A deep convolutional neural network for classification of red blood cells in sickle cell anemia

PLoS Computational Biology

Volumn 13, Issue 10, 2017, Pages

  Xu, Mengjia ^a,b   Papageorgiou, Dimitrios P ^c   Abidi, Sabia Z ^c   Dao, Ming ^c   Zhao, Hong ^a   Karniadakis, George Em ^b  

^a NORTHEASTERN UNIVERSITY   (China)

^b BROWN UNIVERSITY   (United States)

^c Massachusetts Institute of Technology   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BLOOD; CELLS; CONVOLUTION; CYTOLOGY; DEEP NEURAL NETWORKS; DIAGNOSIS; FACTOR ANALYSIS; IMAGE ENHANCEMENT;

BLOOD CELL IMAGES; CELL SHAPES; CONVOLUTIONAL NEURAL NETWORK; HEMATOLOGICAL DISORDERS; RED BLOOD CELL; RHEOLOGICAL CHARACTERISTICS; SHAPES FACTORS; SICKLE CELL DISEASE; SICKLE-CELL ANEMIA; SINGLE RED BLOOD CELL;

BLOOD VESSELS;

ACCURACY; ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; BIOLOGY; COMPARATIVE STUDY; CONCEPTUAL FRAMEWORK; CONTROLLED STUDY; CONVOLUTIONAL NEURAL NETWORK; DEOXYGENATION; DISEASE SEVERITY; ERYTHROCYTE; ERYTHROCYTE SHAPE; EX VIVO STUDY; EXTRACTION; FACTOR ANALYSIS; HEMATOLOGIC DISEASE; HIGH THROUGHPUT SEQUENCING; HUMAN; HUMAN CELL; MICROSCOPY; OXYGENATION; PREDICTION; SICKLE CELL ANEMIA; VALIDATION STUDY; ANEMIA, SICKLE CELL; AUTOMATED PATTERN RECOGNITION; COMPUTER ASSISTED DIAGNOSIS; CYTOLOGY; PATHOLOGY; PROCEDURES;

ANEMIA, SICKLE CELL; COMPUTATIONAL BIOLOGY; ERYTHROCYTES; HUMANS; IMAGE INTERPRETATION, COMPUTER-ASSISTED; MICROSCOPY; NEURAL NETWORKS (COMPUTER); PATTERN RECOGNITION, AUTOMATED;

EID: 85032445528     PISSN: 1553734X     EISSN: 15537358     Source Type: Journal    
DOI: 10.1371/journal.pcbi.1005746     Document Type: Article

References (32)

1. Anglin C, Sickle Cell Disease. Journal of Consumer Health on the Internet. 2015;19(2):122–131. doi: 10.1080/15398285.2015.1026706
2. Fasano RM, Booth GS, Miles M, Du L, Koyama T, Meier ER, et al. Red blood cell alloimmunization is influenced by recipient inflammatory state at time of transfusion in patients with sickle cell disease. British journal of haematology. 2015;168(2):291–300. doi: 10.1111/bjh.13123 25256676
3. Abubakar I, Tillmann T, Banerjee A, Global, regional, and national age-sex specific all-cause and cause-specific mortality for 240 causes of death, 1990-2013: a systematic analysis for the Global Burden of Disease Study 2013. Lancet. 2015;385(9963):117–171. doi: 10.1016/S0140-6736(14)61682-2
4. Milton JN, Gordeuk VR, Taylor JG, Gladwin MT, Steinberg MH, Sebastiani P, Prediction of fetal hemoglobin in sickle cell anemia using an ensemble of genetic risk prediction models. Circulation: Cardiovascular Genetics. 2014; p. CIRCGENETICS–113.
5. Darrow MC, Zhang Y, Cinquin BP, Smith EA, Boudreau R, Rochat RH, et al. Visualizing red blood cell sickling and the effects of inhibition of sphingosine kinase 1 using soft X-ray tomography. J Cell Sci. 2016;129(18):3511–3517. doi: 10.1242/jcs.189225 27505892
6. van Beers EJ, Samsel L, Mendelsohn L, Saiyed R, Fertrin KY, Brantner CA, et al. Imaging flow cytometry for automated detection of hypoxia-induced erythrocyte shape change in sickle cell disease. American journal of hematology. 2014;89(6):598–603. doi: 10.1002/ajh.23699 24585634
7. He Y, Gong H, Xiong B, Xu X, Li A, Jiang T, et al. iCut: an integrative cut algorithm enables accurate segmentation of touching cells. Scientific reports. 2015;5.
8. Liu Z, Liu J, Xiao X, Yuan H, Li X, Chang J, et al. Segmentation of White Blood Cells through Nucleus Mark Watershed Operations and Mean Shift Clustering. sensors. 2015;15(9):22561–22586. doi: 10.3390/s150922561 26370995
9. Arteta C, Lempitsky V, Noble JA, Zisserman A, Detecting overlapping instances in microscopy images using extremal region trees. Medical image analysis. 2016;27:3–16. doi: 10.1016/j.media.2015.03.002 25980675
10. Arteta C, Lempitsky V, Noble J, Zisserman A, Learning to detect cells using non-overlapping extremal regions. Medical image computing and computer-assisted intervention–MICCAI 2012. 2012; p. 348–356. doi: 10.1007/978-3-642-33415-3_43
11. Carpenter AE, Jones TR, Lamprecht MR, Clarke C, Kang IH, Friman O, et al. CellProfiler: image analysis software for identifying and quantifying cell phenotypes. Genome biology. 2006;7(10):R100. doi: 10.1186/gb-2006-7-10-r100 17076895
12. Sacan A, Ferhatosmanoglu H, Coskun H, CellTrack: an open-source software for cell tracking and motility analysis. Bioinformatics. 2008;24(14):1647–1649. doi: 10.1093/bioinformatics/btn247 18511469
13. Schindelin J, Arganda-Carreras I, Frise E, Kaynig V, Longair M, Pietzsch T, et al. Fiji: an open-source platform for biological-image analysis. Nature methods. 2012;9(7):676–682. doi: 10.1038/nmeth.2019 22743772
14. Hodneland E, Kögel T, Frei DM, Gerdes HH, Lundervold A, CellSegm-a MATLAB toolbox for high-throughput 3D cell segmentation. Source code for biology and medicine. 2013;8(1):16. doi: 10.1186/1751-0473-8-16 23938087
15. Shekhar K, Brodin P, Davis MM, Chakraborty AK, Automatic classification of cellular expression by nonlinear stochastic embedding (ACCENSE). Proceedings of the National Academy of Sciences. 2014;111(1):202–207. doi: 10.1073/pnas.1321405111
16. Liu L, Wang L, HEp-2 cell image classification with multiple linear descriptors. Pattern Recognition. 2014;47(7):2400–2408. doi: 10.1016/j.patcog.2013.09.022
17. Liu A, Gao Z, Tong H, Su Y, Yang Z, Sparse coding induced transfer learning for hep-2 cell classification. Bio-medical materials and engineering. 2014;24(1):237–243. 24211903
18. Donato C, Vincenzo T, Marco C, Francesco F, Maria VS, Giuseppe R. HEp-2 cell classification with heterogeneous classes-processes based on k-nearest neighbours. In: Pattern Recognition Techniques for Indirect Immunofluorescence Images (I3A), 2014 1st Workshop on. IEEE; 2014. p. 10–15.
19. Gao Z, Zhang J, Zhou L, Wang L. Hep-2 cell image classification with convolutional neural networks. In: Pattern Recognition Techniques for Indirect Immunofluorescence Images (I3A), 2014 1st Workshop on. IEEE; 2014. p. 24–28.
20. Li H, Zhang J, Zheng WS. Deep CNNs for HEp-2 Cells Classification: A Cross-specimen Analysis. arXiv preprint arXiv:160405816. 2016;.
21. Hosseini P, Abidi SZ, Du E, Papageorgiou DP, Choi Y, Park Y, et al. Cellular normoxic biophysical markers of hydroxyurea treatment in sickle cell disease. Proceedings of the National Academy of Sciences. 2016; p. 201610435. doi: 10.1073/pnas.1610435113
22. Han XH, Lei J, Chen YW. HEp-2 Cell Classification Using K-Support Spatial Pooling in Deep CNNs. In: International Workshop on Large-Scale Annotation of Biomedical Data and Expert Label Synthesis. Springer; 2016. p. 3–11.
23. Grady L, Random walks for image segmentation. IEEE transactions on pattern analysis and machine intelligence. 2006;28(11):1768–1783. doi: 10.1109/TPAMI.2006.233 17063682
24. Dokmanic I, Parhizkar R, Ranieri J, Vetterli M, Euclidean distance matrices: essential theory, algorithms, and applications. IEEE Signal Processing Magazine. 2015;32(6):12–30. doi: 10.1109/MSP.2015.2398954
25. Ozpolat HT, Chang T, Chen J, Wu X, Norby C, Konkle BA, et al. Evaluation of Cell Types and Morphologies in Sickle Cell Disease with an Imaging Flow Cytometer. Blood. 2015;126(23):972–972.
26. Hiruma H, Noguchi CT, Uyesaka N, Hasegawa S, Blanchette-Mackie EJ, Schechter AN, et al. Sickle cell rheology is determined by polymer fraction–not cell morphology. American journal of hematology. 1995;48(1):19–28. doi: 10.1002/ajh.2830480105 7832188
27. HW GL, Wortis M, Mukhopadhyay R, Stomatocyte–discocyte–echinocyte sequence of the human red blood cell: Evidence for the bilayer–couple hypothesis from membrane mechanics. Proceedings of the National Academy of Sciences. 2002;99(26):16766–16769. doi: 10.1073/pnas.202617299
28. Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R, Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research. 2014;15(1):1929–1958.
29. Wong TT, Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recognition. 2015;48(9):2839–2846. doi: 10.1016/j.patcog.2015.03.009
30. Hijiya N, Horiuchi K, Asakura T, Morphology of sickle cells produced in solutions of varying osmolarities. The Journal of laboratory and clinical medicine. 1991;117(1):60–66. 1987310
31. Asakura T, Mattiello JA, Obata K, Asakura K, Reilly MP, Tomassini N, et al. Partially oxygenated sickled cells: sickle-shaped red cells found in circulating blood of patients with sickle cell disease. Proceedings of the National Academy of Sciences. 1994;91(26):12589–12593. doi: 10.1073/pnas.91.26.12589
32. Asakura T, Asakura K, Obata K, Mattiello J, Ballas SK, Blood samples collected under venous oxygen pressure from patients with sickle cell disease contain a significant number of a new type of reversibly sickled cells: Constancy of the percentage of sickled cells in individual patients during steady state. American journal of hematology. 2005;80(4):249–256. doi: 10.1002/ajh.20468 16315254