PEDRO ARTHUR AUGUSTO DE CASTRO
2 resultados
Resultados de Busca
Agora exibindo 1 - 2 de 2
Artigo IPEN-doc 28166 The impact of scan number and its preprocessing in micro-FTIR imaging when applying machine learning for breast cancer subtypes classification2021 - DEL-VALLE, MATHEUS; SANTOS, MOISES O. dos; SANTOS, SOFIA N. dos; CASTRO, PEDRO A.A. de; BERNARDES, EMERSON S.; ZEZELL, DENISE M.The breast cancer molecular subtype is an important classification to outline the prognostic. Gold-standard assessing using immunohistochemistry adds subjectivity due to interlaboratory and interobserver variations. In order to increase the diagnosis confidence, other techniques need to be examined, where the FTIR spectroscopy imaging allied with machine learning techniques may provide additional and quantitative information regarding the molecular composition. However, the impact of co-added scans acquisition parameter into machine learning classifications still needs better evaluation. In this study, FTIR images of Luminal B and HER2 subtypes were acquired varying the scan number and preprocessing techniques. It was demonstrated a spectral quality improvement when the scan number was increased, decreasing the standard deviation and outliers. Six machine learning models were used to classify the subtypes: Linear Discriminant Analysis, Partial Least Squares Discriminant Analysis, K-Nearest Neighbors, Support Vector Machine, Random Forest and Extreme Gradient Boosting. Best mean accuracy of 0.995 was achieved by Extreme Gradient Boosting model. It was found that all models achieved similar high accuracies with groups b256_064 (256 background and 064 scans), b256_128 and b128_128. Besides assessing the performance of different models, the b256_064 was established as the optimal group due to the minimum acquisition time. Therefore, this work indicates b256_064 for breast cancer subtype classification and also as a basis for other studies using machine learning for cancer evaluation.Artigo IPEN-doc 27120 Monitoring the progress and healing status of burn wounds using infrared spectroscopy2020 - CASTRO, PEDRO A.A.; LIMA, CASSIO A.; MORAIS, MYCHEL R.P.T.; ZORN, TELMA M.T.; ZEZELL, DENISE M.Burns are one of the leading causes of morbidity worldwide and the most costly traumatic injuries. A better understanding of the molecular mechanisms in wound healing is required to accelerate tissue recovery and reduce the health economic impact. However, the standard techniques used to evaluate the biological events associated to wound repair are laborious, time-consuming, and/or require multiple assays/staining. Therefore, this study aims to evaluate the feasibility of Fourier transform infrared (FT-IR) spectroscopy to monitor the progress and healing status of burn wounds. Burn injuries were induced on Wistar rats by water vapor exposure and biopsied for further histopathological and spectroscopic evaluation at four time-points (3, 7, 14, and 21 days). Spectral data were preprocessed and compared by principal component analysis. Pairwise comparison of post-burn groups to each other revealed that metabolic activity induced by thermal injury decreases as the healing progresses. Higher amounts of carbohydrates, proteins, lipids, and nucleic acids were evidenced on days 3 and 7 compared to healthy skin and reduced amounts of these molecular structural units on days 14 and 21 postburn. FT-IR spectroscopy was used to determine the healing status of a wound based on the biochemical information retained by spectral signatures in each phase of healing. Our findings demonstrate that FT-IR spectroscopy can monitor the biological events triggered by burn trauma as well as to detect the wound status including full recovery based on the spectral changes associated to the biochemical events in each phase.