Multi-class classification algorithm for optical diagnosis of oral cancer
Multi-class classification algorithm for optical diagnosis of oral cancer
复制标题
DOI：
10.1016/j.jphotobiol.2006.05.004
复制
发表时间：
2006-11-01
影响因子：
5.4
通讯作者：
Gupta, P. K.
中科院分区：
文献类型：
--
作者：
Majumder, S. K.;Gupta, A.;Gupta, P. K.
我们报道了一种直接的多分类光谱诊断算法，用于区分人类口腔的高级别癌组织部位和低级别癌组织部位以及癌前组织和正常鳞状组织部位。该算法是利用最近形成的全主成分回归(TPCR)理论开发的。使用从Indore政府肿瘤医院筛查口腔肿瘤的患者获得的体内自发光光谱数据来训练和验证算法。基于TPCR的诊断算法在高级别鳞癌、低级别鳞癌、白斑和正常鳞状组织四种不同类别的组织位置分类中提供了令人满意的性能。这四个类别的分类准确率与训练数据集的94%、100%、100%和91%相似(基于留一交叉验证)，而对于独立验证数据集的相应类别，分类准确率分别类似90%、90%、85%和88%。(C)2006爱思唯尔B.V.保留所有权利。
We report development of a direct multi-class spectroscopic diagnostic algorithm for discrimination of high-grade cancerous tissue sites from low-grade as well as precancerous and normal squamous tissue sites of human oral cavity. The algorithm was developed making use of the recently formulated theory of total principal component regression (TPCR). The in vivo autolluorescence spectral data acquired from patients screened for neoplasm of oral cavity at the Government Cancer Hospital, Indore, was used to train and validate the algorithm. The diagnostic algorithm based on TPCR was found to provide satisfactory performance in classifying the tissue sites in four different classes-high-grade squamous cell carcinoma, low-grade squamous cell carcinoma, leukoplakia, and normal squamous tissue. The classification accuracy for these four classes was observed to be similar to 94%, 100%, 100% and 91% for the training data set (based on leave-one-out cross-validation), and was similar to 90%, 90%, 85% and 88%, respectively for the corresponding classes for the independent validation data set. (c) 2006 Elsevier B.V. All rights reserved.