Deep convolutional neural networks for tongue squamous cell carcinoma classification using Raman spectroscopy

Yu, Mingxin; Hu, Yan; Xia, Jiabin; Zhu, Lianqing; Zhang, Tao; Zhu, Zhihui; Lou, Xiaoping; Sun, Greg; Dong, Mingli

doi:10.1016/j.pdpdt.2019.05.008

Cited by 56 publications

(51 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is thus advantageous to apply deep neural networks for the analysis of vibrational spectra, which are a complex superposition of all vibrational information within the sample. Applications of deep learning were reported for both infrared and Raman spectroscopy in order to achieve tasks like brain function investigations , biological diagnostics , cytopathology , microbial identification , pathogenic bacteria identification , food science investigations , tobacco leaves characterization and mineral analysis . Furthermore, it was reported in references that deep learning can perform better than classical machine learning methods .…”

Section: Deep Learning For Vibrational Spectroscopymentioning

confidence: 99%

Deep learning a boon for biophotonics?

Pradhan

Guo

Ryabchykov

et al. 2020

Journal of Biophotonics

View full text Add to dashboard Cite

This review covers original articles using deep learning in the biophotonic field published in the last years. In these years deep learning, which is a subset of machine learning mostly based on artificial neural network geometries, was applied to a number of biophotonic tasks and has achieved state-of-the-art performances. Therefore, deep learning in the biophotonic field is rapidly growing and it will be utilized in the next years to obtain real-time biophotonic decision-making systems and to analyze biophotonic data in general. In this contribution, we discuss the possibilities of deep learning in the biophotonic field including image classification, segmentation, registration, pseudostaining and resolution enhancement. Additionally, we discuss the potential use of deep learning for spectroscopic data including spectral data preprocessing and spectral classification. We conclude this review by addressing the potential applications and challenges of using deep learning for biophotonic data.

show abstract

Section: Deep Learning For Vibrational Spectroscopymentioning

confidence: 99%

Deep learning a boon for biophotonics?

Pradhan

Guo

Ryabchykov

et al. 2020

Journal of Biophotonics

View full text Add to dashboard Cite

show abstract

“…Among the 38 studies in the oral cancer group, 5 [33,53,54,56,60] studies evaluated in vivo tissue, whereas 33 [1,[21][22][23][24][25][26][27][28][29][30][31][32][34][35][36][37][38][39][40][41][42][43][44][45][49][50][51][52]55,[57][58][59] studies evaluated in vitro samples. in vitro samples can be categorized as tissues (n = 13), [1,21,22,24,26,27,30,39,[43][44][45]50,55] bio fluids (n = 15),…”

Section: Description Of Studies Included In the Reviewmentioning

confidence: 99%

“…in vitro samples can be categorized as tissues (n = 13), [1,21,22,24,26,27,30,39,[43][44][45]50,55] bio fluids (n = 15), [23,25,31,32,[35][36][37][40][41][42]49,51,[57][58][59] and exfoliated cells (n = 6), [25,28,29,34,38,52] and the tissue group can be divided into a fresh tissue group (n = 5), [21,22,30,45,55] frozen tissue group (n = 7), [1,24,26,27,39,44,50] and dehydrated tissue group (n = 1) [43] (one study [25] had subgroups). A variety of diagnostic algorithms were used to analyze the RS results; most studies used principal component analysis (PCA) and linear discriminate analysis (LDA; n = 14)…”

Section: Description Of Studies Included In the Reviewmentioning

confidence: 99%

“…Of the 38 studies that were identified through our search and included in the oral cancer group, 13 [26,27,33,35,37,[52][53][54][56][57][58][59][60] had an overall quality score of 11 (78.6% YES rate), and 15 [21,22,25,30,34,36,38,41,42,44,45,[49][50][51]55] had a score of 10 (71.4% YES rate). In addition, 10 [1,23,24,28,29,31,32,39,41,43] studies scored only a 9 (64.3% YES rate).…”

Section: Assessment Of Study Qualitymentioning

confidence: 99%

See 1 more Smart Citation

The accuracy of Raman spectroscopy in the detection and diagnosis of oral cancer: A systematic review and meta‐analysis

Zhan

Yuan

et al. 2020

J Raman Spectroscopy

View full text Add to dashboard Cite

The aim of this study was to systematically review and assess the diagnostic accuracy of Raman spectroscopy (RS) for oral cancer tissue, oral precancerous lesions, and normal oral tissue. Methods: PubMed, Embase, Web of Science, the China National Knowledge Infrastructure, and gray literature were searched for all relevant articles published before July 2019. We used the Quality Assessment of Diagnostic Accuracy Studies tool to assess the quality of the included studies. We estimated the pooled sensitivity, specificity, positive and negative likelihood ratios (PLR and NLR), diagnostic odds ratio (DOR), and established summary receiver operating characteristic (SROC) curves to identify the diagnostic accuracy of RS for oral cancer tissue, oral precancerous lesions, and normal oral tissue. In addition, the area under the curve (AUC) was reported to estimate the overall effectiveness of RS. Results: A total of 41 articles were eligible for this meta-analysis. The coalescent sensitivity and specificity of RS in diagnosing oral cancer in vivo were 0.91 and 0.85. The positive likelihood ratio, the negative likelihood ratio, and the area under the curve were 8.01, 0.10, and 0.9284. The frozen tissue subgroup in vitro oral cancer group showed improved diagnostic accuracy with an AUC of 0.9968. The in vitro frozen tissue group also showed better diagnostic accuracy in distinguishing between oral precancerous lesions and normal oral tissues. Conclusions: RS has the advantages of being noninvasive and able to provide real-time and in situ results, so it deserves to be studied and improved further to better serve clinical work. K E Y W O R D S diagnosis, meta-analysis, oral cancer, oral precancerous lesion, Raman spectroscopy 1 | INTRODUCTION Oral cancer, a type of head and neck cancer, is a generic term for malignant tumors that occur in the mouth, most † These authors contributed equally to this work.

show abstract

“…Therefore, the accuracy of tumor tissue recognition is improved. In our previous article [45,46], the data we collected was only from 12 people in total, with a total of 24 tissues, and the spectral range was only 600-1800 cm -1 . In this experiment, 22 patients were obtained, a total of 44 organizations, a significant increase compared to the previous data size.…”

Section: Introductionmentioning

confidence: 99%

Diverse Region-Based CNN for Tongue Squamous Cell Carcinoma Classification With Raman Spectroscopy

Xia

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Border discrimination is very important in the treatment of tongue squamous cell carcinoma (TSCC). This study proposes an ensemble convolutional neural network (CNN) framework based on fiber optic Raman spectroscopy and deep learning techniques to distinguish between TSCC and non-tumor tissue frameworks. First, the data used in the experiments was collected by a fiber optic Raman system. A total of 44 tissues of 22 patients were collected for Raman spectroscopy, with TSCC and adjacent normal tissues each accounting for half. The spectral data range used in the model from a full spectrum of 600-4000 cm-1. Then, the ensemble CNN model was used in the experiment. By using two convolution kernels, the model is able to extract nonlinear feature representations from different spectral regions. It has two advantages, on the one hand, it reduces the generation of noise, on the other hand, it obtains a stronger distinguishing ability. Finally, a feature vector is formed by the fusion layer, and is sent to the fully connected layer for the TSCC classification task. The results showed that the sensitivity and specificity of the model were 99.2% and 99.2%, respectively. In addition, comparison with existing methods shows that our method achieves the highest accuracy of TSCC classification. By comparing the different channels, the results show that the spectral range of 1380-2250cm-1 data has the greatest impact on the results. Therefore, Raman spectroscopy combined with the ensemble CNN model has great potential and can provide a useful technique for intraoperative evaluation of the margins of oral tongue squamous cell carcinoma.

show abstract

Deep convolutional neural networks for tongue squamous cell carcinoma classification using Raman spectroscopy

Cited by 56 publications

References 29 publications

Deep learning a boon for biophotonics?

Deep learning a boon for biophotonics?

The accuracy of Raman spectroscopy in the detection and diagnosis of oral cancer: A systematic review and meta‐analysis

Diverse Region-Based CNN for Tongue Squamous Cell Carcinoma Classification With Raman Spectroscopy

Contact Info

Product

Resources

About