Cross-organ Deployment of EOS Detection AI without Retraining: Feasibility and Limitation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929603763765248 |
|---|---|
| author | Wu, Yifei Xiong, Juming Yao, Tianyuan Deng, Ruining Guo, Junlin Yue, Jialin Chowdhury, Naweed Huo, Yuankai |
| author_facet | Wu, Yifei Xiong, Juming Yao, Tianyuan Deng, Ruining Guo, Junlin Yue, Jialin Chowdhury, Naweed Huo, Yuankai |
| contents | Chronic rhinosinusitis (CRS) is characterized by persistent inflammation in the paranasal sinuses, leading to typical symptoms of nasal congestion, facial pressure, olfactory dysfunction, and discolored nasal drainage, which can significantly impact quality-of-life. Eosinophils (Eos), a crucial component in the mucosal immune response, have been linked to disease severity in CRS. The diagnosis of eosinophilic CRS typically uses a threshold of 10-20 eos per high-power field (HPF). However, manually counting Eos in histological samples is laborious and time-intensive, making the use of AI-driven methods for automated evaluations highly desirable. Interestingly, eosinophils are predominantly located in the gastrointestinal (GI) tract, which has prompted the release of numerous deep learning models trained on GI data. This study leverages a CircleSnake model initially trained on upper-GI data to segment Eos cells in whole slide images (WSIs) of nasal tissues. It aims to determine the extent to which Eos segmentation models developed for the GI tract can be adapted to nasal applications without retraining. The experimental results show promising accuracy in some WSIs, although, unsurprisingly, the performance varies across cases. This paper details these performance outcomes, delves into the reasons for such variations, and aims to provide insights that could guide future development of deep learning models for eosinophilic CRS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_15942 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cross-organ Deployment of EOS Detection AI without Retraining: Feasibility and Limitation Wu, Yifei Xiong, Juming Yao, Tianyuan Deng, Ruining Guo, Junlin Yue, Jialin Chowdhury, Naweed Huo, Yuankai Image and Video Processing Computer Vision and Pattern Recognition Chronic rhinosinusitis (CRS) is characterized by persistent inflammation in the paranasal sinuses, leading to typical symptoms of nasal congestion, facial pressure, olfactory dysfunction, and discolored nasal drainage, which can significantly impact quality-of-life. Eosinophils (Eos), a crucial component in the mucosal immune response, have been linked to disease severity in CRS. The diagnosis of eosinophilic CRS typically uses a threshold of 10-20 eos per high-power field (HPF). However, manually counting Eos in histological samples is laborious and time-intensive, making the use of AI-driven methods for automated evaluations highly desirable. Interestingly, eosinophils are predominantly located in the gastrointestinal (GI) tract, which has prompted the release of numerous deep learning models trained on GI data. This study leverages a CircleSnake model initially trained on upper-GI data to segment Eos cells in whole slide images (WSIs) of nasal tissues. It aims to determine the extent to which Eos segmentation models developed for the GI tract can be adapted to nasal applications without retraining. The experimental results show promising accuracy in some WSIs, although, unsurprisingly, the performance varies across cases. This paper details these performance outcomes, delves into the reasons for such variations, and aims to provide insights that could guide future development of deep learning models for eosinophilic CRS. |
| title | Cross-organ Deployment of EOS Detection AI without Retraining: Feasibility and Limitation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.15942 |