Application of Supervised Self-Organizing Maps in Breast Cancer Diagnosis by Total Synchronous Fluorescence Spectroscopy
Апстракт
Data from total synchronous fluorescence spectroscopy (TSFS) measurements of normal and malignant breast tissue samples are introduced in supervised self-organizing maps, a type of artificial neural network (ANN), to obtain diagnosis. Three spectral regions in both TSFS patterns and first-derivative TSFS patterns exhibited clear differences between normal and malignant tissue groups, and intensities measured from these regions served as inputs to neural networks. Histology findings are used as the gold standard to train self-organizing maps in a supervised way. Diagnostic accuracy of this procedure is evaluated with sample test groups for two cases, when the neural network uses TSFS data and when the neural network uses data from first-derivative TSFS. In the first case diagnostic sensitivity of 87.1% and specificity of 91.7% are found, while in the second case sensitivity of 100% and specificity of 94.4% are achieved.
Кључне речи:
Total synchronous fluorescence spectroscopy / Breast cancer / Artificial neural networks / ANNs / Self-organizing maps / SOMsИзвор:
Applied Spectroscopy, 2011, 65, 3, 293-297Финансирање / пројекти:
- Serbian Ministry of Science and Technological Development [143010]
DOI: 10.1366/10-05928
ISSN: 0003-7028
PubMed: 21352649
WoS: 000287945700008
Scopus: 2-s2.0-79952951811
Колекције
Институција/група
VinčaTY - JOUR AU - Dramićanin, Tatjana AU - Dimitrijević, Bogomir B. AU - Dramićanin, Miroslav PY - 2011 UR - https://vinar.vin.bg.ac.rs/handle/123456789/4235 AB - Data from total synchronous fluorescence spectroscopy (TSFS) measurements of normal and malignant breast tissue samples are introduced in supervised self-organizing maps, a type of artificial neural network (ANN), to obtain diagnosis. Three spectral regions in both TSFS patterns and first-derivative TSFS patterns exhibited clear differences between normal and malignant tissue groups, and intensities measured from these regions served as inputs to neural networks. Histology findings are used as the gold standard to train self-organizing maps in a supervised way. Diagnostic accuracy of this procedure is evaluated with sample test groups for two cases, when the neural network uses TSFS data and when the neural network uses data from first-derivative TSFS. In the first case diagnostic sensitivity of 87.1% and specificity of 91.7% are found, while in the second case sensitivity of 100% and specificity of 94.4% are achieved. T2 - Applied Spectroscopy T1 - Application of Supervised Self-Organizing Maps in Breast Cancer Diagnosis by Total Synchronous Fluorescence Spectroscopy VL - 65 IS - 3 SP - 293 EP - 297 DO - 10.1366/10-05928 ER -
@article{ author = "Dramićanin, Tatjana and Dimitrijević, Bogomir B. and Dramićanin, Miroslav", year = "2011", abstract = "Data from total synchronous fluorescence spectroscopy (TSFS) measurements of normal and malignant breast tissue samples are introduced in supervised self-organizing maps, a type of artificial neural network (ANN), to obtain diagnosis. Three spectral regions in both TSFS patterns and first-derivative TSFS patterns exhibited clear differences between normal and malignant tissue groups, and intensities measured from these regions served as inputs to neural networks. Histology findings are used as the gold standard to train self-organizing maps in a supervised way. Diagnostic accuracy of this procedure is evaluated with sample test groups for two cases, when the neural network uses TSFS data and when the neural network uses data from first-derivative TSFS. In the first case diagnostic sensitivity of 87.1% and specificity of 91.7% are found, while in the second case sensitivity of 100% and specificity of 94.4% are achieved.", journal = "Applied Spectroscopy", title = "Application of Supervised Self-Organizing Maps in Breast Cancer Diagnosis by Total Synchronous Fluorescence Spectroscopy", volume = "65", number = "3", pages = "293-297", doi = "10.1366/10-05928" }
Dramićanin, T., Dimitrijević, B. B.,& Dramićanin, M.. (2011). Application of Supervised Self-Organizing Maps in Breast Cancer Diagnosis by Total Synchronous Fluorescence Spectroscopy. in Applied Spectroscopy, 65(3), 293-297. https://doi.org/10.1366/10-05928
Dramićanin T, Dimitrijević BB, Dramićanin M. Application of Supervised Self-Organizing Maps in Breast Cancer Diagnosis by Total Synchronous Fluorescence Spectroscopy. in Applied Spectroscopy. 2011;65(3):293-297. doi:10.1366/10-05928 .
Dramićanin, Tatjana, Dimitrijević, Bogomir B., Dramićanin, Miroslav, "Application of Supervised Self-Organizing Maps in Breast Cancer Diagnosis by Total Synchronous Fluorescence Spectroscopy" in Applied Spectroscopy, 65, no. 3 (2011):293-297, https://doi.org/10.1366/10-05928 . .