Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.09310 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910697692069888 |
|---|---|
| author | Marzullo, Aldo Ranzini, Marta Bianca Maria |
| author_facet | Marzullo, Aldo Ranzini, Marta Bianca Maria |
| contents | Zero-shot anomaly detection (ZSAD) offers potential for identifying anomalies in medical imaging without task-specific training. In this paper, we evaluate CLIP-based models, originally developed for industrial tasks, on brain tumor detection using the BraTS-MET dataset. Our analysis examines their ability to detect medical-specific anomalies with no or minimal supervision, addressing the challenges posed by limited data annotation. While these models show promise in transferring general knowledge to medical tasks, their performance falls short of the precision required for clinical use. Our findings highlight the need for further adaptation before CLIP-based models can be reliably applied to medical anomaly detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_09310 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring Zero-Shot Anomaly Detection with CLIP in Medical Imaging: Are We There Yet? Marzullo, Aldo Ranzini, Marta Bianca Maria Computer Vision and Pattern Recognition I.4.6 Zero-shot anomaly detection (ZSAD) offers potential for identifying anomalies in medical imaging without task-specific training. In this paper, we evaluate CLIP-based models, originally developed for industrial tasks, on brain tumor detection using the BraTS-MET dataset. Our analysis examines their ability to detect medical-specific anomalies with no or minimal supervision, addressing the challenges posed by limited data annotation. While these models show promise in transferring general knowledge to medical tasks, their performance falls short of the precision required for clinical use. Our findings highlight the need for further adaptation before CLIP-based models can be reliably applied to medical anomaly detection. |
| title | Exploring Zero-Shot Anomaly Detection with CLIP in Medical Imaging: Are We There Yet? |
| topic | Computer Vision and Pattern Recognition I.4.6 |
| url | https://arxiv.org/abs/2411.09310 |