Weighted Circle Fusion: Ensembling Circle Representation from Different Object Detection Results

TL;DR

This paper introduces Weighted Circle Fusion, a novel ensemble method for merging circle detection results from multiple models, improving accuracy in medical imaging applications like glomeruli detection.

Contribution

The paper presents a simple, confidence-based circle merging technique that enhances detection accuracy and reduces false positives in circle-based object detection tasks.

Findings

Achieved 5% performance improvement over existing ensemble methods.

Demonstrated effectiveness on a proprietary glomerular detection dataset.

Showed that HITL annotation significantly improves labeling efficiency.

Abstract

Recently, the use of circle representation has emerged as a method to improve the identification of spherical objects (such as glomeruli, cells, and nuclei) in medical imaging studies. In traditional bounding box-based object detection, combining results from multiple models improves accuracy, especially when real-time processing isn't crucial. Unfortunately, this widely adopted strategy is not readily available for combining circle representations. In this paper, we propose Weighted Circle Fusion (WCF), a simple approach for merging predictions from various circle detection models. Our method leverages confidence scores associated with each proposed bounding circle to generate averaged circles. We evaluate our method on a proprietary dataset for glomerular detection in whole slide imaging (WSI) and find a performance gain of 5% compared to existing ensemble methods. Additionally, we assess the efficiency of two annotation methods, fully manual annotation and a human-in-the-loop (HITL) approach, in labeling 200,000 glomeruli. The HITL approach, which integrates machine learning detection with human verification, demonstrated remarkable improvements in annotation efficiency. The Weighted Circle Fusion technique not only enhances object detection precision but also notably reduces false detections, presenting a promising direction for future research and application in pathological image analysis. The source code has been made publicly available at https://github.com/hrlblab/WeightedCircleFusion