustrates that the algorithm based on feature extraction and machine learning can not only provide realtime monitoring images,but also have important reference value for clinical diagnosis of thyroid malignant tumors when performing quantitative analysis and recognition for OCT images of papillary carcinoma of thyroid.

关 键 词：光学相干层析技术 甲状腺 纹理特征 支持向量机 

分 类 号：O439[机械工程—光学工程]