Vinča Institute of Nuclear Sciences, University of Belgrade, P.O. Box 522, 11001 Belgrade, Serbia.
J Fluoresc. 2012 Sep;22(5):1281-9. doi: 10.1007/s10895-012-1070-0. Epub 2012 Jun 8.
Excitation-emission matrices (EEM) and total synchronous fluorescence spectra (SFS) of normal and malignant breast tissue specimens are measured in UV-VIS spectral region to serve as data inputs in development of Support Vector Machine (SVM) based breast cancer diagnostics tool. Various input data combinations are tested for classification accuracy using SVM prediction against histopathology findings to discover the best combination regarding diagnostics sensitivity and specificity. It is shown that with EEM data SVM provided 67% sensitivity and 62% specificity diagnostics. With SFS data SVM provided 100% sensitivity and specificity for a several input data combinations. Among these combinations those that require minimal data inputs are identified.
采用紫外可见光谱法分别测量正常和恶性乳腺组织标本的激发-发射矩阵（EEM）和全同步荧光光谱（SFS），作为支持向量机（SVM）的基础上开发乳腺癌诊断工具的数据输入。通过 SVM 预测与组织病理学结果进行比较，测试了各种输入数据组合的分类准确性，以发现关于诊断灵敏度和特异性的最佳组合。结果表明，使用 EEM 数据，SVM 的诊断灵敏度为 67%，特异性为 62%。使用 SFS 数据，对于几种输入数据组合，SVM 的灵敏度和特异性均为 100%。在这些组合中，确定了那些需要最小数据输入的组合。
