Identification of new spectral signatures from hepatitis C virus infected human sera

Naseer, K.A.; Saleem, Muhammad; Ali, Safdar; Mirza, Bushra; Qazi, Javaria

doi:10.1016/j.saa.2019.117181

Cited by 23 publications

(19 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Raman peak at 1155 cm -1 is a spectral signature for the CO group of ribose, which is already reported as the most reliable marker for the HCV detection in serum [51]. Therefore, our results validate the previous reports on this Raman band for detecting HCV infection.…”

Section: ) Generate Features Of Reduced Dimensionalitysupporting

confidence: 90%

Analysis and Classification of Hepatitis Infections Using Raman Spectroscopy and Multiscale Convolutional Neural Networks

Zhao

Tian

et al. 2021

J Appl Spectrosc

View full text Add to dashboard Cite

Hepatitis infections represent a major health concern worldwide. Numerous computer-aided approaches have been devised for the early detection of hepatitis. In this study, we propose a method for the analysis and classification of cases of hepatitis-B virus ( HBV), hepatitis-C virus (HCV), and healthy subjects using Raman spectroscopy and a multiscale convolutional neural network (MSCNN). In particular, serum samples of HBV-infected patients (435 cases), HCV-infected patients (374 cases), and healthy persons (499 cases) are analyzed via Raman spectroscopy. The differences between Raman peaks in the measured serum spectra indicate specific biomolecular differences among the three classes. The dimensionality of the spectral data is reduced through principal component analysis. Subsequently, features are extracted, and then feature normalization is applied. Next, the extracted features are used to train different classifiers, namely MSCNN, a single-scale convolutional neural network, and other traditional classifiers. Among these classifiers, the MSCNN model achieved the best outcomes with a precision of 98.89%, sensitivity of 97.44%, specificity of 94.54%, and accuracy of 94.92%. Overall, the results demonstrate that Raman spectral analysis and MSCNN can be effectively utilized for rapid screening of hepatitis B and C cases.

show abstract

Section: ) Generate Features Of Reduced Dimensionalitysupporting

confidence: 90%

Analysis and Classification of Hepatitis Infections Using Raman Spectroscopy and Multiscale Convolutional Neural Networks

Zhao

Tian

et al. 2021

J Appl Spectrosc

View full text Add to dashboard Cite

show abstract

“…TL utilized the weights of pre-trained models which are trained on standard ImageNet dataset and retrained after modifications for entirely new problem. Fundamentally, in TL most of the network layer's weights are frozen and re-trained the existing networks for some of the last layers followed by hyper parameter tunings [27,[40][41][42]. In this work, challenging problem of in vitro HepG2 drug treated cancer cells response predictions using TL approach by modifying pre-trained ResNet101 DNN model is solved.…”

Section: Transfer Learning (Tl)mentioning

confidence: 99%

“…4. This concept makes ResNet101 more appropriate to avoid over fitting and achieve generalization compared to sequential DNN models such as AlexNet and VGG net for prediction problems [34,[42][43][44]. In Fig.…”

Section: Transfer Learning (Tl)mentioning

confidence: 99%

Drug Response Prediction of Liver Cancer Cell Line Using Deep Learning

Hassan¹,

Ali²,

Sanaullah³

et al. 2022

Computers, Materials &Amp; Continua

Self Cite

View full text Add to dashboard Cite

Cancer is the second deadliest human disease worldwide with high mortality rate. Rehabilitation and treatment of this disease requires precise and automatic assessment of effective drug response and control system. Prediction of treated and untreated cancerous cell line is one of the most challenging problems for precise and targeted drug delivery and response. A novel approach is proposed for prediction of drug treated and untreated cancer cell line automatically by employing modified Deep neural networks. Human hepatocellular carcinoma (HepG2) cells are exposed to anticancer drug functionalized CFO@BTO nanoparticles developed by our lab. Prediction models are developed by modifying ResNet101 and exploiting the transfer learning concept. Last three layers of ResNet101 are re-trained for the identification of drug treated cancer cells. Transfer learning approach in an appropriate choice especially when there is limited amount of annotated data. The proposed technique is validated on acquired 203 fluorescent microscopy images of human HepG2 cells treated with drug functionalized cobalt ferrite@barium titanate (CFO@BTO) magnetoelectric nanoparticles in vitro. The developed approach achieved high prediction with accuracy of 97.5% and sensitivity of 100% and outperformed other approaches. The high performance reveals the effectiveness of the approach. It is scalable and fully automatic prediction approach which can be extended for other similar cell diseases such as lung, brain tumor and breast cancer.

show abstract

“…13 Each molecule has a unique scattering patron, which serves as a fingerprint and hence identification entity for a particular molecule or compound in a mixture. In recent years, Raman spectra of blood serum samples were used to diagnose many types of infectious diseases, including dengue virus infection, [14][15][16] hepatitis C, 17,18 typhoid and malaria fever, [19][20][21] HIV infection, 22 tuberculosis, 23 and HBV infection. [24][25][26][27] Therefore, in order to improve the diagnostic capability for infectious diseases, new, reliable, online, and economical methods are needed to be developed for diagnosis and for monitoring the progression of infection.…”

Section: Introductionmentioning

confidence: 99%

“…[24][25][26][27] Therefore, in order to improve the diagnostic capability for infectious diseases, new, reliable, online, and economical methods are needed to be developed for diagnosis and for monitoring the progression of infection. In this regard, different research studies have been reported on the development of diagnostic algorithms using spectroscopic approaches such as Raman spectroscopy in combination with multivariate analysis including machine learning approaches such as support vector machine (SVM), 24,25,28 artificial neural network (ANN), 29 principal component analysis (PCA), 16,18 and partial least squares regression (PLSR). 15,27,30 During recent years, four studies have been reported on the detection of HBV infection in blood sera using Raman spectroscopy.…”

Section: Introductionmentioning

confidence: 99%

Optical diagnosis of hepatitis B virus infection in blood plasma using Raman spectroscopy and chemometric techniques

Saleem

Ali

Khan

et al. 2020

J Raman Spectroscopy

Self Cite

View full text Add to dashboard Cite

The potential of Raman spectroscopy has been utilized for the diagnosis of hepatitis B virus (HBV) infection in blood plasma. Raman spectra of 24 diseased and 10 healthy samples were used to develop distinct types of support vector machine (SVM) models, including linear, quadratic, and radial basis function (RBF) using multivariate method of principal component analysis (PCA) to reduce the dimensions of the obtained datasets. To assess the diagnostic power of these algorithms, developed models were tested on independent dataset. RBF‐based PCA‐SVM model achieved the best performance and yielded accuracy of 98.82%, sensitivity of 98.89%, and specificity of 98.80%. The performance of the SVM models was compared with rerated chemometric method of partial least square regression (PLSR), which has been developed by using the same dataset. The PLSR model attained the diagnostic accuracy of 88%, sensitivity of 93%, and specificity of 78% for same dataset. Our developed model has established promising results compared with state‐of‐the‐art approaches. The results reveal the improved performance of the developed chemometric techniques and clinical prediction potential of HBV by PCA‐SVMs in conjunction with Raman spectroscopy.

show abstract

Identification of new spectral signatures from hepatitis C virus infected human sera

Cited by 23 publications

References 55 publications

Analysis and Classification of Hepatitis Infections Using Raman Spectroscopy and Multiscale Convolutional Neural Networks

Analysis and Classification of Hepatitis Infections Using Raman Spectroscopy and Multiscale Convolutional Neural Networks

Drug Response Prediction of Liver Cancer Cell Line Using Deep Learning

Optical diagnosis of hepatitis B virus infection in blood plasma using Raman spectroscopy and chemometric techniques

Contact Info

Product

Resources

About