Artificial neural networks for processing fluorescence spectroscopy data in skin cancer diagnostics
Апстракт
Over the years various optical spectroscopic techniques have been widely used as diagnostic tools in the discrimination of many types of malignant diseases. Recently, synchronous fluorescent spectroscopy (SFS) coupled with chemometrics has been applied in cancer diagnostics. The SFS method involves simultaneous scanning of both emission and excitation wavelengths while keeping the interval of wavelengths (constant-wavelength mode) or frequencies (constant-energy mode) between them constant. This method is fast, relatively inexpensive, sensitive and non-invasive. Total synchronous fluorescence spectra of normal skin, nevus and melanoma samples were used as input for training of artificial neural networks. Two different types of artificial neural networks were trained, the self-organizing map and the feed-forward neural network. Histopathology results of investigated skin samples were used as the gold standard for network output. Based on the obtained classification success rate of neura...l networks, we concluded that both networks provided high sensitivity with classification errors between 2 and 4%.
Извор:
Physica Scripta, 2013, T157Финансирање / пројекти:
- Материјали редуковане димензионалности за ефикасну апсорпцију светлости и конверзију енергије (RS-MESTD-Integrated and Interdisciplinary Research (IIR or III)-45020)
- Молекуларне детерминанте за дизајн тумор маркера (RS-MESTD-Basic Research (BR or ON)-173049)
Напомена:
- 3rd International Conference on the Physics of Optical Materials and Devices, Sep 02-06, 2012, Belgrade, Serbia
DOI: 10.1088/0031-8949/2013/T157/014057
ISSN: 0031-8949; 1402-4896
WoS: 000332504600058
Scopus: 2-s2.0-84891860671
Колекције
Институција/група
VinčaTY - JOUR AU - Lenhardt, Lea I. AU - Zeković, Ivana Lj. AU - Dramićanin, Tatjana AU - Dramićanin, Miroslav PY - 2013 UR - https://vinar.vin.bg.ac.rs/handle/123456789/7026 AB - Over the years various optical spectroscopic techniques have been widely used as diagnostic tools in the discrimination of many types of malignant diseases. Recently, synchronous fluorescent spectroscopy (SFS) coupled with chemometrics has been applied in cancer diagnostics. The SFS method involves simultaneous scanning of both emission and excitation wavelengths while keeping the interval of wavelengths (constant-wavelength mode) or frequencies (constant-energy mode) between them constant. This method is fast, relatively inexpensive, sensitive and non-invasive. Total synchronous fluorescence spectra of normal skin, nevus and melanoma samples were used as input for training of artificial neural networks. Two different types of artificial neural networks were trained, the self-organizing map and the feed-forward neural network. Histopathology results of investigated skin samples were used as the gold standard for network output. Based on the obtained classification success rate of neural networks, we concluded that both networks provided high sensitivity with classification errors between 2 and 4%. T2 - Physica Scripta T1 - Artificial neural networks for processing fluorescence spectroscopy data in skin cancer diagnostics VL - T157 DO - 10.1088/0031-8949/2013/T157/014057 ER -
@article{ author = "Lenhardt, Lea I. and Zeković, Ivana Lj. and Dramićanin, Tatjana and Dramićanin, Miroslav", year = "2013", abstract = "Over the years various optical spectroscopic techniques have been widely used as diagnostic tools in the discrimination of many types of malignant diseases. Recently, synchronous fluorescent spectroscopy (SFS) coupled with chemometrics has been applied in cancer diagnostics. The SFS method involves simultaneous scanning of both emission and excitation wavelengths while keeping the interval of wavelengths (constant-wavelength mode) or frequencies (constant-energy mode) between them constant. This method is fast, relatively inexpensive, sensitive and non-invasive. Total synchronous fluorescence spectra of normal skin, nevus and melanoma samples were used as input for training of artificial neural networks. Two different types of artificial neural networks were trained, the self-organizing map and the feed-forward neural network. Histopathology results of investigated skin samples were used as the gold standard for network output. Based on the obtained classification success rate of neural networks, we concluded that both networks provided high sensitivity with classification errors between 2 and 4%.", journal = "Physica Scripta", title = "Artificial neural networks for processing fluorescence spectroscopy data in skin cancer diagnostics", volume = "T157", doi = "10.1088/0031-8949/2013/T157/014057" }
Lenhardt, L. I., Zeković, I. Lj., Dramićanin, T.,& Dramićanin, M.. (2013). Artificial neural networks for processing fluorescence spectroscopy data in skin cancer diagnostics. in Physica Scripta, T157. https://doi.org/10.1088/0031-8949/2013/T157/014057
Lenhardt LI, Zeković IL, Dramićanin T, Dramićanin M. Artificial neural networks for processing fluorescence spectroscopy data in skin cancer diagnostics. in Physica Scripta. 2013;T157. doi:10.1088/0031-8949/2013/T157/014057 .
Lenhardt, Lea I., Zeković, Ivana Lj., Dramićanin, Tatjana, Dramićanin, Miroslav, "Artificial neural networks for processing fluorescence spectroscopy data in skin cancer diagnostics" in Physica Scripta, T157 (2013), https://doi.org/10.1088/0031-8949/2013/T157/014057 . .