A Weakly Supervised Learning Method for Cell Detection and Tracking Using Incomplete Initial Annotations
The automatic detection of cells in microscopy image sequences is a significant task in biomedical research. However, routine microscopy images with cells, which are taken during the process whereby constant division and differentiation occur, are notoriously difficult to detect due to changes in th...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/24/22/16028 |
| _version_ | 1797459036579299328 |
|---|---|
| author | Hao Wu Jovial Niyogisubizo Keliang Zhao Jintao Meng Wenhui Xi Hongchang Li Yi Pan Yanjie Wei |
| author_facet | Hao Wu Jovial Niyogisubizo Keliang Zhao Jintao Meng Wenhui Xi Hongchang Li Yi Pan Yanjie Wei |
| author_sort | Hao Wu |
| collection | DOAJ |
| description | The automatic detection of cells in microscopy image sequences is a significant task in biomedical research. However, routine microscopy images with cells, which are taken during the process whereby constant division and differentiation occur, are notoriously difficult to detect due to changes in their appearance and number. Recently, convolutional neural network (CNN)-based methods have made significant progress in cell detection and tracking. However, these approaches require many manually annotated data for fully supervised training, which is time-consuming and often requires professional researchers. To alleviate such tiresome and labor-intensive costs, we propose a novel weakly supervised learning cell detection and tracking framework that trains the deep neural network using incomplete initial labels. Our approach uses incomplete cell markers obtained from fluorescent images for initial training on the Induced Pluripotent Stem (iPS) cell dataset, which is rarely studied for cell detection and tracking. During training, the incomplete initial labels were updated iteratively by combining detection and tracking results to obtain a model with better robustness. Our method was evaluated using two fields of the iPS cell dataset, along with the cell detection accuracy (DET) evaluation metric from the Cell Tracking Challenge (CTC) initiative, and it achieved 0.862 and 0.924 DET, respectively. The transferability of the developed model was tested using the public dataset FluoN2DH-GOWT1, which was taken from CTC; this contains two datasets with reference annotations. We randomly removed parts of the annotations in each labeled data to simulate the initial annotations on the public dataset. After training the model on the two datasets, with labels that comprise 10% cell markers, the DET improved from 0.130 to 0.903 and 0.116 to 0.877. When trained with labels that comprise 60% cell markers, the performance was better than the model trained using the supervised learning method. This outcome indicates that the model’s performance improved as the quality of the labels used for training increased. |
| first_indexed | 2024-03-09T16:46:41Z |
| format | Article |
| id | doaj.art-1d3b8d4966ea4addbc9fdc73335ac796 |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-09T16:46:41Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-1d3b8d4966ea4addbc9fdc73335ac7962023-11-24T14:45:36ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672023-11-0124221602810.3390/ijms242216028A Weakly Supervised Learning Method for Cell Detection and Tracking Using Incomplete Initial AnnotationsHao Wu0Jovial Niyogisubizo1Keliang Zhao2Jintao Meng3Wenhui Xi4Hongchang Li5Yi Pan6Yanjie Wei7Shenzhen Key Laboratory of Intelligent Bioinformatics and Center for High Performance Computing, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaShenzhen Key Laboratory of Intelligent Bioinformatics and Center for High Performance Computing, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaShenzhen Key Laboratory of Intelligent Bioinformatics and Center for High Performance Computing, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaShenzhen Key Laboratory of Intelligent Bioinformatics and Center for High Performance Computing, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaShenzhen Key Laboratory of Intelligent Bioinformatics and Center for High Performance Computing, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaInstitute of Biomedicine and Biotechnology, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaCollege of Computer Science and Control Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaShenzhen Key Laboratory of Intelligent Bioinformatics and Center for High Performance Computing, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaThe automatic detection of cells in microscopy image sequences is a significant task in biomedical research. However, routine microscopy images with cells, which are taken during the process whereby constant division and differentiation occur, are notoriously difficult to detect due to changes in their appearance and number. Recently, convolutional neural network (CNN)-based methods have made significant progress in cell detection and tracking. However, these approaches require many manually annotated data for fully supervised training, which is time-consuming and often requires professional researchers. To alleviate such tiresome and labor-intensive costs, we propose a novel weakly supervised learning cell detection and tracking framework that trains the deep neural network using incomplete initial labels. Our approach uses incomplete cell markers obtained from fluorescent images for initial training on the Induced Pluripotent Stem (iPS) cell dataset, which is rarely studied for cell detection and tracking. During training, the incomplete initial labels were updated iteratively by combining detection and tracking results to obtain a model with better robustness. Our method was evaluated using two fields of the iPS cell dataset, along with the cell detection accuracy (DET) evaluation metric from the Cell Tracking Challenge (CTC) initiative, and it achieved 0.862 and 0.924 DET, respectively. The transferability of the developed model was tested using the public dataset FluoN2DH-GOWT1, which was taken from CTC; this contains two datasets with reference annotations. We randomly removed parts of the annotations in each labeled data to simulate the initial annotations on the public dataset. After training the model on the two datasets, with labels that comprise 10% cell markers, the DET improved from 0.130 to 0.903 and 0.116 to 0.877. When trained with labels that comprise 60% cell markers, the performance was better than the model trained using the supervised learning method. This outcome indicates that the model’s performance improved as the quality of the labels used for training increased.https://www.mdpi.com/1422-0067/24/22/16028cell detectioncell trackingdeep learningweakly supervised learningiPS cell reprogrammingbrightfield microscopy |
| spellingShingle | Hao Wu Jovial Niyogisubizo Keliang Zhao Jintao Meng Wenhui Xi Hongchang Li Yi Pan Yanjie Wei A Weakly Supervised Learning Method for Cell Detection and Tracking Using Incomplete Initial Annotations International Journal of Molecular Sciences cell detection cell tracking deep learning weakly supervised learning iPS cell reprogramming brightfield microscopy |
| title | A Weakly Supervised Learning Method for Cell Detection and Tracking Using Incomplete Initial Annotations |
| title_full | A Weakly Supervised Learning Method for Cell Detection and Tracking Using Incomplete Initial Annotations |
| title_fullStr | A Weakly Supervised Learning Method for Cell Detection and Tracking Using Incomplete Initial Annotations |
| title_full_unstemmed | A Weakly Supervised Learning Method for Cell Detection and Tracking Using Incomplete Initial Annotations |
| title_short | A Weakly Supervised Learning Method for Cell Detection and Tracking Using Incomplete Initial Annotations |
| title_sort | weakly supervised learning method for cell detection and tracking using incomplete initial annotations |
| topic | cell detection cell tracking deep learning weakly supervised learning iPS cell reprogramming brightfield microscopy |
| url | https://www.mdpi.com/1422-0067/24/22/16028 |
| work_keys_str_mv | AT haowu aweaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT jovialniyogisubizo aweaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT keliangzhao aweaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT jintaomeng aweaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT wenhuixi aweaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT hongchangli aweaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT yipan aweaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT yanjiewei aweaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT haowu weaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT jovialniyogisubizo weaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT keliangzhao weaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT jintaomeng weaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT wenhuixi weaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT hongchangli weaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT yipan weaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations AT yanjiewei weaklysupervisedlearningmethodforcelldetectionandtrackingusingincompleteinitialannotations |