SAJID FAROOQ
11 resultados
Resultados de Busca
Agora exibindo 1 - 10 de 11
Artigo IPEN-doc 30368 Recognition of breast cancer subtypes using FTIR hyperspectral data2024 - FAROOQ, SAJID; DEL-VALLE, MATHEUS; SANTOS, SOFIA N. dos; BERNARDES, EMERSON S.; ZEZELL, DENISE M.Fourier -transform infrared spectroscopy (FTIR) is a powerful, non-destructive, highly sensitive and a promising analytical technique to provide spectrochemical signatures of biological samples, where markers like carbohydrates, proteins, and phosphate groups of DNA can be recognized in biological micro -environment. However, method of measurements of large cells need an excessive time to achieve high quality images, making its clinical use difficult due to speed of data -acquisition and lack of optimized computational procedures. To address such challenges, Machine Learning (ML) based technologies can assist to assess an accurate prognostication of breast cancer (BC) subtypes with high performance. Here, we applied FTIR spectroscopy to identify breast cancer subtypes in order to differentiate between luminal (BT474) and nonluminal (SKBR3) molecular subtypes. For this reason, we tested multivariate classification technique to extract feature information employing three -dimension (3D) -discriminant analysis approach based on 3D -principle component analysis -linear discriminant analysis (3D-PCA-LDA) and 3D -principal component analysis -quadratic discriminant analysis (3D-PCA-QDA), showing an improvement in sensitivity (98%), specificity (94%) and accuracy (98%) parameters compared to conventional unfolded methods. Our results evidence that 3D-PCALDA and 3D-PCA-QDA are potential tools for discriminant analysis of hyperspectral dataset to obtain superior classification assessment.Artigo IPEN-doc 30225 Diabetes monitoring through urine analysis using ATR-FTIR spectroscopy and machine learning2023 - FAROOQ, SAJID; ZEZELL, DENISE M.Diabetes mellitus (DM) is a widespread and rapidly growing disease, and it is estimated that it will impact up to 693 million adults by 2045. To cope this challenge, the innovative advances in non-destructive progressive urine glucose-monitoring platforms are important for improving diabetes surveillance technologies. In this study, we aim to better evaluate DM by analyzing 149 urine spectral samples (86 diabetes and 63 healthy control male Wistar rats) utilizing attenuated total reflection–Fourier transform infrared (ATR-FTIR) spectroscopy combined with machine learning (ML) methods, including a 3D discriminant analysis approach—3D–Principal Component Analysis–Linear Discriminant Analysis (3D-PCA-LDA)—in the ‘bio-fingerprint’ region of 1800–900 cm−1 . The 3D discriminant analysis technique demonstrated superior performance compared to the conventional PCA-LDA approach with the 3D-PCA-LDA method achieving 100% accuracy, sensitivity, and specificity. Our results show that this study contributes to the existing methodologies on non-destructive diagnostic methods for DM and also highlights the promising potential of ATR-FTIR spectroscopy with an ML-driven 3D-discriminant analysis approach in disease classification and monitoring.Artigo IPEN-doc 30192 A 3D discriminant analysis for hyperspectral FTIR images2023 - FAROOQ, SAJID; GERMANO, GLEICE; STANCARI, KLEBER A.; RAFFAELI, ROCIO; CROCE, MARIA V.; CROCE, ADELA E.; ZEZELL, DENISE M.Here, we apply a 3D discriminant analysis approach to analyze FTIR hyperspectral images of normal vs malignant Melanoma (MM) samples for skin cancer diagnosis. For this porpose we used 2 samples, for Normal (49k) and for MM(90k). Our results evidence the outstanding performance with accuracy up to 81% for big data (> 100k).Artigo IPEN-doc 30188 Identification of basal cell carcinoma skin cancer using FTIR and Machine learning2023 - PERES, DANIELLA L.; FAROOQ, SAJID; RAFFAELI, ROCIO; CROCE, MARIA V.; CROCE, ADELA E.; ZEZELL, DENISE M.Here we applied ATR-FTIR spectroscopy combined with computational modeling based on 3D-discriminant analysis (3D-PCA-QDA). Our results present an exceptional performance of 3D-discriminant algorithms to diagnose BCC skin cancer, indicating the accuracy up to 99%.Artigo IPEN-doc 30186 Monitoring changes in urine from diabetic rats using ATR-FTIR and Machine Learning2023 - FAROOQ, SAJID; PERES, DANIELLA L.; CAIXETA, DOUGLAS C.; LIMA, CASSIO; SILVA, ROBINSON S. da; ZEZELL, DENISE M.Here, we aim to better characterize diabetes mellitus (DM) by analyzing 149 urine spectral samples, comprising of diabetes versus healthy control groups employing ATR-FTIR spectroscopy, combined with a 3D discriminant analysis machine learning approach. Our results depict that the model is highly precise with accuracy close to 100%.Resumo IPEN-doc 29572 Breast cancer subtypes diagnostic via high performance supervised machine learning2022 - FAROOQ, SAJID; DEL-VALLE, MATHEUS; SANTOS, MOISES O. dos; NASCIMENTO, SOFIA; BERNARDES, EMERSON S.; ZEZELL, DENISE M.Aim: Breast cancer molecular subtypes are being used to improve clinical decision. The Fourier transform infrared (FTIR) spectroscopic imaging, which is a powerful and non-destructive technique, allows performing a non-perturbative and labelling free extraction of biochemical information towards diagnosis and evaluation for cell functionality. However, methods of measurements of large areas of cells demand a long time to achieve high quality images, making its clinical use impractical because of speed of data acquisition and dearth of optimized computational procedures. In order to cope with these challenges, Machine learning (ML) technologies can facilitate to obtain accurate prognosis of Breast Cancer (BC) subtypes with high action ability and accuracy. Methods: Here we propose a ML algorithm based method to distinguish computationally BC cell lines. The method is developed by coupling K neighbors Classifier (KNN) with Neighborhood Component Analysis (NCA) and NCA-KNN methods enables to identify BC subtypes without increasing model size as well additional parameters. Results: By incorporating FTIR imaging data, we show that using NCA-KNN method, the classification accuracies, specificities and sensitivities improve up to 97%, even at very low co-added scan (S_4). Moreover, a clear distinctive accuracy difference of our proposed method was obtained in comparison with other ML supervised models. Conclusion: For confirming our model results performance, the cross validation (k fold = 10) and receiver operation characteristics (ROC) curve were used and found in great agreement, suggest a potential diagnostic method for BC subtypes, even with small co-added scan < 8 at low spectral resolution (4 cm-1).Artigo IPEN-doc 29364 Exploring enamel demineralization from SEM images using deep learning algorithms2022 - FAROOQ, SAJID; CARAMEL-JUVINO, AMANDA; FONTES, YASMIN R.; GARDIANO, SABRINA A.; ZEZELL, DENISE M.Here, we employ segmentation and convolutional neural network (CNN) to identify and quantify enamel demineralization. Our results depict that CNN model using input SEM images achieve accuracy up to 79% for enamel demineralization diagnosis.Artigo IPEN-doc 29360 Identifying breast cancer cell lines using high performance machine learning methods2022 - FAROOQ, SAJID; DEL-VALLE, MATHEUS; SANTOS, SOFIA; BERNARDES, EMERSON S.; ZEZELL, DENISE M.We present a computational framework based on machine learning classifiers K-Nearest Neighbors and Neighborhood Component analysis for breast cancer (BC) subtypes prognostic. Our results has up to 97% accuracy for prognostic stratification of BC subtypes.Artigo IPEN-doc 29303 Superior Machine Learning Method for breast cancer cell lines identification2022 - FAROOQ, SAJID; CARAMEL-JUVINO, AMANDA; DEL-VALLE, MATHEUS; SANTOS, SOFIA; BERNARDES, EMERSON S.; ZEZELL, DENISE M.We propose an artificial intelligence platform based on machine learning (ML) algorithm using Neighborhood Component analysis and K-Nearest Neighbors for breast cancer cell lines recognition. Our model presents up to 97% accuracy for identification of breast cancer cell lines.Artigo IPEN-doc 29302 Identification of enamel demineralization using high performance convolutional neural network2022 - CARAMEL-JUVINO, AMANDA; FAROOQ, SAJID; ROMANO, MARIANA; ZEZELL, DENISE M.Here, we traces use segmentation and convolutional neural network (CNN) to trace, diagnose and quantify enamel demineralization for research. The preprocessing, histograms based methods are used to enhance the contrast and equalize the brightness through the scanning electron microscope images. Our result evidence that the deep learning based CNN model is highly efficient to process the dental image to achieve high accuracy of enamel demineralization and presents promising outcomes with optimal precision.