Serum Raman spectroscopy combined with a multi-feature fusion convolutional neural network diagnosing thyroid dysfunction
| Autor: | Dongni Tong, Xiaoyi Lv, Hongmei Li, Zhiqi Guo, Hao Chen, Rumeng Si, Chen Chen, Hongyi Li, Cheng Chen, Huicheng Lai, Hang Wang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
Decision tree 02 engineering and technology 01 natural sciences Convolutional neural network 010309 optics symbols.namesake Thyroid dysfunction 0103 physical sciences Electrical and Electronic Engineering business.industry Deep learning Pattern recognition 021001 nanoscience & nanotechnology Serum samples Atomic and Molecular Physics and Optics Normal thyroid function Electronic Optical and Magnetic Materials Support vector machine Statistical classification Multi feature fusion symbols Artificial intelligence 0210 nano-technology business Raman spectroscopy |
| Zdroj: | Optik. 216:164961 |
| ISSN: | 0030-4026 |
| DOI: | 10.1016/j.ijleo.2020.164961 |
| Popis: | In this study, serum samples from 199 patients with thyroid dysfunction and 183 people with normal thyroid function were collected by Raman spectroscopy, and the data were dimensions-reduced by PCA. The reduced data were input into a multi-feature fusion convolutional neural network (MCNN), the improved AlexNet, VGGNet, GoogLeNet and ResNet, Support Vector Machine (SVM) and Decision Tree (DT) for classification, and the results of the seven classification algorithms were compared. Their classification accuracy are 94.01 %, 91.91 %, 90.34 %, 93.46 %, 92.42 %, 82.78 % and 80.89 %, respectively. The results of this study indicate that the combination of serum Raman spectra and MCNN has a good diagnostic effect for identifying thyroid dysfunction, and it is feasible to improve the classic deep learning models for Raman spectrum classification. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect