1
|
Wang K, Song L, Wang C, Ren Z, Zhao G, Dou J, Di J, Barbastathis G, Zhou R, Zhao J, Lam EY. On the use of deep learning for phase recovery. LIGHT, SCIENCE & APPLICATIONS 2024; 13:4. [PMID: 38161203 PMCID: PMC10758000 DOI: 10.1038/s41377-023-01340-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/31/2023] [Revised: 11/13/2023] [Accepted: 11/16/2023] [Indexed: 01/03/2024]
Abstract
Phase recovery (PR) refers to calculating the phase of the light field from its intensity measurements. As exemplified from quantitative phase imaging and coherent diffraction imaging to adaptive optics, PR is essential for reconstructing the refractive index distribution or topography of an object and correcting the aberration of an imaging system. In recent years, deep learning (DL), often implemented through deep neural networks, has provided unprecedented support for computational imaging, leading to more efficient solutions for various PR problems. In this review, we first briefly introduce conventional methods for PR. Then, we review how DL provides support for PR from the following three stages, namely, pre-processing, in-processing, and post-processing. We also review how DL is used in phase image processing. Finally, we summarize the work in DL for PR and provide an outlook on how to better use DL to improve the reliability and efficiency of PR. Furthermore, we present a live-updating resource ( https://github.com/kqwang/phase-recovery ) for readers to learn more about PR.
Collapse
Affiliation(s)
- Kaiqiang Wang
- Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong SAR, China.
- School of Physical Science and Technology, Northwestern Polytechnical University, Xi'an, China.
- Department of Biomedical Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China.
| | - Li Song
- Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong SAR, China
| | - Chutian Wang
- Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong SAR, China
| | - Zhenbo Ren
- School of Physical Science and Technology, Northwestern Polytechnical University, Xi'an, China
| | - Guangyuan Zhao
- Department of Biomedical Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Jiazhen Dou
- School of Information Engineering, Guangdong University of Technology, Guangzhou, China
| | - Jianglei Di
- School of Information Engineering, Guangdong University of Technology, Guangzhou, China
| | - George Barbastathis
- Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Renjie Zhou
- Department of Biomedical Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Jianlin Zhao
- School of Physical Science and Technology, Northwestern Polytechnical University, Xi'an, China.
| | - Edmund Y Lam
- Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong SAR, China.
| |
Collapse
|
2
|
Ahamadzadeh E, Jaferzadeh K, Park S, Son S, Moon I. Automated analysis of human cardiomyocytes dynamics with holographic image-based tracking for cardiotoxicity screening. Biosens Bioelectron 2022; 195:113570. [PMID: 34455143 DOI: 10.1016/j.bios.2021.113570] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2020] [Revised: 07/19/2021] [Accepted: 08/14/2021] [Indexed: 11/02/2022]
Abstract
This paper proposes a new non-invasive, low-cost, and fully automated platform to quantitatively analyze dynamics of human-induced pluripotent stem cell-derived cardiomyocytes (hiPS-CMs) at the single-cell level by holographic image-based tracking for cardiotoxicity screening. A dense Farneback optical flow method and holographic imaging informatics were combined to characterize the contractile motion of a single CM, which obviates the need for costly equipment to monitor a CM's mechanical beat activity. The reliability of the proposed platform was tested by single-cell motion characterization, synchronization analysis, motion speed measurement of fixed CMs versus live CMs, and noise sensitivity. The applicability of the motion characterization method was tested to determine the pharmacological effects of two cardiovascular drugs, isoprenaline (166 nM) and E-4031 (500 μM). The experiments were done using single CMs and multiple cells, and the results were compared to control conditions. Cardiomyocytes responded to isoprenaline by increasing the action potential (AP) speed and shortening the resting period, thus increasing the beat frequency. In the presence of E-4031, the AP speed was decreased, and the resting period was prolonged, thus decreasing the beat frequency. The findings offer insights into single hiPS-CMs' contractile motion and a deep understanding of their kinetics at the single-cell level for cardiotoxicity screening.
Collapse
Affiliation(s)
- Ezat Ahamadzadeh
- Department of Robotics Engineering, Daegu Gyeongbuk Institute of Science & Technology (DGIST), Hyeonpung-eup, Dalseong-gun, Daegu, 42988, South Korea
| | - Keyvan Jaferzadeh
- Department of Electronics Design, Mid Sweden University, 85170, Sundsvall, Sweden
| | - Seonghwan Park
- Department of Robotics Engineering, Daegu Gyeongbuk Institute of Science & Technology (DGIST), Hyeonpung-eup, Dalseong-gun, Daegu, 42988, South Korea
| | - Seungwoo Son
- Department of Robotics Engineering, Daegu Gyeongbuk Institute of Science & Technology (DGIST), Hyeonpung-eup, Dalseong-gun, Daegu, 42988, South Korea
| | - Inkyu Moon
- Department of Robotics Engineering, Daegu Gyeongbuk Institute of Science & Technology (DGIST), Hyeonpung-eup, Dalseong-gun, Daegu, 42988, South Korea.
| |
Collapse
|
3
|
Kim E, Park S, Hwang S, Moon I, Javidi B. Deep Learning-based Phenotypic Assessment of Red Cell Storage Lesions for Safe Transfusions. IEEE J Biomed Health Inform 2021; 26:1318-1328. [PMID: 34388103 DOI: 10.1109/jbhi.2021.3104650] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
This study presents a novel approach to automatically perform instant phenotypic assessment of red blood cell (RBC) storage lesion in phase images obtained by digital holographic microscopy. The proposed model combines a generative adversarial network (GAN) with marker-controlled watershed segmentation scheme. The GAN model performed RBC segmentations and classifications to develop ageing markers, and the watershed segmentation was used to completely separate overlapping RBCs. Our approach achieved good segmentation and classification accuracy with a Dices coefficient of 0.94 at a high throughput rate of about 152 cells per second. These results were compared with other deep neural network architectures. Moreover, our image-based deep learning models recognized the morphological changes that occur in RBCs during storage. Our deep learning-based classification results were in good agreement with previous findings on the changes in RBC markers (dominant shapes) affected by storage duration. We believe that our image-based deep learning models can be useful for automated assessment of RBC quality, storage lesions for safe transfusions, and diagnosis of RBC-related diseases.
Collapse
|