|
|
|
|
|
|
| Diagnostic Method for Brain Glioma Grading Based on Convolutional Neural Networks and Raman Spectroscopy |
| XU Qing1, TANG Jia-wei2, LIU Xue-meng3, GUO Jing-xing4, ZHU Li-jun1, ZHOU Qing-qing1, WANG Liang2, LU Guang-ming1* |
1. Department of Radiology, Nanjing Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing 210002, China
2. Laboratory Medicine, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou 510000, China
3. Department of Neurosurgery, Qilu Hospital, Cheeloo College of Medicine and Institute of Brain and Brain-Inspired Science, Shandong University, Jinan 250012, China
4. School of Chemistry, Chemical Engineering and Life Sciences, Wuhan University of Technology, Wuhan 430000, China
|
|
|
|
|
Abstract Gliomas are the most common primary tumors of the central nervous system, and their pathological grading plays a critical role in guiding treatment decisions and prognostic evaluation. In this study, we retrospectively collected data from 53 patients who underwent glioma surgery at the Eastern Theater General Hospital between January 2023 and January 2024. Among these, 33 cases were high-grade gliomas, and 20 were low-grade gliomas. Raman spectral data of tumor tissue samples were obtained using the InVia laser confocal Raman spectrometer (UK), with 50 points collected for each sample. The spectral data were preprocessed using various methods, including the Savitzky-Golay (SG) algorithm, spectral curve smoothing, and min-max normalization. A convolutional neural network (CNN) was developed to classify gliomas into high- and low-grade categories, and its performance was compared with traditional machine learning models, including support vector machines (SVM), random forests (RF), and decision trees (DT). Each predictive model was evaluated using receiver operating characteristic (ROC) curves, and four key metrics- accuracy, precision, recall, and five-fold cross-validation- were employed to assess model performance. Experimental results demonstrated that the CNN model significantly outperformed the SVM, RF, and DT models in various classification tasks, achieving an area under the curve (AUC) of 0.983 9, compared to 0.915 7 for SVM, 0.903 1 for RF, and 0.780 9 for DT. These findings suggest that integrating Raman spectroscopy with deep learning techniques offers an innovative approach to the grading diagnosis of gliomas. This method improves diagnostic accuracy and efficiency and lays a solid foundation for the future development of automated cancer diagnostic systems.
|
|
Received: 2024-11-23
Accepted: 2025-03-06
|
|
|
|
Corresponding Authors:
LU Guang-ming
E-mail: cjr.luguangming@vip.163.com
|
|
[1] Uddin M S, Al Mamun A, Alghamdi B S, et al. Semin Cancer Biol, 2022, 83: 100.
[2] Louis D N, Perry A, Wesseling P, et al. Neuro Oncol, 2021, 23: 1231.
[3] Ren X Q, Zhang Q W, Yang J L, et al. Anal. Chem., 2021, 93: 10841.
[4] Rickard J J S, Di-Pietro V, Smith D J, et al. Nature Biomedical Engineering, 2020, 4: 610.
[5] ZHOU Qing-qing, GUO Jing-xing, XU Qing, et al(周清清, 郭景星, 许 晴, 等). Chin. J. Nucl. Med. Mol. Imaging(中华核医学与分子影像杂志), 2023, 43(9): 566.
[6] Tang J W, Li F, Liu X, et al. Lab Invest., 2023, 104: 100310.
[7] Liu M Y, Mu J, Gong W, et al. ACS Chem Neurosci, 2022, 14(1): 159
[8] Yang J, Xu J F, Zhang X L, et al. Anal. Chim. Acta, 2019, 1081: 6.
[9] Usman M, Tang J W, Li F, et al. J. Adv. Res., 2023, 51: 91.
[10] Hollon T, Golfinos J, Orringer D, et al. Nat. Med., 2023, 29: 828.
[11] Zhang L, Zhou Y, Wu B L, et al. Cancers (Basel), 2023, 15: 1752.
[12] Zhong C H, Tao B, Tang F L, et al. Theranostics, 2021, 11: 1991.
[13] Aftab Q, Mesnil M, Ojefua E, et al. Frontiers in Neuroscience, 2019, 13: 143.
[14] Cheng X, Geng F, Pan M X, et al. Cell Metabolism, 2020, 32(2): 229.
[15] Geng F, Cheng X, Wu X N, et al. Clin. Cancer Res., 2016, 22: 5337.
|
| [1] |
CHEN Xin-gang1, 2, AO Yi1, ZHANG Zhi-xian1*, MA Zhi-peng1, ZHANG Wen-xuan1, WAN Fu3, KUANG Lu1, LUO Bo-wen1. Raman Spectroscopic Detection of the Aging State of Oil-Paper Insulation in Combined Diffusion-Based WGANGP Transformers[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(08): 2164-2173. |
| [2] |
HUANG Tian-yu1, YANG Hui-hua1, 2, LI Ling-qiao1*. InvertResNet: A Qualitative Analysis Method for Drug Products Based on Deep Learning and Near-Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(08): 2218-2227. |
| [3] |
WANG Shu-dong1*, ZHENG Xuan1, TIAN Ren-kui2 , ZHANG Yan1*, WU Jing-jie1*. Identification and Raman Spectroscopy Characteristics Analysis of the New Psychoactive Substances Etomidate and Its Analogs[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(08): 2241-2246. |
| [4] |
WANG Feng-chan1, NIU Lu1, YE Hai-yan1, FU Xiao-ting2, DAI Jing2, LI Yuan-dong2, HU Hai-bo1, LU Xue-chao1*. Study on Rapid Antimicrobial Susceptibility Test of Pseudomonas Aeruginosa by D2O-Labeled Single-Cell Raman Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(08): 2253-2258. |
| [5] |
LU Yang1*, GU Fu-qian1, GU Ying-nan2*, XU Si-yuan1, WANG Peng3, 4. Early Detection of Northern Corn Leaf Blight Using Hyperspectral Images Combined With One-Dimensional Convolutional Neural Networks[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(08): 2302-2310. |
| [6] |
WU Shu-lei1, 2, ZHANG Jia-tian1, 2, WANG Jia-jun2, DANG Shi-jie2, ZHAO Ling-xiao2, CHEN Yi-bo2*. Pathogenic Bacteria Raman Spectrum Classification Method Based on
Diffusion Kernel Attention[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(07): 1940-1945. |
| [7] |
MA Yao-an1, HUANG Yu-ting1, ZHANG Jian-hao1, QU Dong-ming1, HU Bei-bei2, LIU Bi-ye2, YANG Guang1, SUN Hui-hui1*. K-Means-CNN-Based Classification Study of Mixed Alloy Samples of Complex Grades[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(07): 1946-1952. |
| [8] |
JIANG Yi1, PAN Jiao1, DUAN Hong-ying2*. The Scientific Analysis of Materials of Polychrome Paintings From
Northeast Chonglou of the Forbidden City[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(07): 1953-1960. |
| [9] |
CHEN Bei, JIANG Si-yuan, ZHENG En-rang. Research on the Wavelength Attention 1DCNN Algorithm for Quantitative Analysis of Near-Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(06): 1598-1604. |
| [10] |
XU De-fang1, GUAN Hong-pu2, ZHAO Hua-min3, ZHANG Shu-juan3, ZHAO Yan-ru2*. Early Detection Method of Mechanical Damage of Yuluxiang Pear Based on SERS and Deep Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(06): 1712-1718. |
| [11] |
LI Wen1, LUO Cheng-kui1*, CHEN Shi-heng2*, JIN Hao-shu2, LI Jie1, LI Yi-bo1. Rapid Quantitative Analysis of Acidic Ions in In-Situ Leaching Solution Using Cavity-Enhanced Raman Spectrometry[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(06): 1744-1751. |
| [12] |
PENG Jian-heng1, HU Xin-jun1, 2*, ZHANG Jia-hong1, TIAN Jian-ping1, CHEN Man-jiao1, HUANG Dan2, LUO Hui-bo2. Identification and Adulteration Detection of Lotus Root Starch Using
Hyperspectral Imaging Technology Combined With Deep Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(06): 1759-1767. |
| [13] |
GAO Fei1, 2, LIN Wan1, JIA Zhe1, BAI Qi-hui1, LIU Jing1, WANG Yi-fan1, LI Wei-ying3. Spectroscopic Study on the Evolution of Coal Molecular Structure During CO2 Storage[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(06): 1791-1800. |
| [14] |
JIANG Heng1, LÜ Zi-wei1, LI Yang2, DONG Tuo1*. A Novel Strategy for Viral Detection in Acute Respiratory Infections: Combining SERS With Machine Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(05): 1217-1224. |
| [15] |
GUAN Li-chang1, 2, FENG Lei2, 3, ZHAO Nan1*, JIANG Xue-mei2*. Study of Fenfluramine Molecule Based on the Density Functional Theory[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(05): 1270-1276. |
|
|
|
|
