Raman spectroscopy combined with deep learning for rapid detection of melanoma at the single cell level

Qiu, Xun; Wu, Xingda; Fang, Xianglin; Fu, Qiuyue; Wang, Peng; Wang, Xin; Li, Shaoxin; Liu, Ying

doi:10.1016/j.saa.2022.122029

Cited by 14 publications

(15 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolutional neural networks were constructed for classification and demonstrated an accuracy of over 98%. This study highlights the great potential of combining RS and deep learning in clinical applications ( 196 ). Studies have demonstrated that preprocessing of raw data can greatly affect the outcome of diagnosis ( 49 , 197 ).…”

Section: Discussion and Future Perspectivesmentioning

confidence: 73%

The emerging applications and advancements of Raman spectroscopy in pediatric cancers

Feng²,

Xu³

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

Although the survival rate of pediatric cancer has significantly improved, it is still an important cause of death among children. New technologies have been developed to improve the diagnosis, treatment, and prognosis of pediatric cancers. Raman spectroscopy (RS) is a non-destructive analytical technique that uses different frequencies of scattering light to characterize biological specimens. It can provide information on biological components, activities, and molecular structures. This review summarizes studies on the potential of RS in pediatric cancers. Currently, studies on the application of RS in pediatric cancers mainly focus on early diagnosis, prognosis prediction, and treatment improvement. The results of these studies showed high accuracy and specificity. In addition, the combination of RS and deep learning is discussed as a future application of RS in pediatric cancer. Studies applying RS in pediatric cancer illustrated good prospects. This review collected and analyzed the potential clinical applications of RS in pediatric cancers.

show abstract

Section: Discussion and Future Perspectivesmentioning

confidence: 73%

The emerging applications and advancements of Raman spectroscopy in pediatric cancers

Feng²,

Xu³

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…These include: 648 cm −1 (proteins), 950 cm −1 (lipids), 1158 cm −1 (proteins and carotenoids), 1182 cm −1 (DNA backbone), 1215 cm −1 (proteins), 1420 cm −1 (proteins), 1447 cm −1 (proteins and lipids), 1490 cm −1 (proteins), 1583 cm −1 (nucleic acid), and 1633 cm −1 (proteins). A summary of the tentative assignments for these Raman peaks is provided in table 1 [27,40,41,[43][44][45][46][47][48]. Upon analyzing the SERS spectra in figure 3, it can be observed that the levels of proteins and nucleic acids in tumor cells are higher compared to those in NEC.…”

Section: Sers Spectra Of Cell Samplesmentioning

confidence: 99%

“…However, the spectral differences between tumor cells and WBC are relatively minor, particularly among the three types of urinary tumor cells. Therefore, to accurately and efficiently capture the subtle spectral differences present in complex Raman spectra and enable the differentiation of different cell types via Raman spectroscopy, it becomes necessary Amide I [27] to combine advanced machine learning and deep learning algorithms.…”

Section: Sers Spectra Of Cell Samplesmentioning

confidence: 99%

“…Given the complexity, high dimensionality, and limited reproducibility of raw SERS spectral data, conventional statistical methods alone prove insufficient for data processing and feature extraction, making it challenging to discern subtle spectral distinctions in biological analytes [24][25][26]. Consequently, various machine learning approaches have been employed to automatically and efficiently analyze Raman spectra [26][27][28]. Deep learning, a powerful subset of machine learning, has demonstrated remarkable performance in this regard.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Label-free rapid detection of urinary tumor cells based on surface-enhanced Raman scattering and deep learning

Wang,

Wu,

Wang

et al. 2023

Laser Phys.

Self Cite

View full text Add to dashboard Cite

In clinical practice, the primary objective of tumor detection is to acquire comprehensive diagnostic information while minimizing invasiveness and reducing patient discomfort. Urine cytology represents a non-invasive method frequently employed for urologic tumor detection. However, its sensitivity is limited. Enhancing the accurate identification of various urologic tumor cells and blood cells is crucial to improve the sensitivity of urine cytology. Surface-enhanced Raman spectroscopy (SERS), coupled with suitable machine learning algorithms, holds significant potential for rapid, sensitive, label-free, and non-destructive detection and identification of tumor cells. In this investigation, SERS spectra of urologic tumor cells and blood cells were acquired using an ordered substrate comprising Au-wrapped nanorod arrays. Notably, a remarkably high spectral resemblance was observed among the three distinct types of urologic tumor cells. Five machine learning algorithms were implemented for cell type differentiation and prediction. Among these, the classification network system integrating spatial attention mechanism with DenseNet exhibited the highest classification performance, yielding an accuracy rate of nearly 99%. Additionally, an attention heatmap was generated to highlight the wavenumber range that contributed the most in the SERS spectra, aiding in discriminating various cell species. This study demonstrates that SERS technology based on Au-wrapped nanorod arrays, in conjunction with deep learning algorithms, can promptly and accurately differentiate normal cells from tumor cells, thereby offering an effective approach to enhance the sensitivity of urine cytology tests.

show abstract

“…As reported in [16], deep learning (DL), SVM, and extreme gradient boosting trees were used with Raman spectroscopy to determine tumor markers for colon cancer. In addition, the combination of DL and Raman spectroscopy allows rapid detection of melanoma at the single cell level [17].…”

Section: Introductionmentioning

confidence: 99%

Using random forest for brain tissue identification by Raman spectroscopy

Zhang,

Giang,

Cai

et al. 2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

The traditional definitive diagnosis of brain tumors is performed by needle biopsy under the guidance of imaging-based exams. This paradigm is based on the experience of radiogolists, and accuracy could be affected by uncertainty in imaging interpretation and needle placement. Raman spectroscopy has the potential to improve needle biopsy by providing fingerprints of different materials and performing in situ tissue identification. In this paper, we present the development of a supervised machine learning algorithm using random forest (RF) to distinguish the Raman spectrum of different types of tissue. An integral process from raw data collection and preprocessing to model training and evaluation is presented. To illustrate the feasibility of this approach, viable animal tissues were used, including ectocinerea (grey matter), alba (white matter) and blood vessels. Raman spectra were acquired using a custom-built Raman spectrometer. The hyperparameters of the RF model were determined by combining a cross-validation-based algorithm and manually adjusting. The experimental results show the ability of our approach to discriminate different types of tissues with high accuracy.

show abstract

Raman spectroscopy combined with deep learning for rapid detection of melanoma at the single cell level

Cited by 14 publications

References 34 publications

The emerging applications and advancements of Raman spectroscopy in pediatric cancers

The emerging applications and advancements of Raman spectroscopy in pediatric cancers

Label-free rapid detection of urinary tumor cells based on surface-enhanced Raman scattering and deep learning

Using random forest for brain tissue identification by Raman spectroscopy

Contact Info

Product

Resources

About