Characterizing the feeding patterns of microzooplanktons using digital holographic microscopy and deep learning

2021 ◽  
Author(s):  
Harshith Bachimanchi ◽  
Benjamin Midtvedt ◽  
Daniel Midtvedt ◽  
Erik Selander ◽  
Giovanni Volpe
Keyword(s):  
Deep Learning ◽  
Digital Holographic Microscopy ◽  
Feeding Patterns ◽  
Holographic Microscopy

scholarly journals Automatic phase aberration compensation for digital holographic microscopy based on deep learning background detection

2017 ◽  
Vol 25 (13) ◽  
pp. 15043 ◽  
Author(s):  
Thanh Nguyen ◽  
Vy Bui ◽  
Van Lam ◽  
Christopher B. Raub ◽  
Lin-Ching Chang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Digital Holographic Microscopy ◽  
Phase Aberration ◽  
Automatic Phase ◽  
Holographic Microscopy

scholarly journals Fast phase retrieval in off-axis digital holographic microscopy through deep learning

2018 ◽  
Vol 26 (15) ◽  
pp. 19388 ◽  
Author(s):  
Gong Zhang ◽  
Tian Guan ◽  
Zhiyuan Shen ◽  
Xiangnan Wang ◽  
Tao Hu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Phase Retrieval ◽  
Digital Holographic Microscopy ◽  
Fast Phase ◽  
Holographic Microscopy

scholarly journals High throughput hemogram of T cells using digital holographic microscopy and deep learning

2021 ◽  
Author(s):  
Roopam K Gupta ◽  
Nils Hempler ◽  
Graeme Malcolm ◽  
Kishan Dholakia ◽  
Simon J Powis
Keyword(s):  
T Cells ◽  
Deep Learning ◽  
Adaptive Immune System ◽  
Cost Effective ◽  
Magnetic Bead ◽  
T Cell Subsets ◽  
Digital Holographic Microscopy ◽  
Label Free ◽  
Throughput Rate ◽  
Holographic Microscopy

T cells of the adaptive immune system provide effective protection to the human body against numerous pathogenic challenges. Current labelling methods of detecting these cells, such as flow cytometry or magnetic bead labelling, are time consuming and expensive. To overcome these limitations, the label-free method of digital holographic microscopy (DHM) combined with deep learning has recently been introduced which is both time and cost effective. In this study, we demonstrate the application of digital holographic microscopy with deep learning to classify the key CD4+ and CD8+ T cell subsets. We show that combining DHM of varying fields of view, with deep learning, can potentially achieve a classification throughput rate of 78,000 cells per second with an accuracy of 76.2% for these morphologically similar cells. This throughput rate is 100 times faster than the previous studies and proves to be an effective replacement for labelling methods.

Sign in / Sign up

Export Citation Format

Share Document