Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.13939 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913035344412672 |
|---|---|
| author | Amster, Martin Polotto, Camila María |
| author_facet | Amster, Martin Polotto, Camila María |
| contents | Computer vision techniques have advanced significantly in recent years, finding diverse and impactful applications within the medical field. In this paper, we introduce a new framework for the detection of Bethesda cells in Pap smear images, developed for Track B of the Riva Cytology Challenge held in association with the International Symposium on Biomedical Imaging (ISBI). This work focuses on enhancing computer vision models for cell detection, with performance evaluated using the mAP50-95 metric. We propose a solution based on an ensemble of YOLO and U-Net architectures, followed by a refinement stage utilizing overlap removal techniques and a binary classifier. Our framework achieved second place with a mAP50-95 score of 0.5909 in the competition. The implementation and source code are available at the following repository: github.com/martinamster/riva-trackb |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13939 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Multi-Stage Optimization Pipeline for Bethesda Cell Detection in Pap Smear Cytology Amster, Martin Polotto, Camila María Computer Vision and Pattern Recognition Computer vision techniques have advanced significantly in recent years, finding diverse and impactful applications within the medical field. In this paper, we introduce a new framework for the detection of Bethesda cells in Pap smear images, developed for Track B of the Riva Cytology Challenge held in association with the International Symposium on Biomedical Imaging (ISBI). This work focuses on enhancing computer vision models for cell detection, with performance evaluated using the mAP50-95 metric. We propose a solution based on an ensemble of YOLO and U-Net architectures, followed by a refinement stage utilizing overlap removal techniques and a binary classifier. Our framework achieved second place with a mAP50-95 score of 0.5909 in the competition. The implementation and source code are available at the following repository: github.com/martinamster/riva-trackb |
| title | A Multi-Stage Optimization Pipeline for Bethesda Cell Detection in Pap Smear Cytology |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.13939 |