Red Blood Cell Phenotyping from 3D Confocal Images Using Artificial Neural Networks

Overview

Journal PLoS Comput Biol

Specialty Biology

Date 2021 May 13

PMID 33983926

Citations 17

Authors

Greta Simionato

Konrad Hinkelmann

Revaz Chachanidze

Paola Bianchi

Elisa Fermo

Richard van Wijk

Marc Leonetti

Christian Wagner

Lars Kaestner

Stephan Quint

Affiliations

Soon will be listed here.

Abstract

The investigation of cell shapes mostly relies on the manual classification of 2D images, causing a subjective and time consuming evaluation based on a portion of the cell surface. We present a dual-stage neural network architecture for analyzing fine shape details from confocal microscopy recordings in 3D. The system, tested on red blood cells, uses training data from both healthy donors and patients with a congenital blood disease, namely hereditary spherocytosis. Characteristic shape features are revealed from the spherical harmonics spectrum of each cell and are automatically processed to create a reproducible and unbiased shape recognition and classification. The results show the relation between the particular genetic mutation causing the disease and the shape profile. With the obtained 3D phenotypes, we suggest our method for diagnostics and theragnostics of blood diseases. Besides the application employed in this study, our algorithms can be easily adapted for the 3D shape phenotyping of other cell types and extend their use to other applications, such as industrial automated 3D quality control.

Citing Articles

Osmotic gradient ektacytometry - a novel diagnostic approach for neuroacanthocytosis syndromes.

Hernandez C, Peikert K, Qiao M, Darras A, de Wilde J, Bos J Front Neurosci. 2024; 18:1406969.

PMID: 39091345 PMC: 11292800. DOI: 10.3389/fnins.2024.1406969.

Advances in Red Blood Cells Research.

Bogdanova A, Kaestner L Cells. 2024; 13(4.

PMID: 38391972 PMC: 10887574. DOI: 10.3390/cells13040359.

Volumetric segmentation of biological cells and subcellular structures for optical diffraction tomography images.

Mazur M, Krauze W Biomed Opt Express. 2023; 14(10):5022-5035.

PMID: 37854559 PMC: 10581803. DOI: 10.1364/BOE.498275.

Big Data in Transfusion Medicine and Artificial Intelligence Analysis for Red Blood Cell Quality Control.

Lopes M, Recktenwald S, Simionato G, Eichler H, Wagner C, Quint S Transfus Med Hemother. 2023; 50(3):163-173.

PMID: 37408647 PMC: 10319094. DOI: 10.1159/000530458.

Computer vision quantitation of erythrocyte shape abnormalities provides diagnostic, prognostic, and mechanistic insight.

Foy B, Stefely J, Bendapudi P, Hasserjian R, Al-Samkari H, Louissaint A Blood Adv. 2023; 7(16):4621-4630.

PMID: 37146262 PMC: 10448422. DOI: 10.1182/bloodadvances.2022008967.

References

Ruan X, Murphy R . Evaluation of methods for generative modeling of cell and nuclear shape. Bioinformatics. 2018; 35(14):2475-2485. PMC: 6612826. DOI: 10.1093/bioinformatics/bty983. View

Newby J, Schaefer A, Lee P, Gregory Forest M, Lai S . Convolutional neural networks automate detection for tracking of submicron-scale particles in 2D and 3D. Proc Natl Acad Sci U S A. 2018; 115(36):9026-9031. PMC: 6130393. DOI: 10.1073/pnas.1804420115. View

Medyukhina A, Blickensdorf M, Cseresnyes Z, Ruef N, Stein J, Figge M . Dynamic spherical harmonics approach for shape classification of migrating cells. Sci Rep. 2020; 10(1):6072. PMC: 7142146. DOI: 10.1038/s41598-020-62997-7. View

Abay A, Simionato G, Chachanidze R, Bogdanova A, Hertz L, Bianchi P . Glutaraldehyde - A Subtle Tool in the Investigation of Healthy and Pathologic Red Blood Cells. Front Physiol. 2019; 10:514. PMC: 6527840. DOI: 10.3389/fphys.2019.00514. View

Eber S, Lux S . Hereditary spherocytosis--defects in proteins that connect the membrane skeleton to the lipid bilayer. Semin Hematol. 2004; 41(2):118-41. DOI: 10.1053/j.seminhematol.2004.01.002. View

Khairy K, Foo J, Howard J . Shapes of Red Blood Cells: Comparison of 3D Confocal Images with the Bilayer-Couple Model. Cell Mol Bioeng. 2010; 1(2-3):173-181. PMC: 2963995. DOI: 10.1007/s12195-008-0019-5. View

Cutiongco M, Jensen B, Reynolds P, Gadegaard N . Predicting gene expression using morphological cell responses to nanotopography. Nat Commun. 2020; 11(1):1384. PMC: 7070086. DOI: 10.1038/s41467-020-15114-1. View

Xu M, Papageorgiou D, Abidi S, Dao M, Zhao H, Karniadakis G . A deep convolutional neural network for classification of red blood cells in sickle cell anemia. PLoS Comput Biol. 2017; 13(10):e1005746. PMC: 5654260. DOI: 10.1371/journal.pcbi.1005746. View

Kihm A, Kaestner L, Wagner C, Quint S . Classification of red blood cell shapes in flow using outlier tolerant machine learning. PLoS Comput Biol. 2018; 14(6):e1006278. PMC: 6021115. DOI: 10.1371/journal.pcbi.1006278. View

10.

Hardie R . Acanthocytosis and neurological impairment--a review. Q J Med. 1989; 71(264):291-306. View

11.

Alvarez O, Montague N, Marin M, OBrien R, Rodriguez M . Quantification of sickle cells in the peripheral smear as a marker of disease severity. Fetal Pediatr Pathol. 2014; 34(3):149-54. DOI: 10.3109/15513815.2014.987937. View

12.

Takko H, Pajanoja C, Kurtzeborn K, Hsin J, Kuure S, Kerosuo L . ShapeMetrics: A userfriendly pipeline for 3D cell segmentation and spatial tissue analysis. Dev Biol. 2020; 462(1):7-19. PMC: 9624194. DOI: 10.1016/j.ydbio.2020.02.003. View

13.

Diez-Silva M, Dao M, Han J, Lim C, Suresh S . Shape and Biomechanical Characteristics of Human Red Blood Cells in Health and Disease. MRS Bull. 2010; 35(5):382-388. PMC: 2998922. DOI: 10.1557/mrs2010.571. View

14.

Lim H W G, Wortis M, Mukhopadhyay R . Stomatocyte-discocyte-echinocyte sequence of the human red blood cell: evidence for the bilayer- couple hypothesis from membrane mechanics. Proc Natl Acad Sci U S A. 2002; 99(26):16766-9. PMC: 139218. DOI: 10.1073/pnas.202617299. View

15.

Gul-Mohammed J, Arganda-Carreras I, Andrey P, Galy V, Boudier T . A generic classification-based method for segmentation of nuclei in 3D images of early embryos. BMC Bioinformatics. 2014; 15:9. PMC: 3900670. DOI: 10.1186/1471-2105-15-9. View

16.

Wenk R . Comparison of five methods for preparing blood smears. Am J Med Technol. 1976; 42(3):71-8. View

17.

Larkin T, Pages G, Chapman B, Rasko J, Kuchel P . NMR q-space analysis of canonical shapes of human erythrocytes: stomatocytes, discocytes, spherocytes and echinocytes. Eur Biophys J. 2012; 42(1):3-16. DOI: 10.1007/s00249-012-0822-8. View

18.

Kaestner L, Bianchi P . Trends in the Development of Diagnostic Tools for Red Blood Cell-Related Diseases and Anemias. Front Physiol. 2020; 11:387. PMC: 7264400. DOI: 10.3389/fphys.2020.00387. View

19.

Berg S, Kutra D, Kroeger T, Straehle C, Kausler B, Haubold C . ilastik: interactive machine learning for (bio)image analysis. Nat Methods. 2019; 16(12):1226-1232. DOI: 10.1038/s41592-019-0582-9. View

20.

Kamnitsas K, Ledig C, Newcombe V, Simpson J, Kane A, Menon D . Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal. 2016; 36:61-78. DOI: 10.1016/j.media.2016.10.004. View