Ensemble Deep Learning Object Detection Fusion for Cell Tracking, Mitosis, and Lineage
Cell tracking and motility analysis are essential for understanding multicellular processes, automated quantification in biomedical experiments, and medical diagnosis and treatment. However, manual tracking is labor-intensive, tedious, and prone to selection bias and errors. Building upon our previo...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Engineering in Medicine and Biology |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10159213/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583982994161664 |
|---|---|
| author | Imad Eddine Toubal Noor Al-Shakarji D. D. W. Cornelison Kannappan Palaniappan |
| author_facet | Imad Eddine Toubal Noor Al-Shakarji D. D. W. Cornelison Kannappan Palaniappan |
| author_sort | Imad Eddine Toubal |
| collection | DOAJ |
| description | Cell tracking and motility analysis are essential for understanding multicellular processes, automated quantification in biomedical experiments, and medical diagnosis and treatment. However, manual tracking is labor-intensive, tedious, and prone to selection bias and errors. Building upon our previous work, we propose a new deep learning-based method, EDNet, for cell detection, tracking, and motility analysis that is more robust to shape across different cell lines, and models cell lineage and proliferation. EDNet uses an ensemble approach for 2D cell detection that is deep-architecture-agnostic and achieves state-of-the-art performance surpassing single-model YOLO and FasterRCNN convolutional neural networks. EDNet detections are used in our M2Track multiobject tracking algorithm for tracking cells, detecting cell mitosis (cell division) events, and cell lineage graphs. Our methods produce state-of-the-art performance on the Cell Tracking and Mitosis (CTMCv1) dataset with a Multiple Object Tracking Accuracy (MOTA) score of 50.6% and tracking lineage graph edit (TRA) score of 52.5%. Additionally, we compare our detection and tracking methods to human performance on external data in studying the motility of muscle stem cells with different physiological and molecular stimuli. We believe that our method has the potential to improve the accuracy and efficiency of cell tracking and motility analysis. This could lead to significant advances in biomedical research and medical diagnosis. Our code is made publicly available on GitHub. |
| format | Article |
| id | doaj-art-736f3a9e70a74b4fb938a69c9c1a91a1 |
| institution | Kabale University |
| issn | 2644-1276 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Engineering in Medicine and Biology |
| spelling | doaj-art-736f3a9e70a74b4fb938a69c9c1a91a12025-01-28T00:02:12ZengIEEEIEEE Open Journal of Engineering in Medicine and Biology2644-12762024-01-01544345810.1109/OJEMB.2023.328847010159213Ensemble Deep Learning Object Detection Fusion for Cell Tracking, Mitosis, and LineageImad Eddine Toubal0https://orcid.org/0000-0003-1754-0823Noor Al-Shakarji1D. D. W. Cornelison2Kannappan Palaniappan3https://orcid.org/0000-0003-2663-1380Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USADepartment of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USAChristopher S. Bond Life Sciences Center, University of Missouri, Columbia, MO, USADepartment of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USACell tracking and motility analysis are essential for understanding multicellular processes, automated quantification in biomedical experiments, and medical diagnosis and treatment. However, manual tracking is labor-intensive, tedious, and prone to selection bias and errors. Building upon our previous work, we propose a new deep learning-based method, EDNet, for cell detection, tracking, and motility analysis that is more robust to shape across different cell lines, and models cell lineage and proliferation. EDNet uses an ensemble approach for 2D cell detection that is deep-architecture-agnostic and achieves state-of-the-art performance surpassing single-model YOLO and FasterRCNN convolutional neural networks. EDNet detections are used in our M2Track multiobject tracking algorithm for tracking cells, detecting cell mitosis (cell division) events, and cell lineage graphs. Our methods produce state-of-the-art performance on the Cell Tracking and Mitosis (CTMCv1) dataset with a Multiple Object Tracking Accuracy (MOTA) score of 50.6% and tracking lineage graph edit (TRA) score of 52.5%. Additionally, we compare our detection and tracking methods to human performance on external data in studying the motility of muscle stem cells with different physiological and molecular stimuli. We believe that our method has the potential to improve the accuracy and efficiency of cell tracking and motility analysis. This could lead to significant advances in biomedical research and medical diagnosis. Our code is made publicly available on GitHub.https://ieeexplore.ieee.org/document/10159213/Cell trackingdeep learningdetectionensemblemultiobject trackingdeformable object tracking |
| spellingShingle | Imad Eddine Toubal Noor Al-Shakarji D. D. W. Cornelison Kannappan Palaniappan Ensemble Deep Learning Object Detection Fusion for Cell Tracking, Mitosis, and Lineage IEEE Open Journal of Engineering in Medicine and Biology Cell tracking deep learning detection ensemble multiobject tracking deformable object tracking |
| title | Ensemble Deep Learning Object Detection Fusion for Cell Tracking, Mitosis, and Lineage |
| title_full | Ensemble Deep Learning Object Detection Fusion for Cell Tracking, Mitosis, and Lineage |
| title_fullStr | Ensemble Deep Learning Object Detection Fusion for Cell Tracking, Mitosis, and Lineage |
| title_full_unstemmed | Ensemble Deep Learning Object Detection Fusion for Cell Tracking, Mitosis, and Lineage |
| title_short | Ensemble Deep Learning Object Detection Fusion for Cell Tracking, Mitosis, and Lineage |
| title_sort | ensemble deep learning object detection fusion for cell tracking mitosis and lineage |
| topic | Cell tracking deep learning detection ensemble multiobject tracking deformable object tracking |
| url | https://ieeexplore.ieee.org/document/10159213/ |
| work_keys_str_mv | AT imadeddinetoubal ensembledeeplearningobjectdetectionfusionforcelltrackingmitosisandlineage AT nooralshakarji ensembledeeplearningobjectdetectionfusionforcelltrackingmitosisandlineage AT ddwcornelison ensembledeeplearningobjectdetectionfusionforcelltrackingmitosisandlineage AT kannappanpalaniappan ensembledeeplearningobjectdetectionfusionforcelltrackingmitosisandlineage |