A Multi-Stage Optimization Pipeline for Bethesda Cell Detection in Pap Smear Cytology

TL;DR

This paper presents a multi-stage ensemble framework combining YOLO and U-Net models, with refinement techniques, for detecting Bethesda cells in Pap smear images, achieving high accuracy in a competitive challenge.

Contribution

The authors develop a novel multi-stage pipeline integrating ensemble models and refinement steps for improved cell detection in cytology images.

Findings

Achieved a mAP50-95 score of 0.5909 in the Riva Cytology Challenge.

Outperformed baseline models with an ensemble approach and refinement techniques.

Secured second place in the competition with the proposed method.

Abstract

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