融合YOLO与U-Net的多阶段模型，提升巴氏涂片中宫颈细胞检测精度。
A Multi-Stage Optimization Pipeline for Bethesda Cell Detection in Pap Smear Cytology
- 采用YOLO与U-Net集成架构进行初步检测
- 通过重叠消除与二分类器实现结果优化，mAP50-95达0.5909
- 适合医学图像分析与宫颈癌筛查方向研究者参考
近年来，计算机视觉技术在医疗领域取得显著进展。本文针对国际生物医学成像研讨会（ISBI）主办的Riva细胞学挑战赛第B赛道，提出一种巴氏涂片中巴塞罗那细胞检测的新框架。该框架聚焦于提升细胞检测模型性能，使用mAP50-95作为评估指标。方法基于YOLO与U-Net架构的集成，后续加入重叠去除与二分类器进行精细化修正。最终在比赛中获得第二名，mAP50-95得分为0.5909。代码已开源，地址为github.com/martinamster/riva-trackb。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。