OC_Finder: Osteoclast Segmentation, Counting, and Classification Using Watershed and Deep Learning
Osteoclasts are multinucleated cells that exclusively resorb bone matrix proteins and minerals on the bone surface. They differentiate from monocyte/macrophage lineage cells in the presence of osteoclastogenic cytokines such as the receptor activator of nuclear factor-κB ligand (RANKL) and are stain...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-03-01
|
| Series: | Frontiers in Bioinformatics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbinf.2022.819570/full |
| _version_ | 1819178046518722560 |
|---|---|
| author | Xiao Wang Mizuho Kittaka Mizuho Kittaka Yilin He Yiwei Zhang Yasuyoshi Ueki Yasuyoshi Ueki Daisuke Kihara Daisuke Kihara Daisuke Kihara |
| author_facet | Xiao Wang Mizuho Kittaka Mizuho Kittaka Yilin He Yiwei Zhang Yasuyoshi Ueki Yasuyoshi Ueki Daisuke Kihara Daisuke Kihara Daisuke Kihara |
| author_sort | Xiao Wang |
| collection | DOAJ |
| description | Osteoclasts are multinucleated cells that exclusively resorb bone matrix proteins and minerals on the bone surface. They differentiate from monocyte/macrophage lineage cells in the presence of osteoclastogenic cytokines such as the receptor activator of nuclear factor-κB ligand (RANKL) and are stained positive for tartrate-resistant acid phosphatase (TRAP). In vitro osteoclast formation assays are commonly used to assess the capacity of osteoclast precursor cells for differentiating into osteoclasts wherein the number of TRAP-positive multinucleated cells is counted as osteoclasts. Osteoclasts are manually identified on cell culture dishes by human eyes, which is a labor-intensive process. Moreover, the manual procedure is not objective and results in lack of reproducibility. To accelerate the process and reduce the workload for counting the number of osteoclasts, we developed OC_Finder, a fully automated system for identifying osteoclasts in microscopic images. OC_Finder consists of cell image segmentation with a watershed algorithm and cell classification using deep learning. OC_Finder detected osteoclasts differentiated from wild-type and Sh3bp2KI/+ precursor cells at a 99.4% accuracy for segmentation and at a 98.1% accuracy for classification. The number of osteoclasts classified by OC_Finder was at the same accuracy level with manual counting by a human expert. OC_Finder also showed consistent performance on additional datasets collected with different microscopes with different settings by different operators. Together, successful development of OC_Finder suggests that deep learning is a useful tool to perform prompt and accurate unbiased classification and detection of specific cell types in microscopic images. |
| first_indexed | 2024-12-22T21:36:19Z |
| format | Article |
| id | doaj.art-c76e88be9b594650b3f8d83463694eaf |
| institution | Directory Open Access Journal |
| issn | 2673-7647 |
| language | English |
| last_indexed | 2024-12-22T21:36:19Z |
| publishDate | 2022-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Bioinformatics |
| spelling | doaj.art-c76e88be9b594650b3f8d83463694eaf2022-12-21T18:11:44ZengFrontiers Media S.A.Frontiers in Bioinformatics2673-76472022-03-01210.3389/fbinf.2022.819570819570OC_Finder: Osteoclast Segmentation, Counting, and Classification Using Watershed and Deep LearningXiao Wang0Mizuho Kittaka1Mizuho Kittaka2Yilin He3Yiwei Zhang4Yasuyoshi Ueki5Yasuyoshi Ueki6Daisuke Kihara7Daisuke Kihara8Daisuke Kihara9Department of Computer Science, Purdue University, West Lafayette, IN, United StatesDepartment of Biomedical Sciences and Comprehensive Care, Indiana University School of Dentistry, Indianapolis, IN, United StatesIndiana Center for Musculoskeletal Health, Indiana University School of Medicine, Indianapolis, IN, United StatesSchool of Software Engineering, Shandong University, Jinan, ChinaDepartment of Computer Science, Rensselaer Polytechnic Institute, Troy, NY, United StatesDepartment of Biomedical Sciences and Comprehensive Care, Indiana University School of Dentistry, Indianapolis, IN, United StatesIndiana Center for Musculoskeletal Health, Indiana University School of Medicine, Indianapolis, IN, United StatesDepartment of Computer Science, Purdue University, West Lafayette, IN, United StatesDepartment of Biological Sciences, Purdue University, West Lafayette, IN, United StatesPurdue Cancer Research Institute, Purdue University, West Lafayette, IN, United StatesOsteoclasts are multinucleated cells that exclusively resorb bone matrix proteins and minerals on the bone surface. They differentiate from monocyte/macrophage lineage cells in the presence of osteoclastogenic cytokines such as the receptor activator of nuclear factor-κB ligand (RANKL) and are stained positive for tartrate-resistant acid phosphatase (TRAP). In vitro osteoclast formation assays are commonly used to assess the capacity of osteoclast precursor cells for differentiating into osteoclasts wherein the number of TRAP-positive multinucleated cells is counted as osteoclasts. Osteoclasts are manually identified on cell culture dishes by human eyes, which is a labor-intensive process. Moreover, the manual procedure is not objective and results in lack of reproducibility. To accelerate the process and reduce the workload for counting the number of osteoclasts, we developed OC_Finder, a fully automated system for identifying osteoclasts in microscopic images. OC_Finder consists of cell image segmentation with a watershed algorithm and cell classification using deep learning. OC_Finder detected osteoclasts differentiated from wild-type and Sh3bp2KI/+ precursor cells at a 99.4% accuracy for segmentation and at a 98.1% accuracy for classification. The number of osteoclasts classified by OC_Finder was at the same accuracy level with manual counting by a human expert. OC_Finder also showed consistent performance on additional datasets collected with different microscopes with different settings by different operators. Together, successful development of OC_Finder suggests that deep learning is a useful tool to perform prompt and accurate unbiased classification and detection of specific cell types in microscopic images.https://www.frontiersin.org/articles/10.3389/fbinf.2022.819570/fulldeep learningosteoclast segmentationosteoclast countingautomatic segmentationopen source software |
| spellingShingle | Xiao Wang Mizuho Kittaka Mizuho Kittaka Yilin He Yiwei Zhang Yasuyoshi Ueki Yasuyoshi Ueki Daisuke Kihara Daisuke Kihara Daisuke Kihara OC_Finder: Osteoclast Segmentation, Counting, and Classification Using Watershed and Deep Learning Frontiers in Bioinformatics deep learning osteoclast segmentation osteoclast counting automatic segmentation open source software |
| title | OC_Finder: Osteoclast Segmentation, Counting, and Classification Using Watershed and Deep Learning |
| title_full | OC_Finder: Osteoclast Segmentation, Counting, and Classification Using Watershed and Deep Learning |
| title_fullStr | OC_Finder: Osteoclast Segmentation, Counting, and Classification Using Watershed and Deep Learning |
| title_full_unstemmed | OC_Finder: Osteoclast Segmentation, Counting, and Classification Using Watershed and Deep Learning |
| title_short | OC_Finder: Osteoclast Segmentation, Counting, and Classification Using Watershed and Deep Learning |
| title_sort | oc finder osteoclast segmentation counting and classification using watershed and deep learning |
| topic | deep learning osteoclast segmentation osteoclast counting automatic segmentation open source software |
| url | https://www.frontiersin.org/articles/10.3389/fbinf.2022.819570/full |
| work_keys_str_mv | AT xiaowang ocfinderosteoclastsegmentationcountingandclassificationusingwatershedanddeeplearning AT mizuhokittaka ocfinderosteoclastsegmentationcountingandclassificationusingwatershedanddeeplearning AT mizuhokittaka ocfinderosteoclastsegmentationcountingandclassificationusingwatershedanddeeplearning AT yilinhe ocfinderosteoclastsegmentationcountingandclassificationusingwatershedanddeeplearning AT yiweizhang ocfinderosteoclastsegmentationcountingandclassificationusingwatershedanddeeplearning AT yasuyoshiueki ocfinderosteoclastsegmentationcountingandclassificationusingwatershedanddeeplearning AT yasuyoshiueki ocfinderosteoclastsegmentationcountingandclassificationusingwatershedanddeeplearning AT daisukekihara ocfinderosteoclastsegmentationcountingandclassificationusingwatershedanddeeplearning AT daisukekihara ocfinderosteoclastsegmentationcountingandclassificationusingwatershedanddeeplearning AT daisukekihara ocfinderosteoclastsegmentationcountingandclassificationusingwatershedanddeeplearning |