Fluorescence Spectroscopy Combined with Machine Learning Applied to Molecular Typing of Breast Cancer

Nuo Xu; Qi Li; Hanlin Huang; Longhai Shen; Dongli Qi; Hongda Li; Yu Feng

doi:10.3788/LOP241367

Laser & Optoelectronics Progress, Volume. 62, Issue 6, 0617001(2025)

Fluorescence Spectroscopy Combined with Machine Learning Applied to Molecular Typing of Breast Cancer

Nuo Xu^1、*, Qi Li¹, Hanlin Huang¹, Longhai Shen¹, Dongli Qi¹, Hongda Li², and Yu Feng¹

Author Affiliations

¹School of Science, Shenyang Ligong University, Shenyang 110159, Liaoning , China

²School of Equipment Engineering, Shenyang Ligong University, Shenyang 110159, Liaoning , China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(8)

Fig. 1. Fluorescence spectra under different experimental parameters. (a) Acquisition under different angles at supply current of 35 mA; (b) acquisition under different current at sampling angle of 80°

Download full size

Fig. 2. Average fluorescence spectra of four molecular subtypes of breast cancer tissues

Download full size

Fig. 3. Average fluorescence spectra fitted by Gaussian function. (a) Luminal A breast cancer tissue; (b) Luminal B breast cancer tissue; (c) triple-negative breast cancer tissue; (d) HER-2 over-expressed breast cancer tissue

Download full size

Fig. 4. Scree plot of principal component analysis

Download full size

Fig. 5. Principal component factor score chart

Download full size

Table 1. Fluorescence spectrum gaussian fitting results and corresponding fluorescent groups

View table

Table 1. Fluorescence spectrum gaussian fitting results and corresponding fluorescent groups

Type	Peak 1 /nm	Peak 2 /nm	Peak 3 /nm	Peak 4 /nm	$R^{2}$
Fluorophore	NADH	Riboflavin	Oxidized melanin	Porphyrin	—
Luminal A	498.52	543.56	580.38	630.88	0.997
Luminal B	497.14	542.43	580.68	630.70	0.997
HER-2 over-expression	499.71	544.22	580.20	630.70	0.997
Triple-negative	501.35	545.36	580.38	630.88	0.995

Table 2. Performance indexes of PCA-SVM model before and after optimization
View table
Table 2. Performance indexes of PCA-SVM model before and after optimization
Parameter Accuracy Precision F1-score
$C = 1.0$
$γ = ‘ s c a l e ’$
0.930±0.08 0.942±0.07 0.928±0.08
$C = 4.1$
$γ = 2.0001$
0.950±0.06 0.959±0.05 0.949±0.06

Table 3. Discriminant sensitivity of PCA-SVM model for 4 types of breast cancer samples
View table
Table 3. Discriminant sensitivity of PCA-SVM model for 4 types of breast cancer samples
Type Sensitivity
Luminal A 0.91
Luminal B 0.97
HER-2 over-expression 0.94
Triple-negative 1.00

Tools

Get Citation

Copy Citation Text

Nuo Xu, Qi Li, Hanlin Huang, Longhai Shen, Dongli Qi, Hongda Li, Yu Feng. Fluorescence Spectroscopy Combined with Machine Learning Applied to Molecular Typing of Breast Cancer[J]. Laser & Optoelectronics Progress, 2025, 62(6): 0617001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Medical Optics and Biotechnology

Received: May. 24, 2024

Accepted: Aug. 28, 2024

Published Online: Mar. 3, 2025

The Author Email:

DOI:10.3788/LOP241367

CSTR:32186.14.LOP241367

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Fluorescence spectrum gaussian fitting results and corresponding fluorescent groups

Table 1. Fluorescence spectrum gaussian fitting results and corresponding fluorescent groups

Table 2. Performance indexes of PCA-SVM model before and after optimization

Table 2. Performance indexes of PCA-SVM model before and after optimization

Table 3. Discriminant sensitivity of PCA-SVM model for 4 types of breast cancer samples

Table 3. Discriminant sensitivity of PCA-SVM model for 4 types of breast cancer samples