High-accuracy morphological identification of bone marrow cells using deep learning-based Morphogo system
Abstract Accurate identification and classification of bone marrow (BM) nucleated cell morphology are crucial for the diagnosis of hematological diseases. However, the subjective and time-consuming nature of manual identification by pathologists hinders prompt diagnosis and patient treatment. To add...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-08-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-40424-x |
| _version_ | 1797452928805502976 |
|---|---|
| author | Zhanwu Lv Xinyi Cao Xinyi Jin Shuangqing Xu Huangling Deng |
| author_facet | Zhanwu Lv Xinyi Cao Xinyi Jin Shuangqing Xu Huangling Deng |
| author_sort | Zhanwu Lv |
| collection | DOAJ |
| description | Abstract Accurate identification and classification of bone marrow (BM) nucleated cell morphology are crucial for the diagnosis of hematological diseases. However, the subjective and time-consuming nature of manual identification by pathologists hinders prompt diagnosis and patient treatment. To address this issue, we developed Morphogo, a convolutional neural network-based system for morphological examination. Morphogo was trained using a vast dataset of over 2.8 million BM nucleated cell images. Its performance was evaluated using 508 BM cases that were categorized into five groups based on the degree of morphological abnormalities, comprising a total of 385,207 BM nucleated cells. The results demonstrated Morphogo’s ability to identify over 25 different types of BM nucleated cells, achieving a sensitivity of 80.95%, specificity of 99.48%, positive predictive value of 76.49%, negative predictive value of 99.44%, and an overall accuracy of 99.01%. In most groups, Morphogo cell analysis and Pathologists' proofreading showed high intragroup correlation coefficients for granulocytes, erythrocytes, lymphocytes, monocytes, and plasma cells. These findings further validate the practical applicability of the Morphogo system in clinical practice and emphasize its value in assisting pathologists in diagnosing blood disorders. |
| first_indexed | 2024-03-09T15:15:46Z |
| format | Article |
| id | doaj.art-9da033cbdabc4c95a2de201b8fc79f95 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-09T15:15:46Z |
| publishDate | 2023-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-9da033cbdabc4c95a2de201b8fc79f952023-11-26T13:05:31ZengNature PortfolioScientific Reports2045-23222023-08-0113111110.1038/s41598-023-40424-xHigh-accuracy morphological identification of bone marrow cells using deep learning-based Morphogo systemZhanwu Lv0Xinyi Cao1Xinyi Jin2Shuangqing Xu3Huangling Deng4Bone Marrow Chamber, Guangzhou Kingmed Diagnostic Laboratory Group Co., Ltd.Division of Medical Technology Development, Hangzhou Zhiwei Information Technology Co., Ltd.Division of Medical Technology Development, Hangzhou Zhiwei Information Technology Co., Ltd.Bone Marrow Chamber, Guangzhou Kingmed Diagnostic Laboratory Group Co., Ltd.Bone Marrow Chamber, Guangzhou Kingmed Diagnostic Laboratory Group Co., Ltd.Abstract Accurate identification and classification of bone marrow (BM) nucleated cell morphology are crucial for the diagnosis of hematological diseases. However, the subjective and time-consuming nature of manual identification by pathologists hinders prompt diagnosis and patient treatment. To address this issue, we developed Morphogo, a convolutional neural network-based system for morphological examination. Morphogo was trained using a vast dataset of over 2.8 million BM nucleated cell images. Its performance was evaluated using 508 BM cases that were categorized into five groups based on the degree of morphological abnormalities, comprising a total of 385,207 BM nucleated cells. The results demonstrated Morphogo’s ability to identify over 25 different types of BM nucleated cells, achieving a sensitivity of 80.95%, specificity of 99.48%, positive predictive value of 76.49%, negative predictive value of 99.44%, and an overall accuracy of 99.01%. In most groups, Morphogo cell analysis and Pathologists' proofreading showed high intragroup correlation coefficients for granulocytes, erythrocytes, lymphocytes, monocytes, and plasma cells. These findings further validate the practical applicability of the Morphogo system in clinical practice and emphasize its value in assisting pathologists in diagnosing blood disorders.https://doi.org/10.1038/s41598-023-40424-x |
| spellingShingle | Zhanwu Lv Xinyi Cao Xinyi Jin Shuangqing Xu Huangling Deng High-accuracy morphological identification of bone marrow cells using deep learning-based Morphogo system Scientific Reports |
| title | High-accuracy morphological identification of bone marrow cells using deep learning-based Morphogo system |
| title_full | High-accuracy morphological identification of bone marrow cells using deep learning-based Morphogo system |
| title_fullStr | High-accuracy morphological identification of bone marrow cells using deep learning-based Morphogo system |
| title_full_unstemmed | High-accuracy morphological identification of bone marrow cells using deep learning-based Morphogo system |
| title_short | High-accuracy morphological identification of bone marrow cells using deep learning-based Morphogo system |
| title_sort | high accuracy morphological identification of bone marrow cells using deep learning based morphogo system |
| url | https://doi.org/10.1038/s41598-023-40424-x |
| work_keys_str_mv | AT zhanwulv highaccuracymorphologicalidentificationofbonemarrowcellsusingdeeplearningbasedmorphogosystem AT xinyicao highaccuracymorphologicalidentificationofbonemarrowcellsusingdeeplearningbasedmorphogosystem AT xinyijin highaccuracymorphologicalidentificationofbonemarrowcellsusingdeeplearningbasedmorphogosystem AT shuangqingxu highaccuracymorphologicalidentificationofbonemarrowcellsusingdeeplearningbasedmorphogosystem AT huanglingdeng highaccuracymorphologicalidentificationofbonemarrowcellsusingdeeplearningbasedmorphogosystem |