An antibody-free liver cancer screening approach based on nanoplasmonics biosensing chips via spectrum-based deep learning

Cheng, Ningtao; Fu, Jing; Chen, Dajing; Chen, Shuzhen; Wang, Hongyang

doi:10.1016/j.impact.2021.100296

Cited by 22 publications

(18 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model is composed of 4 conv-blocks for the extraction of features and 1 output layer for the classification of the spectrogram. Aside from the aforementioned, Chen et al, deployed a 1D-CNN to a nanoplasmonics biosensing chip (NBC), on a validation dataset which was accurately identified with an accuracy of 91 % [25]. This model has 8 kernels or 16 kernels of size 3×1 in 2 convolutional layers, correspondingly.…”

Section: Related Workmentioning

confidence: 99%

A Label-Free Marker Based Breast Cancer Detection using Hybrid Deep Learning Models and Raman Spectroscopy

Selvarani

Jose

2023

Trends Sci

View full text Add to dashboard Cite

Breast Cancer (BC) is a serious menace to women’s health around the world. Early BC identification has been critically important for diagnosing protocol. Several classification methods for breast cancer were examined recently with various techniques, and Raman spectroscopy (RS) has become an effective approach for the identification of responsible metabolites. Moreover, the rapid and accurate classification of BC using RS necessitates active engagement in processing and analyzing Raman spectral data. This work aims to develop an efficient Hybrid Deep Learning (HDL) neural network model to differentiate breast cancer blood plasma from control samples and the spectral features obtained are used as spectral cancer markers for the detection of breast cancer. To find the optimum performing HDL model, several other HDL models were implemented to perform the binary classification of the Raman spectral signal. A total of 62199 Raman spectra generated from 26 blood plasma samples are evaluated in this study. Mainly 6 HDL methods, 1D-CNN-GRU, CNN-BiLSTM-AT, 1D-CNN-LSTM, GRU-LSTM, RNN-LSTM, and OGRU-LSTM are modeled to evaluate the performance of hybrid models to identify 2 classes of Raman spectral data. Comparative classification results show that the stacked 1D-CNN-GRU model outperforms well for breast cancer detection using the Raman spectral dataset than other prominent HDL architectures. The stacked 1D-CNN-GRUclassifier model achieved the highest classification accuracy (98.90 %), Cohen-kappa score (0.941), F1-score (0.969), and the lowermost number of test loss as 0.102776 and MSE (0.0230) indicating that the model outperforms other HDL classifiers. HIGHLIGHTS The potential of Raman spectroscopy in combination with hybrid deep learning (HDL) models to diagnose and classify cancerous or noncancerous samples, specifically blood plasma samples, based on chemical composition The implementation of data augmentation techniques to address underfitting and overfitting issues occur in the classification of spectral samples due to a lack of sufficient Raman spectral data The development of an efficient Hybrid Deep Learning (HDL) neural network model to differentiate breast cancer blood plasma from control samples and the use of spectral features as spectral cancer markers for breast cancer detection The evaluation of several HDL models for binary classification of Raman spectral signals, with the stacked 1D-CNN-GRU model achieving the highest classification accuracy and the lowest test losses The potential for this technique is to accurately classify breast cancerous samples and reduce the number of unnecessary excisional breast biopsies GRAPHICAL ABSTRACT

show abstract

Section: Related Workmentioning

confidence: 99%

A Label-Free Marker Based Breast Cancer Detection using Hybrid Deep Learning Models and Raman Spectroscopy

Selvarani

Jose

2023

Trends Sci

View full text Add to dashboard Cite

show abstract

“…This model consists of four convolutional blocks (each contains a convolutional layer, a ReLU layer, and a maxpooling layer) for feature extraction and one output layer for spectral classification. Apart from the above, a 1D CNN composed of only two convolutional layers was applied into a nanoplasmonics biosensing chip (NBC) by Cheng et al, which could correctly identify 91% of the 100 spectra on validation dataset for hepatocellular carcinoma (HCC) or healthy patients [41]. The two convolutional layers of this model are with 8 or 16 kernels of the size 3 × 1, respectively.…”

Section: Classification and Regressionmentioning

confidence: 99%

“…Examples of typical deep learning applications for Raman spectroscopy. Dong et al[37], Lee et al[38], Kirchberger-Tolstik et al[39], Maruthamuthu et al[40], Cheng et al[41], Fan et al[42], Fu et al[43], Houston et al[44], Ho et al[45], Ding et al[46], Chen et al[47], Saifuzzaman et al[48], Pan et al[49,50], Sohn et al[51], Yu et al[52], Thrift and Ragan[53], and Zhang et al[54] …”

mentioning

confidence: 99%

Deep Learning for Raman Spectroscopy: A Review

2022

View full text Add to dashboard Cite

Raman spectroscopy (RS) is a spectroscopic method which indirectly measures the vibrational states within samples. This information on vibrational states can be utilized as spectroscopic fingerprints of the sample, which, subsequently, can be used in a wide range of application scenarios to determine the chemical composition of the sample without altering it, or to predict a sample property, such as the disease state of patients. These two examples are only a small portion of the application scenarios, which range from biomedical diagnostics to material science questions. However, the Raman signal is weak and due to the label-free character of RS, the Raman data is untargeted. Therefore, the analysis of Raman spectra is challenging and machine learning based chemometric models are needed. As a subset of representation learning algorithms, deep learning (DL) has had great success in data science for the analysis of Raman spectra and photonic data in general. In this review, recent developments of DL algorithms for Raman spectroscopy and the current challenges in the application of these algorithms will be discussed.

show abstract

“…Therefore, to use the SERS signal of more complex structures as a fingerprint for disease diagnosis, more precise signal analysis methods are used such as multivariate statistical methods ( principal component analysis, "PCA"), [229][230][231][232] and the more recently developed methods of machine learning 231,233 and neural networks. 234,235 We will not discuss much about analysis techniques, focusing on the SERS platforms themselves, but the reader should take into consideration that label-free SERS analysis outcome depends 50% on data analysis tools. Label-free SERS analysis is attractive to scientists due to the rich information outcome it provides.…”

Section: Label-free Sersmentioning

confidence: 99%