Deep Learning-enabled Holographic Imaging Flow-Cytometry for Label-Free Detection of Giardia Lamblia in Water Samples

2021 ◽  
Author(s):  
Zoltán Göröcs ◽  
David Baum ◽  
Fang Song ◽  
Kevin de Haan ◽  
Hatice Ceylan Koydemir ◽  
...  
Keyword(s):  
Flow Cytometry ◽  
Deep Learning ◽  
Water Samples ◽  
Giardia Lamblia ◽  
Label Free ◽  
Holographic Imaging ◽  
Imaging Flow Cytometry ◽  
Label Free Detection

scholarly journals Label-free detection of Giardia lamblia cysts using a deep learning-enabled portable imaging flow cytometer

Lab on a Chip ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 4404-4412
Author(s):  
Zoltán Göröcs ◽  
David Baum ◽  
Fang Song ◽  
Kevin de Haan ◽  
Hatice Ceylan Koydemir ◽  
...  
Keyword(s):  
Deep Learning ◽  
Water Samples ◽  
Giardia Lamblia ◽  
Cost Effective ◽  
Flow Cytometer ◽  
Label Free ◽  
Label Free Detection

We developed a field-portable and cost-effective imaging flow cytometer that uses deep learning to accurately detect Giardia cysts in water samples.

Deep learning-based label-free imaging flow cytometry for on-site analysis of water samples (Conference Presentation)

2019 ◽  
Author(s):  
Zoltán S. Göröcs ◽  
Miu Tamamitsu ◽  
Vittorio Bianco ◽  
Patrick Wolf ◽  
Shounak Roy ◽  
...  
Keyword(s):  
Flow Cytometry ◽  
Deep Learning ◽  
Water Samples ◽  
Label Free ◽  
Site Analysis ◽  
Imaging Flow Cytometry

Label-free detection of Giardia lamblia cysts in water samples using a field-portable imaging flow cytometer and deep learning

2021 ◽  
Author(s):  
Zoltán S. Göröcs ◽  
David Baum ◽  
Fang Song ◽  
Kevin De Haan ◽  
Hatice Ceylan Koydemir ◽  
...  
Keyword(s):  
Deep Learning ◽  
Water Samples ◽  
Giardia Lamblia ◽  
Flow Cytometer ◽  
Label Free ◽  
Label Free Detection

scholarly journals A weakly supervised deep learning approach for label-free imaging flow-cytometry-based blood diagnostics

2021 ◽  
Vol 1 (6) ◽  
pp. 100094
Author(s):  
Corin F. Otesteanu ◽  
Martina Ugrinic ◽  
Gregor Holzner ◽  
Yun-Tsan Chang ◽  
Christina Fassnacht ◽  
...  
Keyword(s):  
Flow Cytometry ◽  
Deep Learning ◽  
Learning Approach ◽  
Label Free ◽  
Imaging Flow Cytometry ◽  
Weakly Supervised

Label-free imaging flow cytometry for phenotypic analysis of microalgae populations using deep learning

2021 ◽  
Author(s):  
Çağatay Işıl ◽  
Kevin de Haan ◽  
Zoltán Gӧrӧcs ◽  
Hatice Ceylan Koydemir ◽  
Spencer Peterman ◽  
...  
Keyword(s):  
Flow Cytometry ◽  
Deep Learning ◽  
Label Free ◽  
Phenotypic Analysis ◽  
Imaging Flow Cytometry

Phenotypic Analysis of Microalgae Populations Using Label-Free Imaging Flow Cytometry and Deep Learning

ACS Photonics ◽  
2021 ◽  
Author(s):  
Çaǧatay Işıl ◽  
Kevin de Haan ◽  
Zoltán Göröcs ◽  
Hatice Ceylan Koydemir ◽  
Spencer Peterman ◽  
...  
Keyword(s):  
Flow Cytometry ◽  
Deep Learning ◽  
Label Free ◽  
Phenotypic Analysis ◽  
Imaging Flow Cytometry

scholarly journals Objective assessment of stored blood quality by deep learning

2020 ◽  
Vol 117 (35) ◽  
pp. 21381-21390 ◽  
Author(s):  
Minh Doan ◽  
Joseph A. Sebastian ◽  
Juan C. Caicedo ◽  
Stefanie Siegert ◽  
Aline Roch ◽  
...  
Keyword(s):  
Neural Network ◽  
Flow Cytometry ◽  
Deep Learning ◽  
Morphological Changes ◽  
Objective Assessment ◽  
Feature Space ◽  
Label Free ◽  
Storage Duration ◽  
Imaging Flow Cytometry ◽  
The Impact

Stored red blood cells (RBCs) are needed for life-saving blood transfusions, but they undergo continuous degradation. RBC storage lesions are often assessed by microscopic examination or biochemical and biophysical assays, which are complex, time-consuming, and destructive to fragile cells. Here we demonstrate the use of label-free imaging flow cytometry and deep learning to characterize RBC lesions. Using brightfield images, a trained neural network achieved 76.7% agreement with experts in classifying seven clinically relevant RBC morphologies associated with storage lesions, comparable to 82.5% agreement between different experts. Given that human observation and classification may not optimally discern RBC quality, we went further and eliminated subjective human annotation in the training step by training a weakly supervised neural network using only storage duration times. The feature space extracted by this network revealed a chronological progression of morphological changes that better predicted blood quality, as measured by physiological hemolytic assay readouts, than the conventional expert-assessed morphology classification system. With further training and clinical testing across multiple sites, protocols, and instruments, deep learning and label-free imaging flow cytometry might be used to routinely and objectively assess RBC storage lesions. This would automate a complex protocol, minimize laboratory sample handling and preparation, and reduce the impact of procedural errors and discrepancies between facilities and blood donors. The chronology-based machine-learning approach may also improve upon humans’ assessment of morphological changes in other biomedically important progressions, such as differentiation and metastasis.

scholarly journals Label-free assessment of red blood cell storage lesions by deep learning

2018 ◽  
Author(s):  
M. Doan ◽  
J. A. Sebastian ◽  
R. N. Pinto ◽  
C. McQuin ◽  
A. Goodman ◽  
...  
Keyword(s):  
Flow Cytometry ◽  
Deep Learning ◽  
Morphological Changes ◽  
Dark Field ◽  
Label Free ◽  
Imaging Flow Cytometry ◽  
Life Saving ◽  
Laboratory Procedures ◽  
Stored Blood

AbstractBlood transfusion is a life-saving clinical procedure. With millions of units needed globally each year, it is a growing concern to improve product quality and recipient outcomes.Stored red blood cells (RBCs) undergo continuous degradation, leading to structural and biochemical changes. To analyze RBC storage lesions, complex biochemical and biophysical assays are often employed.We demonstrate that label-free imaging flow cytometry and deep learning can characterize RBC morphologies during 42-day storage, replacing the current practice of manually quantifying a blood smear from stored blood units. Based only on bright field and dark field images, our model achieved 90% accuracy in classifying six different RBC morphologies associated with storage lesions versus human-curated manual examination. A model fitted to the deep learning-extracted features revealed a pattern of morphological changes within the aging blood unit that allowed predicting the expiration date of stored blood using solely morphological assessment.Deep learning and label-free imaging flow cytometry could therefore be applied to reduce complex laboratory procedures and facilitate robust and objective characterization of blood samples.

Sign in / Sign up

Export Citation Format

Share Document