Super-Resolution Reconstruction of Cytoskeleton Image Based on Deep Learning

Fen Hu; Yang Lin; Mengdi Hou; Haofeng Hu; Leiting Pan; Tiegen Liu; Jingjun Xu

doi:10.3788/AOS202040.2410001

Acta Optica Sinica, Volume. 40, Issue 24, 2410001(2020)

Super-Resolution Reconstruction of Cytoskeleton Image Based on Deep Learning

Fen Hu¹, Yang Lin², Mengdi Hou¹, Haofeng Hu^2、*, Leiting Pan^1,3,4、**, Tiegen Liu², and Jingjun Xu¹

¹Key Laboratory of Weak-Light Nonlinear Photonics, Ministry of Education, School of Physics, TEDA Applied Physics School, Nankai University, Tianjin 300071, China

²Key Laboratory of Opto-Electronics Information Technology, Ministry of Education, School of Precision Instrument & Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China;

³State Key Laboratory of Medicinal Chemical Biology, College of Life Sciences, Nankai University, Tianjin 300071, China

⁴Collaborative Innovation Center of Extreme Optics, Shanxi University, Taiyuan, Shanxi 0 30006, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(7)

Fig. 1. Structural diagram of EDSR. Conv represents convolution layer, ResBlock represents residual module, ReLU represents linear rectification activation function, Upsample represents upsampling, and Shuffle represents cycle screening

Download full size

Fig. 2. Schematic of training process for deep-learning based image super-resolution reconstruction

Download full size

Fig. 3. Relationship between loss function and training epoch of EDSR in the case of double down-sampling

Download full size

Fig. 4. Super-resolution reconstruction of cell microtubule cytoskeleton images obtained by double down-sampling based on EDSR deep learning. (a) Images of cytoskeletons; (b) enlarged views

Download full size

Fig. 5. Super-resolution reconstruction of three and four times down-sampling STORM images based on EDSR deep learning. (a) Reconstruction of three times down-sampling images; (b) reconstruction of four times down-sampling images

Download full size

Table 1. Average gradient values of different images in the case of double down-sampling
View table
Table 1. Average gradient values of different images in the case of double down-sampling
Region Down-sampling Interpolation method EDSR Original
1 20.18 17.75 27.53 26.99
2 18.36 16.45 25.90 26.66
3 21.29 18.67 30.39 31.23

Table 2. Average gradient values of different images in the case of three and four times down-sampling

View table

Table 2. Average gradient values of different images in the case of three and four times down-sampling

Condition		Down-sampling	Interpolation	EDSR	Original
	Region 1	11.69	10.04	20.03	18.47
Three times down-sampling	Region 2	20.47	18.05	32.44	31.26
	Region 3	18.01	14.88	28.85	27.40
	Region 1	14.24	11.74	30.60	35.59
Four times down-sampling	Region 2	19.10	15.25	36.97	38.64
	Region 3	15.24	13.30	28.40	33.25

Tools

Get Citation

Copy Citation Text

Fen Hu, Yang Lin, Mengdi Hou, Haofeng Hu, Leiting Pan, Tiegen Liu, Jingjun Xu. Super-Resolution Reconstruction of Cytoskeleton Image Based on Deep Learning[J]. Acta Optica Sinica, 2020, 40(24): 2410001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Image Processing

Received: Jul. 8, 2020

Accepted: Sep. 15, 2020

Published Online: Nov. 23, 2020

The Author Email: Hu Haofeng (haofeng_hu@tju.edu.cn), Pan Leiting (plt@nankai.edu.cn)

DOI:10.3788/AOS202040.2410001

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Average gradient values of different images in the case of double down-sampling

Table 1. Average gradient values of different images in the case of double down-sampling

Table 2. Average gradient values of different images in the case of three and four times down-sampling

Table 2. Average gradient values of different images in the case of three and four times down-sampling