Video-Rate Quantitative Phase Imaging Using a Digital Holographic Microscope and a Generative Adversarial Network
The conventional reconstruction method of off-axis digital holographic microscopy (DHM) relies on computational processing that involves spatial filtering of the sample spectrum and tilt compensation between the interfering waves to accurately reconstruct the phase of a biological sample. Additional...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/23/8021 |
| _version_ | 1827674670952873984 |
|---|---|
| author | Raul Castaneda Carlos Trujillo Ana Doblas |
| author_facet | Raul Castaneda Carlos Trujillo Ana Doblas |
| author_sort | Raul Castaneda |
| collection | DOAJ |
| description | The conventional reconstruction method of off-axis digital holographic microscopy (DHM) relies on computational processing that involves spatial filtering of the sample spectrum and tilt compensation between the interfering waves to accurately reconstruct the phase of a biological sample. Additional computational procedures such as numerical focusing may be needed to reconstruct free-of-distortion quantitative phase images based on the optical configuration of the DHM system. Regardless of the implementation, any DHM computational processing leads to long processing times, hampering the use of DHM for video-rate renderings of dynamic biological processes. In this study, we report on a conditional generative adversarial network (cGAN) for robust and fast quantitative phase imaging in DHM. The reconstructed phase images provided by the GAN model present stable background levels, enhancing the visualization of the specimens for different experimental conditions in which the conventional approach often fails. The proposed learning-based method was trained and validated using human red blood cells recorded on an off-axis Mach–Zehnder DHM system. After proper training, the proposed GAN yields a computationally efficient method, reconstructing DHM images seven times faster than conventional computational approaches. |
| first_indexed | 2024-03-10T04:45:36Z |
| format | Article |
| id | doaj.art-999cc6ef6d8843cc89b17ec79241a32e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T04:45:36Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-999cc6ef6d8843cc89b17ec79241a32e2023-11-23T03:02:46ZengMDPI AGSensors1424-82202021-12-012123802110.3390/s21238021Video-Rate Quantitative Phase Imaging Using a Digital Holographic Microscope and a Generative Adversarial NetworkRaul Castaneda0Carlos Trujillo1Ana Doblas2Department of Electrical and Computer Engineering, The University of Memphis, Memphis, TN 38152, USAApplied Optics Group, Physical Sciences Department, Universidad EAFIT, Medellin 050037, ColombiaDepartment of Electrical and Computer Engineering, The University of Memphis, Memphis, TN 38152, USAThe conventional reconstruction method of off-axis digital holographic microscopy (DHM) relies on computational processing that involves spatial filtering of the sample spectrum and tilt compensation between the interfering waves to accurately reconstruct the phase of a biological sample. Additional computational procedures such as numerical focusing may be needed to reconstruct free-of-distortion quantitative phase images based on the optical configuration of the DHM system. Regardless of the implementation, any DHM computational processing leads to long processing times, hampering the use of DHM for video-rate renderings of dynamic biological processes. In this study, we report on a conditional generative adversarial network (cGAN) for robust and fast quantitative phase imaging in DHM. The reconstructed phase images provided by the GAN model present stable background levels, enhancing the visualization of the specimens for different experimental conditions in which the conventional approach often fails. The proposed learning-based method was trained and validated using human red blood cells recorded on an off-axis Mach–Zehnder DHM system. After proper training, the proposed GAN yields a computationally efficient method, reconstructing DHM images seven times faster than conventional computational approaches.https://www.mdpi.com/1424-8220/21/23/8021phase compensationdigital holographic microscopylearning-based methodgenerative adversarial networksvideo-rate performance |
| spellingShingle | Raul Castaneda Carlos Trujillo Ana Doblas Video-Rate Quantitative Phase Imaging Using a Digital Holographic Microscope and a Generative Adversarial Network Sensors phase compensation digital holographic microscopy learning-based method generative adversarial networks video-rate performance |
| title | Video-Rate Quantitative Phase Imaging Using a Digital Holographic Microscope and a Generative Adversarial Network |
| title_full | Video-Rate Quantitative Phase Imaging Using a Digital Holographic Microscope and a Generative Adversarial Network |
| title_fullStr | Video-Rate Quantitative Phase Imaging Using a Digital Holographic Microscope and a Generative Adversarial Network |
| title_full_unstemmed | Video-Rate Quantitative Phase Imaging Using a Digital Holographic Microscope and a Generative Adversarial Network |
| title_short | Video-Rate Quantitative Phase Imaging Using a Digital Holographic Microscope and a Generative Adversarial Network |
| title_sort | video rate quantitative phase imaging using a digital holographic microscope and a generative adversarial network |
| topic | phase compensation digital holographic microscopy learning-based method generative adversarial networks video-rate performance |
| url | https://www.mdpi.com/1424-8220/21/23/8021 |
| work_keys_str_mv | AT raulcastaneda videoratequantitativephaseimagingusingadigitalholographicmicroscopeandagenerativeadversarialnetwork AT carlostrujillo videoratequantitativephaseimagingusingadigitalholographicmicroscopeandagenerativeadversarialnetwork AT anadoblas videoratequantitativephaseimagingusingadigitalholographicmicroscopeandagenerativeadversarialnetwork |