Computational analysis of peripheral blood smears detects disease-associated cytomorphologies
Abstract Many hematological diseases are characterized by altered abundance and morphology of blood cells and their progenitors. Myelodysplastic syndromes (MDS), for example, are a group of blood cancers characterised by cytopenias, dysplasia of hematopoietic cells and blast expansion. Examination o...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-07-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-023-39676-y |
| _version_ | 1827895042824470528 |
|---|---|
| author | José Guilherme de Almeida Emma Gudgin Martin Besser William G. Dunn Jonathan Cooper Torsten Haferlach George S. Vassiliou Moritz Gerstung |
| author_facet | José Guilherme de Almeida Emma Gudgin Martin Besser William G. Dunn Jonathan Cooper Torsten Haferlach George S. Vassiliou Moritz Gerstung |
| author_sort | José Guilherme de Almeida |
| collection | DOAJ |
| description | Abstract Many hematological diseases are characterized by altered abundance and morphology of blood cells and their progenitors. Myelodysplastic syndromes (MDS), for example, are a group of blood cancers characterised by cytopenias, dysplasia of hematopoietic cells and blast expansion. Examination of peripheral blood slides (PBS) in MDS often reveals changes such as abnormal granulocyte lobulation or granularity and altered red blood cell (RBC) morphology; however, some of these features are shared with conditions such as haematinic deficiency anemias. Definitive diagnosis of MDS requires expert cytomorphology analysis of bone marrow smears and complementary information such as blood counts, karyotype and molecular genetics testing. Here, we present Haemorasis, a computational method that detects and characterizes white blood cells (WBC) and RBC in PBS. Applied to over 300 individuals with different conditions (SF3B1-mutant and SF3B1-wildtype MDS, megaloblastic anemia, and iron deficiency anemia), Haemorasis detected over half a million WBC and millions of RBC and characterized their morphology. These large sets of cell morphologies can be used in diagnosis and disease subtyping, while identifying novel associations between computational morphotypes and disease. We find that hypolobulated neutrophils and large RBC are characteristic of SF3B1-mutant MDS. Additionally, while prevalent in both iron deficiency and megaloblastic anemia, hyperlobulated neutrophils are larger in the latter. By integrating cytomorphological features using machine learning, Haemorasis was able to distinguish SF3B1-mutant MDS from other MDS using cytomorphology and blood counts alone, with high predictive performance. We validate our findings externally, showing that they generalize to other centers and scanners. Collectively, our work reveals the potential for the large-scale incorporation of automated cytomorphology into routine diagnostic workflows. |
| first_indexed | 2024-03-12T22:16:03Z |
| format | Article |
| id | doaj.art-899f50b6b94d4f4393095f6debfb084d |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-03-12T22:16:03Z |
| publishDate | 2023-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-899f50b6b94d4f4393095f6debfb084d2023-07-23T11:19:17ZengNature PortfolioNature Communications2041-17232023-07-0114111410.1038/s41467-023-39676-yComputational analysis of peripheral blood smears detects disease-associated cytomorphologiesJosé Guilherme de Almeida0Emma Gudgin1Martin Besser2William G. Dunn3Jonathan Cooper4Torsten Haferlach5George S. Vassiliou6Moritz Gerstung7European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI)Department of Haematology, Cambridge Institute for Medical Research, University of CambridgeDepartment of Haematology, Cambridge Institute for Medical Research, University of CambridgeDepartment of Haematology, Cambridge Institute for Medical Research, University of CambridgeWellcome Sanger Institute, Wellcome Genome CampusMunich Leukemia Laboratory GmbHWellcome Sanger Institute, Wellcome Genome CampusEuropean Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI)Abstract Many hematological diseases are characterized by altered abundance and morphology of blood cells and their progenitors. Myelodysplastic syndromes (MDS), for example, are a group of blood cancers characterised by cytopenias, dysplasia of hematopoietic cells and blast expansion. Examination of peripheral blood slides (PBS) in MDS often reveals changes such as abnormal granulocyte lobulation or granularity and altered red blood cell (RBC) morphology; however, some of these features are shared with conditions such as haematinic deficiency anemias. Definitive diagnosis of MDS requires expert cytomorphology analysis of bone marrow smears and complementary information such as blood counts, karyotype and molecular genetics testing. Here, we present Haemorasis, a computational method that detects and characterizes white blood cells (WBC) and RBC in PBS. Applied to over 300 individuals with different conditions (SF3B1-mutant and SF3B1-wildtype MDS, megaloblastic anemia, and iron deficiency anemia), Haemorasis detected over half a million WBC and millions of RBC and characterized their morphology. These large sets of cell morphologies can be used in diagnosis and disease subtyping, while identifying novel associations between computational morphotypes and disease. We find that hypolobulated neutrophils and large RBC are characteristic of SF3B1-mutant MDS. Additionally, while prevalent in both iron deficiency and megaloblastic anemia, hyperlobulated neutrophils are larger in the latter. By integrating cytomorphological features using machine learning, Haemorasis was able to distinguish SF3B1-mutant MDS from other MDS using cytomorphology and blood counts alone, with high predictive performance. We validate our findings externally, showing that they generalize to other centers and scanners. Collectively, our work reveals the potential for the large-scale incorporation of automated cytomorphology into routine diagnostic workflows.https://doi.org/10.1038/s41467-023-39676-y |
| spellingShingle | José Guilherme de Almeida Emma Gudgin Martin Besser William G. Dunn Jonathan Cooper Torsten Haferlach George S. Vassiliou Moritz Gerstung Computational analysis of peripheral blood smears detects disease-associated cytomorphologies Nature Communications |
| title | Computational analysis of peripheral blood smears detects disease-associated cytomorphologies |
| title_full | Computational analysis of peripheral blood smears detects disease-associated cytomorphologies |
| title_fullStr | Computational analysis of peripheral blood smears detects disease-associated cytomorphologies |
| title_full_unstemmed | Computational analysis of peripheral blood smears detects disease-associated cytomorphologies |
| title_short | Computational analysis of peripheral blood smears detects disease-associated cytomorphologies |
| title_sort | computational analysis of peripheral blood smears detects disease associated cytomorphologies |
| url | https://doi.org/10.1038/s41467-023-39676-y |
| work_keys_str_mv | AT joseguilhermedealmeida computationalanalysisofperipheralbloodsmearsdetectsdiseaseassociatedcytomorphologies AT emmagudgin computationalanalysisofperipheralbloodsmearsdetectsdiseaseassociatedcytomorphologies AT martinbesser computationalanalysisofperipheralbloodsmearsdetectsdiseaseassociatedcytomorphologies AT williamgdunn computationalanalysisofperipheralbloodsmearsdetectsdiseaseassociatedcytomorphologies AT jonathancooper computationalanalysisofperipheralbloodsmearsdetectsdiseaseassociatedcytomorphologies AT torstenhaferlach computationalanalysisofperipheralbloodsmearsdetectsdiseaseassociatedcytomorphologies AT georgesvassiliou computationalanalysisofperipheralbloodsmearsdetectsdiseaseassociatedcytomorphologies AT moritzgerstung computationalanalysisofperipheralbloodsmearsdetectsdiseaseassociatedcytomorphologies |