Deep learning application of the discrimination of bone marrow aspiration cells in patients with myelodysplastic syndromes
Abstract Myelodysplastic syndromes (MDS) are a group of hematologic neoplasms accompanied by dysplasia of the bone marrow hematopoietic cells with cytopenia. Detecting dysplasia is important in the diagnosis of MDS, but it takes considerable time and effort. Also, since the assessment of dysplasia i...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-11-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-022-21887-w |
_version_ | 1811223469198671872 |
---|---|
author | Nuri Lee Seri Jeong Min-Jeong Park Wonkeun Song |
author_facet | Nuri Lee Seri Jeong Min-Jeong Park Wonkeun Song |
author_sort | Nuri Lee |
collection | DOAJ |
description | Abstract Myelodysplastic syndromes (MDS) are a group of hematologic neoplasms accompanied by dysplasia of the bone marrow hematopoietic cells with cytopenia. Detecting dysplasia is important in the diagnosis of MDS, but it takes considerable time and effort. Also, since the assessment of dysplasia is subjective and difficult to quantify, a more efficient tool is needed for quality control and standardization of bone marrow aspiration smear interpretation. In this study, we developed and evaluated an algorithm to automatically discriminate hematopoietic cell lineages and detect dysplastic cells in bone marrow aspiration smears using deep learning technology. Bone marrow aspiration images were acquired from 34 patients diagnosed with MDS and from 24 normal bone marrow slides. In total, 8065 cells were classified into eight categories: normal erythrocytes, normal granulocytes, normal megakaryocytes, dysplastic erythrocytes, dysplastic granulocytes, dysplastic megakaryocytes, blasts, and others. The algorithm demonstrated acceptable performance in classifying dysplastic cells, with an AUC of 0.945–0.996 and accuracy of 0.912–0.993. The algorithm developed in this study could be used as an auxiliary tool for diagnosing patients with MDS and is expected to contribute to shortening the time required for MDS bone marrow aspiration diagnosis and standardizing visual reading. |
first_indexed | 2024-04-12T08:34:31Z |
format | Article |
id | doaj.art-d5c316bdae054f2088545671f21824a2 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-12T08:34:31Z |
publishDate | 2022-11-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-d5c316bdae054f2088545671f21824a22022-12-22T03:40:04ZengNature PortfolioScientific Reports2045-23222022-11-011211810.1038/s41598-022-21887-wDeep learning application of the discrimination of bone marrow aspiration cells in patients with myelodysplastic syndromesNuri Lee0Seri Jeong1Min-Jeong Park2Wonkeun Song3Department of Laboratory Medicine, Kangnam Sacred Heart Hospital, Hallym University College of MedicineDepartment of Laboratory Medicine, Kangnam Sacred Heart Hospital, Hallym University College of MedicineDepartment of Laboratory Medicine, Kangnam Sacred Heart Hospital, Hallym University College of MedicineDepartment of Laboratory Medicine, Kangnam Sacred Heart Hospital, Hallym University College of MedicineAbstract Myelodysplastic syndromes (MDS) are a group of hematologic neoplasms accompanied by dysplasia of the bone marrow hematopoietic cells with cytopenia. Detecting dysplasia is important in the diagnosis of MDS, but it takes considerable time and effort. Also, since the assessment of dysplasia is subjective and difficult to quantify, a more efficient tool is needed for quality control and standardization of bone marrow aspiration smear interpretation. In this study, we developed and evaluated an algorithm to automatically discriminate hematopoietic cell lineages and detect dysplastic cells in bone marrow aspiration smears using deep learning technology. Bone marrow aspiration images were acquired from 34 patients diagnosed with MDS and from 24 normal bone marrow slides. In total, 8065 cells were classified into eight categories: normal erythrocytes, normal granulocytes, normal megakaryocytes, dysplastic erythrocytes, dysplastic granulocytes, dysplastic megakaryocytes, blasts, and others. The algorithm demonstrated acceptable performance in classifying dysplastic cells, with an AUC of 0.945–0.996 and accuracy of 0.912–0.993. The algorithm developed in this study could be used as an auxiliary tool for diagnosing patients with MDS and is expected to contribute to shortening the time required for MDS bone marrow aspiration diagnosis and standardizing visual reading.https://doi.org/10.1038/s41598-022-21887-w |
spellingShingle | Nuri Lee Seri Jeong Min-Jeong Park Wonkeun Song Deep learning application of the discrimination of bone marrow aspiration cells in patients with myelodysplastic syndromes Scientific Reports |
title | Deep learning application of the discrimination of bone marrow aspiration cells in patients with myelodysplastic syndromes |
title_full | Deep learning application of the discrimination of bone marrow aspiration cells in patients with myelodysplastic syndromes |
title_fullStr | Deep learning application of the discrimination of bone marrow aspiration cells in patients with myelodysplastic syndromes |
title_full_unstemmed | Deep learning application of the discrimination of bone marrow aspiration cells in patients with myelodysplastic syndromes |
title_short | Deep learning application of the discrimination of bone marrow aspiration cells in patients with myelodysplastic syndromes |
title_sort | deep learning application of the discrimination of bone marrow aspiration cells in patients with myelodysplastic syndromes |
url | https://doi.org/10.1038/s41598-022-21887-w |
work_keys_str_mv | AT nurilee deeplearningapplicationofthediscriminationofbonemarrowaspirationcellsinpatientswithmyelodysplasticsyndromes AT serijeong deeplearningapplicationofthediscriminationofbonemarrowaspirationcellsinpatientswithmyelodysplasticsyndromes AT minjeongpark deeplearningapplicationofthediscriminationofbonemarrowaspirationcellsinpatientswithmyelodysplasticsyndromes AT wonkeunsong deeplearningapplicationofthediscriminationofbonemarrowaspirationcellsinpatientswithmyelodysplasticsyndromes |