Intelligent Skin-Removal for Photoacoustic Computed Tomography

Yixin Yuan; Tao Chen; Chengbo Liu; Jing Meng

doi:10.3788/CJL230930

Chinese Journal of Lasers, Volume. 50, Issue 21, 2107111(2023)

Intelligent Skin-Removal for Photoacoustic Computed Tomography

Yixin Yuan¹, Tao Chen², Chengbo Liu^2、**, and Jing Meng^1、*

Author Affiliations

¹School of Computer, Qufu Normal University, Rizhao 276826, Shandong, China

²Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, Guangdong, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(7)

Fig. 1. PACT skin signal removal method based on deep learning

Download full size

Fig. 2. Flowchart of skin-integrity fitting. (a) Breaking in the middle of skin; (b) incomplete skin at the ends

Download full size

Fig. 3. Flowchart of mask generation and skin removing

Download full size

Fig. 4. PACT imaging for human periphery blood vessels of legs. (a1)‒(f1) Original PACT images; (a2)‒(f2) ground truth; (a3)‒(f3) predicted results of Unet; (a4)‒(f4) predicted results of ResUnet; (a5)‒(f5) predicted results of MD-ResUnet

Download full size

Fig. 5. Comparisons of different skin-removal methods. (a)(b) Original PACT MAP images from the two datasets; (c)(d) skin-removal MAP images with local weight fitting method; (e)(f) skin-removal MAP images with MD-ResUnet; (a1)‒(f1) typical B-Scan images and their enlarged sub-images

Download full size

Table 1. Quantitative evaluation among different deep learning models

View table

Table 1. Quantitative evaluation among different deep learning models

Dataset	Model	Accuracy /%	Dice coefficient /%	Specificity /%	Sensitivity /%	Average /%
Dataset 1	Unet	80.3924	99.6900	99.8733	87.6141	91.8925
	ResUnet	86.0536	99.7006	99.8640	88.9374	93.6389
	MD-ResUnet	86.7972	99.7073	99.8480	90.4299	94.1956
Dataset 2	Unet	69.7649	99.3782	99.7198	75.9882	86.2128
	ResUnet	72.4788	99.3696	99.6549	79.8348	87.8345
	MD-ResUnet	72.7585	99.3620	99.6283	81.1242	88.2183

Table 2. Quantitative comparison between traditional skin-removal method and proposed deep learning method
View table
Table 2. Quantitative comparison between traditional skin-removal method and proposed deep learning method
Dataset Method MSE SSIM /% PSNR /dB
Dataset 1 Zhang et al. 0.0136 98.6654 38.6774
MD-ResUnet 0.0040 99.0471 43.9745
Dataset 2 Zhang et al. 0.0072 98.3557 38.4836
MD-ResUnet 0.0032 99.2403 41.9694

Tools

Get Citation

Copy Citation Text

Yixin Yuan, Tao Chen, Chengbo Liu, Jing Meng. Intelligent Skin-Removal for Photoacoustic Computed Tomography[J]. Chinese Journal of Lasers, 2023, 50(21): 2107111

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites