Prediction of EGFR Amplification Status of Glioma Based on Terahertz Spectral Data With Convolutional Neural Networks
ZHAO Xiao-yan1*, ZHENG Shao-wen1, WU Xian-hao1, SUN Zhi-yan2, 3, TAO Rui2, 3, ZHANG Tian-yao1, YUAN Yuan1, LIU Xing4, ZHOU Da-biao2, 3, ZHANG Zhao-hui1, YANG Pei2, 3*
1. School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China
2. Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing 100069, China
3. Department of Neurosurgery, Beijing Neurosurgical Institute, Capital Medical University, Beijing 100069, China
4. Department of Pathology, Beijing Tiantan Hospital, Capital Medical University, Beijing 100069, China
Abstract：Gliomas are the most common primary central nervous system tumors with high invasiveness. Glioblastoma (GBM) is the most malignant type of brain glioma, with a 5-year survival rate of only 5.6%. The epidermal growth factor receptor (EGFR) plays an important role in the growth, invasion, and recurrence of glioblastoma. EGFR amplification and mutation have been identified as driving factors in glioblastoma. Currently, the integrated diagnosis process for glioma is limited by complex experimental procedures, often with a certain lag, and results can only be obtained approximately 2 weeks after surgery, which does not provide real-time molecular pathological information support for the operator. This article proposes a method for predicting EGFR amplification status based on intraoperative pathological frozen sections using terahertz time-domain spectroscopy (THz-TDS) data combined with convolutional neural networks (CNN). During the operation, spectral data of frozen sections of brain gliomas were collected using the THz-TDS system, and their absorption coefficients were calculated. After smoothing using the Savitzky-Golay filter, the absorption coefficients were converted into two-dimensional image data using the Gram Angular Field (GAF), Markov Transition Field (MTF), and Recursive Plots (RP) as inputs for subsequent CNN models. To fully utilize image data, we employ various methods, including single-image input, front-end fusion, and mid-range fusion, to construct CNN models. By comparing and analyzing the Area Under the Curve (AUC) values of Receiver Operating Characteristic (ROC) curves under different models, it was found that the Mid range Fusion Convolutional Neural Network model with Gram Angular Summation Field (GASF) and Gram Angular Difference Field (GADF) had the best prediction performance, with a predicted AUC value of 94.74% in the test set. In addition, the commonly used prediction models based on terahertz spectral data often -employ one-dimensional spectral data for dimensionality reduction and machine learning analysis, which may result in partial loss of data information during processing. Therefore, we also trained and tested the method of combining the absorption coefficient with machine learning. By comparing the results of different models for one-dimensional data and two-dimensional images, it is found that training models with two-dimensional spectral images in convolutional neural networks yields better predictive performance compared to machine learning with one-dimensional terahertz time-domain spectral data. The experimental results -demonstrate that the proposed method, based on terahertz spectroscopy data and a convolutional neural network model, can achieve real-time and rapid prediction of EGFR amplification status, providing new insights for molecular pathological classification of brain gliomas using terahertz time-domain spectroscopy. It is of great significance for the timely adjustment of surgical strategies during surgery and the early development of postoperative adjuvant treatment plans.
赵小燕，郑绍文，吴先毫，孙志延，陶 锐，张天尧，袁 媛，刘 幸，周大彪，张朝晖，杨 沛. 基于太赫兹光谱数据和卷积神经网络的脑胶质瘤EGFR扩增状态预测[J]. 光谱学与光谱分析, 2025, 45(10): 2856-2862.
ZHAO Xiao-yan, ZHENG Shao-wen, WU Xian-hao, SUN Zhi-yan, TAO Rui, ZHANG Tian-yao, YUAN Yuan, LIU Xing, ZHOU Da-biao, ZHANG Zhao-hui, YANG Pei. Prediction of EGFR Amplification Status of Glioma Based on Terahertz Spectral Data With Convolutional Neural Networks. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(10): 2856-2862.
[1] Rasmussen B K, Hansen S, Laursen R J, et al. J. Neuro-Oncol, 2017, 135(3): 571.
[2] Louis D N, Perry A, Wesseling P, et al. Neuro-Oncology, 2021, 23(8): 1231.
[3] Luo C, Xu S, Dai G, et al. Biomedicine and Pharmacotherapy, 2020, 127: 110193.
[4] Zhang A S, Ostrom Q T, Kruchko C, et al. Neuro-Oncology, 2017, 19(5): 726.
[5] Ruan M, Sun L Y, Qiu W, et al. Bosnian Journal of Basic Medical Sciences, 2022, 22(4): 553.
[6] Song X, Liu Z Y, Yu Z Y. Cancer Management and Research, 2020, 12: 703.
[7] Liu Y, Li Z J, Zhang M L, et al. Neuro-Oncology, 2021, 23(5): 743.
[8] Ha T, Yoo D, Heo C, et al. Nano Letters, 2022, 22(24): 10200.
[9] Gong A P, Qiu Y T, Chen X W, et al. Applied Spectroscopy Reviews, 2020, 55(5): 418.
[10] Zaytsev K I, Dolganova I N, Chernomyrdin N V, et al. Journal of Optics, 2020, 22(1): 013001.
[11] Smolyanskaya O A, Chernomyrdin N V, Konovko A A, et al. Progress in Quantum Electronics, 2018, 62: 1.
[12] Cherkasova O, Vrazhnov D, Knyazkova A, et al. Applied Sciences-Basel, 2023, 13(9): 5434.
[13] Vrazhnov D A, Ovchinnikova D A, Kabanova T V, et al. Applied Sciences-Basel, 2024, 14(7): 2872.
[14] Kistenev Y V, Teteneva A V, Sorokina T V, et al. Optics and Spectroscopy, 2020, 128(6): 809.
[15] Cao Y, Huang P, Chen J, et al. Biomedical Optics Express, 2020, 11(2): 982.
[16] Huang P, Cao Y, Chen J, et al. Optics Express, 2019, 27(18): 26014.
[17] Sun Z, Wu X, Tao R, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2023, 295: 122629.
[18] Wu X, Tao R, Sun Z, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2024, 316: 124351.
[19] Liu Y, Pu H, Li Q, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2023, 286: 122035.
[20] Kim S I, Park D W, Kim H S, et al. Journal of the Korean Society for Nondestructive Testing, 2022, 42(2): 129.
[21] Wang B, Qin X, Meng K, et al. Nanomaterials, 2022, 12(12): 2114.
[22] Wu X, Tao R, Zhang T, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2023, 285: 121933.
[23] ZHANG Tian-yao, ZHANG Zhao-hui, ZHAO Xiao-yan, et al（张天尧，张朝晖，赵小燕，等）. Spectroscopy and Spectral Analysis（光谱学与光谱分析）, 2021, 41(6): 1688.
[24] Zhou Y, Long X, Sun M, et al. Mathematical Biosciences and Engineering, 2022, 19(12): 14086.
[25] Wang M, Wang W, Zhang X, et al. Entropy, 2022, 24(6): 751.
[26] Mathunjwa B M, Lin Y T, Lin C H, et al. Biomedical Signal Processing and Control, 2021, 64: 102262.
