Lasers in surgery and medicine · 2015
Discrimination of non-melanoma skin lesions from non-tumor human skin tissues in vivo using Raman spectroscopy and multivariate statistics.
Оценочное исследованиеСтатьяПоддержка исследования: вне правительства СШАНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Silveira Fabricio L, Pacheco Marcos T T, Bodanese Benito, Pasqualucci Carlos A, Zângaro Renato A, Silveira Landulfo
Аннотация
BACKGROUND AND OBJECTIVE: Raman spectroscopy was used to discriminate human non-melanoma skin lesions from non-tumor tissues in vivo. This work proposed the discrimination between non-melanoma (basal cell carcinoma, BCC; squamous cell carcinoma, SCC) and pre-cancerous lesions (actinic keratosis, AK) from benign lesions and normal (non-tumor group, NT) tissues, using near-infrared Raman spectroscopy with a Raman probe.
MATERIALS AND METHODS: Prior to surgery, the spectra of suspicious lesions were obtained in situ. The spectra of adjacent, clinically normal skin were also obtained. Lesions were resectioned and submitted for histopathology. The Raman spectra were measured using a Raman spectrometer (830 nm). Two types of discrimination models were developed to distinguish the different histopathological groups. The principal components analysis discriminant analysis (PCA/DA) and the partial least squares discriminant analysis (PLS/DA) were based on Euclidean, quadratic and Mahalanobis distances.
RESULTS: PCA and PLS spectral vectors showed spectral features of skin constituents, such as lipids (between 1,250 cm(-1) and 1,300 cm(-1) and at 1,450 cm(-1)) and proteins (between 870 cm(-1) and 940 cm(-1), 1,240 cm(-1) and 1,271 cm(-1), and at 1,000 cm(-1) and 1,450 cm(-1)). Despite the small spectral differences between malignant lesions and benign tissues, the algorithms discriminated the spectra of non-melanoma skin and pre-cancerous lesions from benign and normal tissues, with an overall accuracy of 82.8% and 91.9%, respectively.
CONCLUSION: PCA and PLS could discriminate Raman spectra of skin tissues, opening the way for an in vivo optical diagnosis.
MATERIALS AND METHODS: Prior to surgery, the spectra of suspicious lesions were obtained in situ. The spectra of adjacent, clinically normal skin were also obtained. Lesions were resectioned and submitted for histopathology. The Raman spectra were measured using a Raman spectrometer (830 nm). Two types of discrimination models were developed to distinguish the different histopathological groups. The principal components analysis discriminant analysis (PCA/DA) and the partial least squares discriminant analysis (PLS/DA) were based on Euclidean, quadratic and Mahalanobis distances.
RESULTS: PCA and PLS spectral vectors showed spectral features of skin constituents, such as lipids (between 1,250 cm(-1) and 1,300 cm(-1) and at 1,450 cm(-1)) and proteins (between 870 cm(-1) and 940 cm(-1), 1,240 cm(-1) and 1,271 cm(-1), and at 1,000 cm(-1) and 1,450 cm(-1)). Despite the small spectral differences between malignant lesions and benign tissues, the algorithms discriminated the spectra of non-melanoma skin and pre-cancerous lesions from benign and normal tissues, with an overall accuracy of 82.8% and 91.9%, respectively.
CONCLUSION: PCA and PLS could discriminate Raman spectra of skin tissues, opening the way for an in vivo optical diagnosis.
Предметные рубрики MeSH
AdultAgedAlgorithmsBasal Cell CarcinomaCarcinoma, Squamous CellCase-Control StudiesDecision Support TechniquesDiagnosis, DifferentialDiscriminant AnalysisFemaleHumansKeratosis, ActinicLeast-Squares AnalysisMaleMiddle AgedMultivariate AnalysisPrincipal Component AnalysisSkin NeoplasmsSpectroscopy, Near-InfraredSpectrum Analysis, Raman