دورية أكاديمية
Machine Learning of Bone Marrow Histopathology Identifies Genetic and Clinical Determinants in Patients with MDS.
| العنوان: | Machine Learning of Bone Marrow Histopathology Identifies Genetic and Clinical Determinants in Patients with MDS. |
|---|---|
| المؤلفون: | Brück OE; Hematology Research Unit Helsinki, University of Helsinki and Helsinki University Hospital Comprehensive Cancer Center, Helsinki, Finland.; Translational Immunology Research Program, University of Helsinki, Helsinki, Finland.; iCAN Digital Precision Cancer Medicine Flagship, Helsinki, Finland.; Helsinki University Hospital Comprehensive Cancer Center, Department of Hematology, Helsinki, Finland., Lallukka-Brück SE; Hematology Research Unit Helsinki, University of Helsinki and Helsinki University Hospital Comprehensive Cancer Center, Helsinki, Finland., Hohtari HR; Hematology Research Unit Helsinki, University of Helsinki and Helsinki University Hospital Comprehensive Cancer Center, Helsinki, Finland.; Translational Immunology Research Program, University of Helsinki, Helsinki, Finland., Ianevski A; Institute for Molecular Medicine Finland, HiLIFE, University of Helsinki, Helsinki, Finland., Ebeling FT; Helsinki University Hospital Comprehensive Cancer Center, Department of Hematology, Helsinki, Finland., Kovanen PE; Department of Pathology, HUSLAB, Helsinki University Hospital and University of Helsinki, Helsinki, Finland., Kytölä SI; HUS Diagnostic Center, HUSLAB, Helsinki University Hospital, Helsinki, Finland., Aittokallio TA; iCAN Digital Precision Cancer Medicine Flagship, Helsinki, Finland.; Institute for Molecular Medicine Finland, HiLIFE, University of Helsinki, Helsinki, Finland.; Department of Cancer Genetics, Institute for Cancer Research, Oslo University Hospital, and Oslo Centre for Biostatistics and Epidemiology, University of Oslo, Oslo, Norway., Ramos PM; Novartis Pharmaceuticals, Basel, Switzerland., Porkka KV; Hematology Research Unit Helsinki, University of Helsinki and Helsinki University Hospital Comprehensive Cancer Center, Helsinki, Finland.; Translational Immunology Research Program, University of Helsinki, Helsinki, Finland.; iCAN Digital Precision Cancer Medicine Flagship, Helsinki, Finland.; Helsinki University Hospital Comprehensive Cancer Center, Department of Hematology, Helsinki, Finland., Mustjoki SM; Hematology Research Unit Helsinki, University of Helsinki and Helsinki University Hospital Comprehensive Cancer Center, Helsinki, Finland.; Translational Immunology Research Program, University of Helsinki, Helsinki, Finland.; iCAN Digital Precision Cancer Medicine Flagship, Helsinki, Finland.; Department of Clinical Chemistry and Hematology, University of Helsinki, Helsinki, Finland. |
| المصدر: | Blood cancer discovery [Blood Cancer Discov] 2021 Mar 22; Vol. 2 (3), pp. 238-249. Date of Electronic Publication: 2021 Mar 22 (Print Publication: 2021). |
| نوع المنشور: | Journal Article; Research Support, Non-U.S. Gov't; Comment |
| اللغة: | English |
| بيانات الدورية: | Publisher: American Association for Cancer Research Country of Publication: United States NLM ID: 101764786 Publication Model: eCollection Cited Medium: Internet ISSN: 2643-3249 (Electronic) Linking ISSN: 26433230 NLM ISO Abbreviation: Blood Cancer Discov |
| أسماء مطبوعة: | Original Publication: Philadelphia, PA : American Association for Cancer Research, [2020]- |
| مواضيع طبية MeSH: | Myelodysplastic Syndromes*/diagnosis , Myelodysplastic-Myeloproliferative Diseases*/genetics, Bone Marrow/pathology ; Humans ; Machine Learning ; Mutation/genetics |
| مستخلص: | In myelodysplastic syndrome (MDS) and myeloproliferative neoplasm (MPN), bone marrow (BM) histopathology is assessed to identify dysplastic cellular morphology, cellularity, and blast excess. Yet, other morphologic findings may elude the human eye. We used convolutional neural networks to extract morphologic features from 236 MDS, 87 MDS/MPN, and 11 control BM biopsies. These features predicted genetic and cytogenetic aberrations, prognosis, age, and gender in multivariate regression models. Highest prediction accuracy was found for TET2 [area under the receiver operating curve (AUROC) = 0.94] and spliceosome mutations (0.89) and chromosome 7 monosomy (0.89). Mutation prediction probability correlated with variant allele frequency and number of affected genes per pathway, demonstrating the algorithms' ability to identify relevant morphologic patterns. By converting regression models to texture and cellular composition, we reproduced the classical del(5q) MDS morphology consisting of hypolobulated megakaryocytes. In summary, this study highlights the potential of linking deep BM histopathology with genetics and clinical variables. Significance: Histopathology is elementary in the diagnostics of patients with MDS, but its high-dimensional data are underused. By elucidating the association of morphologic features with clinical variables and molecular genetics, this study highlights the vast potential of convolutional neural networks in understanding MDS pathology and how genetics is reflected in BM morphology. See related commentary by Elemento, p. 195. (©2021 American Association for Cancer Research.) |
| التعليقات: | Comment on: Blood Cancer Discov. 2021 May;2(3):195-197. (PMID: 34027414) |
| References: | Nat Cancer. 2020 Aug;1(8):789-799. (PMID: 33763651) Nat Med. 2019 Jul;25(7):1054-1056. (PMID: 31160815) Nature. 2015 May 28;521(7553):436-44. (PMID: 26017442) Lancet Respir Med. 2018 Nov;6(11):801. (PMID: 30343029) Nature. 2017 Feb 2;542(7639):115-118. (PMID: 28117445) Blood. 2020 Nov 12;136(20):2249-2262. (PMID: 32961553) Sci Rep. 2017 Dec 4;7(1):16878. (PMID: 29203879) Bone. 1996 Oct;19(4):401-5. (PMID: 8894147) Sci Rep. 2018 Feb 21;8(1):3395. (PMID: 29467373) Cell. 2015 Jul 2;162(1):184-97. (PMID: 26095251) Blood. 2016 May 19;127(20):2391-405. (PMID: 27069254) Leukemia. 2014 Feb;28(2):241-7. (PMID: 24220272) Nat Med. 2018 Sep;24(9):1337-1341. (PMID: 30104767) Leukemia. 2017 Apr;31(4):1003-1007. (PMID: 28074069) BMC Genomics. 2018 Jun 19;19(1):477. (PMID: 29914354) Nat Med. 2018 Oct;24(10):1559-1567. (PMID: 30224757) Am J Hematol. 2018 Jan;93(1):129-147. (PMID: 29214694) Lancet Oncol. 2020 Feb;21(2):222-232. (PMID: 31926806) Nature. 1974 Oct 4;251(5474):437-8. (PMID: 4421285) Nat Med. 2019 Aug;25(8):1301-1309. (PMID: 31308507) Haematologica. 2011 Feb;96(2):180-3. (PMID: 21282718) Blood. 2012 Sep 20;120(12):2454-65. (PMID: 22740453) Leukemia. 2016 Apr;30(4):906-13. (PMID: 26648538) Nat Cancer. 2020 Aug;1(8):800-810. (PMID: 35122049) Blood. 2013 Nov 21;122(22):3616-27; quiz 3699. (PMID: 24030381) IEEE Trans Med Imaging. 2016 May;35(5):1285-98. (PMID: 26886976) Blood. 2019 Mar 7;133(10):1031-1038. (PMID: 30670448) Haematologica. 2018 Jan;103(1):61-68. (PMID: 29079596) Eur J Haematol. 2015 Sep;95(3):181-9. (PMID: 25600827) Bioinformatics. 2017 Aug 01;33(15):2424-2426. (PMID: 28369169) |
| تواريخ الأحداث: | Date Created: 20211018 Date Completed: 20220314 Latest Revision: 20240403 |
| رمز التحديث: | 20240403 |
| مُعرف محوري في PubMed: | PMC8513905 |
| DOI: | 10.1158/2643-3230.BCD-20-0162 |
| PMID: | 34661156 |
| قاعدة البيانات: | MEDLINE |
| تدمد: | 2643-3249 |
|---|---|
| DOI: | 10.1158/2643-3230.BCD-20-0162 |