TY - JOUR
T1 - Multi-branch attention Raman network and surface-enhanced Raman spectroscopy for the classification of neurological disorders
AU - Xiong, Changchun
AU - Zhong, Qingshan
AU - Yan, Denghui
AU - Zhang, Baihua
AU - Yao, Yudong
AU - Qian, Wei
AU - Zheng, Chengying
AU - Mei, Xi
AU - Zhu, Shanshan
N1 - Publisher Copyright:
© 2024 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.
PY - 2024/6/1
Y1 - 2024/6/1
N2 - Surface-enhanced Raman spectroscopy (SERS), a rapid, low-cost, non-invasive, ultrasensitive, and label-free technique, has been widely used in-situ and ex-situ biomedical diagnostics questions. However, analyzing and interpreting the untargeted spectral data remains challenging due to the difficulty of designing an optimal data pre-processing and modelling procedure. In this paper, we propose a Multi-branch Attention Raman Network (MBA-RamanNet) with a multi-branch attention module, including the convolutional block attention module (CBAM) branch, deep convolution module (DCM) branch, and branch weights, to extract more global and local information of characteristic Raman peaks which are more distinctive for classification tasks. CBAM, including channel and spatial aspects, is adopted to enhance the distinctive global information on Raman peaks. DCM is used to supplement local information of Raman peaks. Autonomously trained branch weights are applied to fuse the features of each branch, thereby optimizing the global and local information of the characteristic Raman peaks for identifying diseases. Extensive experiments are performed for two different neurological disorders classification tasks via untargeted serum SERS data. The results demonstrate that MBA-RamanNet outperforms commonly used CNN methods with an accuracy of 88.24% for the classification of healthy controls, mild cognitive impairment, Alzheimer’s disease, and Non-Alzheimer’s dementia; an accuracy of 90% for the classification of healthy controls, elderly depression, and elderly anxiety.
AB - Surface-enhanced Raman spectroscopy (SERS), a rapid, low-cost, non-invasive, ultrasensitive, and label-free technique, has been widely used in-situ and ex-situ biomedical diagnostics questions. However, analyzing and interpreting the untargeted spectral data remains challenging due to the difficulty of designing an optimal data pre-processing and modelling procedure. In this paper, we propose a Multi-branch Attention Raman Network (MBA-RamanNet) with a multi-branch attention module, including the convolutional block attention module (CBAM) branch, deep convolution module (DCM) branch, and branch weights, to extract more global and local information of characteristic Raman peaks which are more distinctive for classification tasks. CBAM, including channel and spatial aspects, is adopted to enhance the distinctive global information on Raman peaks. DCM is used to supplement local information of Raman peaks. Autonomously trained branch weights are applied to fuse the features of each branch, thereby optimizing the global and local information of the characteristic Raman peaks for identifying diseases. Extensive experiments are performed for two different neurological disorders classification tasks via untargeted serum SERS data. The results demonstrate that MBA-RamanNet outperforms commonly used CNN methods with an accuracy of 88.24% for the classification of healthy controls, mild cognitive impairment, Alzheimer’s disease, and Non-Alzheimer’s dementia; an accuracy of 90% for the classification of healthy controls, elderly depression, and elderly anxiety.
UR - http://www.scopus.com/inward/record.url?scp=85195076202&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85195076202&partnerID=8YFLogxK
U2 - 10.1364/BOE.514196
DO - 10.1364/BOE.514196
M3 - Article
AN - SCOPUS:85195076202
VL - 15
SP - 3523
EP - 3540
JO - Biomedical Optics Express
JF - Biomedical Optics Express
IS - 6
ER -