Raman Spectral Segmentation Method for Tongue Squamous Cell Carcinoma Using Deep Learning

Jinyang Liu; Mingxin Yu; Shengnan Ji; Lianqing Zhu; Tao Zhang; Jingya Ding; Jiabin Xia

doi:10.3788/LOP212701

Laser & Optoelectronics Progress, Volume. 60, Issue 2, 0230001(2023)

Raman Spectral Segmentation Method for Tongue Squamous Cell Carcinoma Using Deep Learning

Jinyang Liu¹, Mingxin Yu^1、*, Shengnan Ji², Lianqing Zhu¹, Tao Zhang¹, Jingya Ding¹, and Jiabin Xia¹

¹Key Laboratory of Optoelectronic Measurement Technology and Instrument, Ministry of Education, School of Instrument Science and Opto-Electronics Engineering, Beijing Information Science & Technology University, Beijing 100192, China

²China North Chemical Research Academy Group Co., Ltd., Beijing 100089, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(12)

Fig. 1. Effect drawing of data preprocessing

Download full size

Fig. 2. Average Raman characteristic peaks of tongue squamous cell carcinoma tissue and normal tissue

Download full size

Fig. 3. Structure diagram of ISB-CNN model

Download full size

Fig. 4. Conv Block and Identity Block

Download full size

Fig. 5. Schematic of preseted band

Download full size

Fig. 6. Functional diagram of candidate band pooling layer

Download full size

Fig. 7. P-R curve of tongue squamous cell carcinoma

Download full size

Fig. 8. Labeling results of tongue squamous cell carcinoma

Download full size

Fig. 9. Important spectral band regions predicted by the proposed model

Download full size

Table 1. Characteristic peaks of Raman spectrum of tongue squamous cell carcinoma
View table
Table 1. Characteristic peaks of Raman spectrum of tongue squamous cell carcinoma
Raman shifting /cm^-1 Corresponding material
798 Nucleic
993 Phenylalanine
1236 Amide Ⅲ
1376 Phospholipid （CH3）
1451 Lipid
1659 Keratin

Table 2. Training hyperparameters of ISB-CNN model
View table
Table 2. Training hyperparameters of ISB-CNN model
Hyper parameter Content
Optimizer Adam
Learning rate 0.001
Batch size 1
Epoch 100

Table 3. Comparison between predicted bands of ISB-CNN model and manually labeled bands

View table

Table 3. Comparison between predicted bands of ISB-CNN model and manually labeled bands

Characteristic peak /cm^-1	Corresponding material	Manual mark area /cm^-1	Model output area /cm^-1	IoU /%
795	Nucleic	［765，820］	［767，817］	90.90
989	Phenylalanine	［972，1003］	［971，1004］	93.93
1230	AmideIII	［1205，1250］	［1207，1254］	87.75
1376	Phospholipid （CH3）	［1350，1402］	［1353，1401］	92.30
1451	Lipid	［1433，1470］	［1433，1472］	94.87
1668	Keratin	［1650，1683］	［1649，1686］	91.67

Tools

Get Citation

Copy Citation Text

Jinyang Liu, Mingxin Yu, Shengnan Ji, Lianqing Zhu, Tao Zhang, Jingya Ding, Jiabin Xia. Raman Spectral Segmentation Method for Tongue Squamous Cell Carcinoma Using Deep Learning[J]. Laser & Optoelectronics Progress, 2023, 60(2): 0230001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Spectroscopy

Received: Oct. 11, 2021

Accepted: Nov. 29, 2021

Published Online: Jan. 6, 2023

The Author Email: Mingxin Yu (yumingxin@bistu.edu.cn)

DOI:10.3788/LOP212701

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Characteristic peaks of Raman spectrum of tongue squamous cell carcinoma

Table 1. Characteristic peaks of Raman spectrum of tongue squamous cell carcinoma

Table 2. Training hyperparameters of ISB-CNN model

Table 2. Training hyperparameters of ISB-CNN model

Table 3. Comparison between predicted bands of ISB-CNN model and manually labeled bands

Table 3. Comparison between predicted bands of ISB-CNN model and manually labeled bands