1
|
Wang CW, Huang SC, Lee YC, Shen YJ, Meng SI, Gaol JL. Deep learning for bone marrow cell detection and classification on whole-slide images. Med Image Anal 2021; 75:102270. [PMID: 34710655 DOI: 10.1016/j.media.2021.102270] [Citation(s) in RCA: 32] [Impact Index Per Article: 10.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2020] [Revised: 10/06/2021] [Accepted: 10/13/2021] [Indexed: 12/19/2022]
Abstract
Bone marrow (BM) examination is an essential step in both diagnosing and managing numerous hematologic disorders. BM nucleated differential count (NDC) analysis, as part of BM examination, holds the most fundamental and crucial information. However, there are many challenges to perform automated BM NDC analysis on whole-slide images (WSIs), including large dimensions of data to process, complicated cell types with subtle differences. To the authors best knowledge, this is the first study on fully automatic BM NDC using WSIs with 40x objective magnification, which can replace traditional manual counting relying on light microscopy via oil-immersion 100x objective lens with a total 1000x magnification. In this study, we develop an efficient and fully automatic hierarchical deep learning framework for BM NDC WSI analysis in seconds. The proposed hierarchical framework consists of (1) a deep learning model for rapid localization of BM particles and cellular trails generating regions of interest (ROI) for further analysis, (2) a patch-based deep learning model for cell identification of 16 cell types, including megakaryocytes, mitotic cells, and four stages of erythroblasts which have not been demonstrated in previous studies before, and (3) a fast stitching model for integrating patch-based results and producing final outputs. In evaluation, the proposed method is firstly tested on a dataset with a total of 12,426 annotated cells using cross validation, achieving high recall and accuracy of 0.905 ± 0.078 and 0.989 ± 0.006, respectively, and taking only 44 seconds to perform BM NDC analysis for a WSI. To further examine the generalizability of our model, we conduct an evaluation on the second independent dataset with a total of 3005 cells, and the results show that the proposed method also obtains high recall and accuracy of 0.842 and 0.988, respectively. In comparison with the existing small-image-based benchmark methods, the proposed method demonstrates superior performance in recall, accuracy and computational time.
Collapse
Affiliation(s)
- Ching-Wei Wang
- Graduate Institute of Biomedical Engineering, National Taiwan University of Science and Technology, Taipei, 106, Taiwan; Graduate Institute of Applied Science and Technology, National Taiwan University of Science and Technology, Taipei, 106, Taiwan.
| | - Sheng-Chuan Huang
- Department of Laboratory Medicine, National Taiwan University Hospital, Taipei, 100, Taiwan; Department of Hematology and Oncology, Hualien Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Hualien, Taiwan; Department of Clinical Pathology, Hualien Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Hualien, Taiwan
| | - Yu-Ching Lee
- Graduate Institute of Applied Science and Technology, National Taiwan University of Science and Technology, Taipei, 106, Taiwan
| | - Yu-Jie Shen
- Graduate Institute of Biomedical Engineering, National Taiwan University of Science and Technology, Taipei, 106, Taiwan
| | - Shwu-Ing Meng
- Department of Laboratory Medicine, National Taiwan University Hospital, Taipei, 100, Taiwan
| | - Jeff L Gaol
- Graduate Institute of Biomedical Engineering, National Taiwan University of Science and Technology, Taipei, 106, Taiwan
| |
Collapse
|