Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.09153 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912581965316096 |
|---|---|
| author | Shin, JaeWoong Ryu, Jeongun Puche, Aaron Valero Lee, Jinhee Brattoli, Biagio Jung, Wonkyung Cho, Soo Ick Paeng, Kyunghyun Ock, Chan-Young Yoo, Donggeun Li, Zhaoyang Li, Wangkai Mai, Huayu Millward, Joshua He, Zhen Nibali, Aiden Schoenpflug, Lydia Anette Koelzer, Viktor Hendrik Shuoyu, Xu Zheng, Ji Bin, Hu Lo, Yu-Wen Yang, Ching-Hui Pereira, Sérgio |
| author_facet | Shin, JaeWoong Ryu, Jeongun Puche, Aaron Valero Lee, Jinhee Brattoli, Biagio Jung, Wonkyung Cho, Soo Ick Paeng, Kyunghyun Ock, Chan-Young Yoo, Donggeun Li, Zhaoyang Li, Wangkai Mai, Huayu Millward, Joshua He, Zhen Nibali, Aiden Schoenpflug, Lydia Anette Koelzer, Viktor Hendrik Shuoyu, Xu Zheng, Ji Bin, Hu Lo, Yu-Wen Yang, Ching-Hui Pereira, Sérgio |
| contents | Pathologists routinely alternate between different magnifications when examining Whole-Slide Images, allowing them to evaluate both broad tissue morphology and intricate cellular details to form comprehensive diagnoses. However, existing deep learning-based cell detection models struggle to replicate these behaviors and learn the interdependent semantics between structures at different magnifications. A key barrier in the field is the lack of datasets with multi-scale overlapping cell and tissue annotations. The OCELOT 2023 challenge was initiated to gather insights from the community to validate the hypothesis that understanding cell and tissue (cell-tissue) interactions is crucial for achieving human-level performance, and to accelerate the research in this field. The challenge dataset includes overlapping cell detection and tissue segmentation annotations from six organs, comprising 673 pairs sourced from 306 The Cancer Genome Atlas (TCGA) Whole-Slide Images with hematoxylin and eosin staining, divided into training, validation, and test subsets. Participants presented models that significantly enhanced the understanding of cell-tissue relationships. Top entries achieved up to a 7.99 increase in F1-score on the test set compared to the baseline cell-only model that did not incorporate cell-tissue relationships. This is a substantial improvement in performance over traditional cell-only detection methods, demonstrating the need for incorporating multi-scale semantics into the models. This paper provides a comparative analysis of the methods used by participants, highlighting innovative strategies implemented in the OCELOT 2023 challenge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09153 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OCELOT 2023: Cell Detection from Cell-Tissue Interaction Challenge Shin, JaeWoong Ryu, Jeongun Puche, Aaron Valero Lee, Jinhee Brattoli, Biagio Jung, Wonkyung Cho, Soo Ick Paeng, Kyunghyun Ock, Chan-Young Yoo, Donggeun Li, Zhaoyang Li, Wangkai Mai, Huayu Millward, Joshua He, Zhen Nibali, Aiden Schoenpflug, Lydia Anette Koelzer, Viktor Hendrik Shuoyu, Xu Zheng, Ji Bin, Hu Lo, Yu-Wen Yang, Ching-Hui Pereira, Sérgio Computer Vision and Pattern Recognition Artificial Intelligence Pathologists routinely alternate between different magnifications when examining Whole-Slide Images, allowing them to evaluate both broad tissue morphology and intricate cellular details to form comprehensive diagnoses. However, existing deep learning-based cell detection models struggle to replicate these behaviors and learn the interdependent semantics between structures at different magnifications. A key barrier in the field is the lack of datasets with multi-scale overlapping cell and tissue annotations. The OCELOT 2023 challenge was initiated to gather insights from the community to validate the hypothesis that understanding cell and tissue (cell-tissue) interactions is crucial for achieving human-level performance, and to accelerate the research in this field. The challenge dataset includes overlapping cell detection and tissue segmentation annotations from six organs, comprising 673 pairs sourced from 306 The Cancer Genome Atlas (TCGA) Whole-Slide Images with hematoxylin and eosin staining, divided into training, validation, and test subsets. Participants presented models that significantly enhanced the understanding of cell-tissue relationships. Top entries achieved up to a 7.99 increase in F1-score on the test set compared to the baseline cell-only model that did not incorporate cell-tissue relationships. This is a substantial improvement in performance over traditional cell-only detection methods, demonstrating the need for incorporating multi-scale semantics into the models. This paper provides a comparative analysis of the methods used by participants, highlighting innovative strategies implemented in the OCELOT 2023 challenge. |
| title | OCELOT 2023: Cell Detection from Cell-Tissue Interaction Challenge |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.09153 |