Orbit image analysis machine learning software can be used for the histological quantification of acute ischemic stroke blood clots

Autoři: Seán Fitzgerald aff001;  Shunli Wang aff002;  Daying Dai aff002;  Dennis H. Murphree, Jr. aff005;  Abhay Pandit aff001;  Andrew Douglas aff001;  Asim Rizvi aff002;  Ramanathan Kadirvel aff002;  Michael Gilvarry aff006;  Ray McCarthy aff006;  Manuel Stritt aff007;  Matthew J. Gounis aff008;  Waleed Brinjikji aff002;  David F. Kallmes aff002;  Karen M. Doyle aff001
Působiště autorů: CÚRAM–Centre for Research in Medical Devices, National University of Ireland Galway, Galway, Ireland aff001;  Department of Radiology, Mayo Clinic, Rochester, Minnesota, United States of America aff002;  Department of Physiology, National University of Ireland Galway, Galway, Ireland aff003;  Department of Pathology, Shanghai East Hospital, Tongji University, Shanghai, China aff004;  Department of Health Sciences Research, Mayo Clinic, Rochester, Minnesota, United States of America aff005;  Cerenovus, Ballybrit, Galway, Ireland aff006;  Orbit Image Analysis, Binningen, Switzerland aff007;  Department of Radiology, New England Center for Stroke Research, University of Massachusetts Medical School, Worcester, Massachusetts, United States of America aff008
Vyšlo v časopise: PLoS ONE 14(12)
Kategorie: Research Article
prolekare.web.journal.doi_sk: 10.1371/journal.pone.0225841


Our aim was to assess the utility of a novel machine learning software (Orbit Image Analysis) in the histological quantification of acute ischemic stroke (AIS) clots. We analyzed 50 AIS blood clots retrieved using mechanical thrombectomy procedures. Following H&E staining, quantification of clot components was performed by two different methods: a pathologist using a reference standard method (Adobe Photoshop CC) and an experienced researcher using Orbit Image Analysis. Following quantification, the clots were categorized into 3 types: RBC dominant (≥60% RBCs), Mixed and Fibrin dominant (≥60% Fibrin). Correlations between clot composition and Hounsfield Units density on Computed Tomography (CT) were assessed. There was a significant correlation between the components of clots as quantified by the Orbit Image Analysis algorithm and the reference standard approach (ρ = 0.944**, p < 0.001, n = 150). A significant relationship was found between clot composition (RBC-Rich, Mixed, Fibrin-Rich) and the presence of a Hyperdense artery sign using the algorithmic method (X2(2) = 6.712, p = 0.035*) but not using the reference standard method (X2(2) = 3.924, p = 0.141). Orbit Image Analysis machine learning software can be used for the histological quantification of AIS clots, reproducibly generating composition analyses similar to current reference standard methods.

Klíčová slova:

Computed axial tomography – Fibrin – Hematoxylin staining – Histology – Image analysis – Machine learning – Machine learning algorithms – Red blood cells


1. Albers GW, Marks MP, Kemp S, Christensen S, Tsai JP, Ortega-Gutierrez S, et al. Thrombectomy for Stroke at 6 to 16 Hours with Selection by Perfusion Imaging. New England Journal of Medicine. 2018. doi: 10.1056/NEJMoa1713973 29364767

2. Nogueira RG, Jadhav AP, Haussen DC, Bonafe A, Budzik RF, Bhuva P, et al. Thrombectomy 6 to 24 Hours after Stroke with a Mismatch between Deficit and Infarct. New England Journal of Medicine. 2017;378(1):11–21. doi: 10.1056/NEJMoa1706442 29129157

3. Jovin TG, Chamorro A, Cobo E, de Miquel MA, Molina CA, Rovira A, et al. Thrombectomy within 8 Hours after Symptom Onset in Ischemic Stroke. New England Journal of Medicine. 2015;372(24):2296–306. doi: 10.1056/NEJMoa1503780 25882510

4. Goyal M, Demchuk AM, Menon BK, Eesa M, Rempel JL, Thornton J, et al. Randomized Assessment of Rapid Endovascular Treatment of Ischemic Stroke. New England Journal of Medicine. 2015;372(11):1019–30. doi: 10.1056/NEJMoa1414905 25671798

5. Saver JL, Goyal M, Bonafe A, Diener H-C, Levy EI, Pereira VM, et al. Stent-Retriever Thrombectomy after Intravenous t-PA vs. t-PA Alone in Stroke. New England Journal of Medicine. 2015;372(24):2285–95. doi: 10.1056/NEJMoa1415061 25882376

6. Rothwell PM, Algra A, Chen Z, Diener HC, Norrving B, Mehta Z. Effects of aspirin on risk and severity of early recurrent stroke after transient ischaemic attack and ischaemic stroke: time-course analysis of randomised trials. Lancet (London, England). 2016;388(10042):365–75. Epub 2016/05/23. doi: 10.1016/s0140-6736(16)30468-8 27209146; PubMed Central PMCID: PMC5321490.

7. Diener HC, Bogousslavsky J, Brass LM, Cimminiello C, Csiba L, Kaste M, et al. Aspirin and clopidogrel compared with clopidogrel alone after recent ischaemic stroke or transient ischaemic attack in high-risk patients (MATCH): randomised, double-blind, placebo-controlled trial. Lancet (London, England). 2004;364(9431):331–7. Epub 2004/07/28. doi: 10.1016/s0140-6736(04)16721-4 15276392.

8. Madabhushi A, Lee G. Image analysis and machine learning in digital pathology: Challenges and opportunities. Medical Image Analysis. 2016;33:170–5. doi: 10.1016/j.media.2016.06.037 27423409

9. Arena Ellen T, Rueden Curtis T, Hiner Mark C, Wang S, Yuan M, Eliceiri Kevin W. Quantitating the cell: turning images into numbers with Image J. Wiley Interdisciplinary Reviews: Developmental Biology. 2016;6(2):e260. doi: 10.1002/wdev.260 27911038

10. Prasad K, Prabhu GK. Image Analysis Tools for Evaluation of Microscopic Views of Immunohistochemically Stained Specimen in Medical Research–a Review. Journal of Medical Systems. 2012;36(4):2621–31. doi: 10.1007/s10916-011-9737-7 21584771

11. Lehr H-A, van der Loss CM, Teeling P, Gown AM. Complete Chromogen Separation and Analysis in Double Immunohistochemical Stains Using Photoshop-based Image Analysis. Journal of Histochemistry & Cytochemistry. 1999;47(1):119–25. doi: 10.1177/002215549904700113 9857219

12. Zhou Y, Ru GQ, Yan R, Wang MS, Chen MJ, Yu LL, et al. An Inexpensive Digital Image Analysis Technique for Liver Fibrosis Quantification in Chronic Hepatitis B Patients. Annals of hepatology. 2017;16(6):881–7. Epub 2017/10/23. doi: 10.5604/01.3001.0010.5278 29055926.

13. Stritt M, Stalder AK, Vezzali E. Orbit Image Analysis: An open-source whole slide image analysis tool. bioRxiv. 2019:731000. doi: 10.1101/731000

14. De Meyer SF, Andersson T, Baxter B, Bendszus M, Brouwer P, Brinjikji W, et al. Analyses of thrombi in acute ischemic stroke: A consensus statement on current knowledge and future directions. International journal of stroke: official journal of the International Stroke Society. 2017;12(6):606–14. Epub 2017/05/24. doi: 10.1177/1747493017709671 28534706.

15. Brinjikji W, Duffy S, Burrows A, Hacke W, Liebeskind D, Majoie CBLM, et al. Correlation of imaging and histopathology of thrombi in acute ischemic stroke with etiology and outcome: a systematic review. Journal of NeuroInterventional Surgery. 2016.

16. Boeckh-Behrens T, Schubert M, Forschler A, Prothmann S, Kreiser K, Zimmer C, et al. The Impact of Histological Clot Composition in Embolic Stroke. Clinical neuroradiology. 2016;26(2):189–97. Epub 2014/09/28. doi: 10.1007/s00062-014-0347-x 25261075.

17. Seger S, Stritt M, Vezzali E, Nayler O, Hess P, Groenen PMA, et al. A fully automated image analysis method to quantify lung fibrosis in the bleomycin-induced rat model. PLOS ONE. 2018;13(3):e0193057. doi: 10.1371/journal.pone.0193057 29547661

18. Stritt M, Bär R, Freyss J, Marrie J, Vezzali E, Weber E, et al. Supervised Machine Learning Methods for Quantification of Pulmonary Fibrosis2011. 24–37 p.

19. Kuhn M, Johnson K. An Introduction to Feature Selection. In: Kuhn M, Johnson K, editors. Applied Predictive Modeling. New York, NY: Springer New York; 2013. p. 487–519.

20. El-Badry AM, Breitenstein S, Jochum W, Washington K, Paradis V, Rubbia-Brandt L, et al. Assessment of Hepatic Steatosis by Expert Pathologists: The End of a Gold Standard. Annals of Surgery. 2009;250(5):691–7. doi: 10.1097/SLA.0b013e3181bcd6dd PubMed PMID: 00000658-200911000-00005. 19806055

21. Meijer GA, Beliën JA, van Diest PJ, Baak JP. Origins of … image analysis in clinical pathology. Journal of Clinical Pathology. 1997;50(5):365. doi: 10.1136/jcp.50.5.365 9215116

22. Kayser K, Borkenfeld S, Kayser G. Digital Image Content and Context Information in Tissue-based Diagnosis. Diagnostic Pathology; Vol 4 No 1 (2018): 2018DO—1017629/wwwdiagnosticpathologyeu-2018-4:269. 2018.

23. Feldman AT, Wolfe D. Tissue Processing and Hematoxylin and Eosin Staining. In: Day CE, editor. Histopathology: Methods and Protocols. New York, NY: Springer New York; 2014. p. 31–43.

24. Suvarna KS, Layton C, Bancroft JD. Bancroft's Theory and Practice of Histological Techniques E-Book: Elsevier Health Sciences; 2018.

25. Niesten JM, van der Schaaf IC, Biessels GJ, van Otterloo AE, van Seeters T, Horsch AD, et al. Relationship between thrombus attenuation and different stroke subtypes. Neuroradiology. 2013;55(9):1071–9. doi: 10.1007/s00234-013-1217-y 23793862

26. Liebeskind DS, Sanossian N, Yong WH, Starkman S, Tsang MP, Moya AL, et al. CT and MRI Early Vessel Signs Reflect Clot Composition in Acute Stroke. Stroke. 2011;42(5):1237. doi: 10.1161/STROKEAHA.110.605576 21393591

27. Boeckh-Behrens T, Schubert M, Förschler A, Prothmann S, Kreiser K, Zimmer C, et al. The Impact of Histological Clot Composition in Embolic Stroke. Clinical Neuroradiology. 2016;26(2):189–97. doi: 10.1007/s00062-014-0347-x 25261075

28. Kim SK, Yoon W, Kim TS, Kim HS, Heo TW, Park MS. Histologic Analysis of Retrieved Clots in Acute Ischemic Stroke: Correlation with Stroke Etiology and Gradient-Echo MRI. American Journal of Neuroradiology. 2015;36(9):1756. doi: 10.3174/ajnr.A4402 26159515

29. Mokin M, Morr S, Natarajan SK, Lin N, Snyder KV, Hopkins LN, et al. Thrombus density predicts successful recanalization with Solitaire stent retriever thrombectomy in acute ischemic stroke. Journal of NeuroInterventional Surgery. 2015;7(2):104. doi: 10.1136/neurintsurg-2013-011017 24510378

30. Froehler MT, Tateshima S, Duckwiler G, Jahan R, Gonzalez N, Vinuela F, et al. The hyperdense vessel sign on CT predicts successful recanalization with the Merci device in acute ischemic stroke. Journal of NeuroInterventional Surgery. 2012.

31. Moftakhar P, English JD, Cooke DL, Kim WT, Stout C, Smith WS, et al. Density of Thrombus on Admission CT Predicts Revascularization Efficacy in Large Vessel Occlusion Acute Ischemic Stroke. Stroke. 2013;44(1):243. doi: 10.1161/STROKEAHA.112.674127 23111438

32. Hufnagl P, Zwönitzer R, Haroske G. Guidelines Digital Pathology for Diagnosis on (and Reports of) Digital Images Version 1.0 Bundesverband deutscher Pathologen e.V. (Federal Association of German Pathologist). Diagnostic Pathology; Vol 4 No 1 (2018): 2018DO—1017629/wwwdiagnosticpathologyeu-2018-4:266. 2018.

Článok vyšiel v časopise


2019 Číslo 12