ABSTRACT
Molecular vibrational spectroscopy is an essential technique for analyzing the biomolecular components of human tissues and body fluids with high sensitivity. There are many studies on tumor disease diagnosis that combine artificial intelligence with vibrational spectroscopy, and vibrational spectroscopy has shown good potential in non-invasive disease auxiliary diagnosis. However, the complexity of spectral data processing flow and the variety of algorithms make it difficult for non-professionals to use it efficiently, which limits the development of molecular vibrational spectroscopy-assisted diagnosis technology. This study developed the Spectral Data Processing Platform (SDPP) that normalizes the data processing flow. SDPP can quickly perform preprocessing, feature extraction, and model building on spectral data. As an application desktop program, SDPP has an executable file size of 232 M, an average response time of 3 s for each component, an average CPU utilization rate of 7.30%, and a throughput of 106 times/s. The experimental data selected for testing the platform were collected from Raman data and infrared data of patients and the control group. The results showed that SDPP could efficiently classify patients and the control group and also proved the stability and operability of SDPP.
- Y. Liu, Z. Wang, Z. Zhou, T. Xiong, Analysis and comparison of machine learning methods for blood identification using single-cell laser tweezer Raman spectroscopy, Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2022.Google ScholarCross Ref
- M. Kopec, H. Abramczyk, The role of pro- and antiangiogenic factors in angiogenesis process by Raman spectroscopy, Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 268. 2022. 120667.Google ScholarCross Ref
- M. Mittal, S. Gupta, A.S. Rathore, Raman spectroscopy as process analytical technology tool for monitoring atomic layer deposition. ALD) of drug particles, Materials Chemistry and Physics 282. 2022.Google Scholar
- J. Xie, F. Yang, H. Shi, J. Yan, H. Shen, S. Yu, N. Gan, B. Feng, L. Wang, Protein FT-IR amide bands are beneficial to bacterial typing, International Journal of Biological Macromolecules 207. 2022. 358-364.Google ScholarCross Ref
- T. Lilo, C.L.M. Morais, C. Shenton, A. Ray, N. Gurusinghe, Revising Fourier-transform infrared (FT-IR) and Raman spectroscopy towards brain cancer detection, Photodiagnosis and Photodynamic Therapy 38. 2022. 102785.Google ScholarCross Ref
- K. Liu, Q. Zhao, B. Li, X. Zhao, Raman Spectroscopy: A Novel Technology for Gastric Cancer Diagnosis, frontiers in Bioengineering and Biotechnology 10. 2022. 856591.Google Scholar
- J. Ingham, M.J. Pilling, D.S. Martin, C.I. Smith, B.G. Ellis, C.A. Whitley, M.R.F. Siggel-King, P. Harrison, T. Craig, A. Varro, D.M. Pritchard, A. Varga, P. Gardner, P. Weightman, S. Barrett, A novel FTIR analysis method for rapid high-confidence discrimination of esophageal cancer, Infrared Physics & Technology 102. 2019.Google ScholarCross Ref
- S.S. Nazeer, T.P. Sreedevi, R.S. Jayasree, Autofluorescence spectroscopy and multivariate analysis for predicting the induced damages to other organs due to liver fibrosis, Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 257. 2021. 119741.Google ScholarCross Ref
- N. Iturrioz-Rodriguez, D. De Pasquale, P. Fiaschi, G. Ciofani, Discrimination of glioma patient-derived cells from healthy astrocytes by exploiting Raman spectroscopy, Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 269. 2022. 120773.Google ScholarCross Ref
- T. Tuncer, F. Ertam, Neighborhood component analysis and reliefF based survival recognition methods for Hepatocellular carcinoma, Physica A: Statistical Mechanics and its Applications 540. 2020.Google ScholarCross Ref
- F. Chen, C. Meng, H. Qu, C. Cheng, C. Chen, B. Yang, R. Gao, X. Lv, Human serum mid-infrared spectroscopy combined with machine learning algorithms for rapid detection of gliomas, Photodiagnosis and Photodynamic Therapy 35. 2021. 102308.Google ScholarCross Ref
- H. Qu, W. Wu, C. Chen, Z. Yan, W. Guo, C. Meng, X. Lv, F. Chen, C. Chen, Application of serum mid-infrared spectroscopy combined with an ensemble learning method in rapid diagnosis of gliomas, Analytical Methods 13(39). 2021. 4642-4651.Google ScholarCross Ref
- Q. Wu, C. Li, Z. Qi, L. Zong, C. Hu, J. Li, X. Wang, Comparison of hair medulla from esophageal cancer patients and healthy persons using synchrotron radiation infrared microspectroscopy, Infrared Physics & Technology 105. 2020.Google ScholarCross Ref
- Z. Zhu, C. Chen, C. Chen, Z. Yan, F. Chen, B. Yang, H. Zhang, H. Han, X. Lv, Prediction of tumor size in patients with invasive ductal carcinoma using FT-IR spectroscopy combined with chemometrics: a preliminary study, Analytical and Bioanalytical Chemistry 413(12). 2021. 3209-3222.Google ScholarCross Ref
- B. Curto, V. Moreno, J.A. Garcia-Esteban, F.J. Blanco, I. Gonzalez, A. Vivar, I. Revilla, Accurate Prediction of Sensory Attributes of Cheese Using Near-Infrared Spectroscopy Based on Artificial Neural Network, Sensors (Basel) 20(12). 2020.Google ScholarCross Ref
- J. Geng, W. Zhang, C. Chen, H. Zhang, A. Zhou, Y. Huang, Tracking the Differentiation Status of Human Neural Stem Cells through Label-Free Raman Spectroscopy and Machine Learning-Based Analysis, Analytical Chemistry 93(30). 2021. 10453-10461.Google ScholarCross Ref
- F. Yue, C. Chen, Z. Yan, C. Chen, Z. Guo, Z. Zhang, Z. Chen, F. Zhang, X. Lv, Fourier transform infrared spectroscopy combined with deep learning and data enhancement for quick diagnosis of abnormal thyroid function, Photodiagnosis and Photodynamic Therapy 32. 2020. 101923.Google ScholarCross Ref
- D. Wang, F. Tian, S.X. Yang, Z. Zhu, D. Jiang, B. Cai, Improved Deep CNN with Parameter Initialization for Data Analysis of Near-Infrared Spectroscopy Sensors, Sensors (Basel) 20(3). 2020.Google ScholarCross Ref
- W. Wu, S. Huang, X. Xie, C. Chen, Z. Yan, X. Lv, Y. Fan, C. Chen, F. Yue, B. Yang, Raman spectroscopy may allow rapid noninvasive screening of keratitis and conjunctivitis, Photodiagnosis and Photodynamic Therapy 37. 2022. 102689.Google ScholarCross Ref
- L.B. Tuan, ., D. Xiao, Y. Mao, L. Song, D. He, S. Liu, Coal Classification Based on Visible, Near-Infrared Spectroscopy and CNN-ELM Algorithm., Spectropy and Spectral Analysis 38. 2018.Google Scholar
- A. Sherstinsky, Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network, Physica D: Nonlinear Phenomena 404. 2020.Google ScholarCross Ref
- C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, Going Deeper with Convolutions, 2014, p. arXiv:1409.4842.Google Scholar
- K. He, X. Zhang, S. Ren, J. Sun, Deep Residual Learning for Image Recognition, 2015, p. arXiv:1512.03385.Google Scholar
Index Terms
- SDPP: A tumor disease diagnosis application based on vibration spectroscopy and machine learning
Recommendations
A Disease Diagnosis Method Based on Machine Learning
ICIIP '18: Proceedings of the 3rd International Conference on Intelligent Information ProcessingFor the problem of low accuracy of intelligent medical diagnosis, this paper designs a secondary diagnosis model based on machine learning. First diagnosis using softmax regression model. It will conduct a diagnosis of major disease classification, ...
Research and Application of Animal Disease Intelligent Diagnosis Based on Support Vector Machine
CIS '09: Proceedings of the 2009 International Conference on Computational Intelligence and Security - Volume 02Diagnosing animal disease quickly and accurately has the economic effectiveness. But livestock breeding farms usually have relatively poor condition of disease diagnosis and animal disease cannot be diagnosed quickly and accurately. Traditional ...
An application of machine learning in the diagnosis of ischaemic heart disease
CBMS '97: Proceedings of the 10th IEEE Symposium on Computer-Based Medical Systems (CBMS '97)Ischaemic heart disease is one of the world's most important causes of mortality, so improvements and rationalization of diagnostic procedures would be very useful. The four diagnostic levels consist of evaluation of signs and symptoms of the disease ...
Comments