# Detecting Lesion Bounding Ellipses With Gaussian Proposal Networks

arXiv: https://arxiv.org/abs/1902.09658 · HTML: https://mlsanity.com/paper/1902.09658/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2019.

## Built on by (most cited first, 6 of 6)

- [Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization](https://mlsanity.com/paper/2209.10839/) (2022)
- [Wholly-WOOD: Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection](https://mlsanity.com/paper/2502.09471/) (2025)
- [EllipseNet: Anchor-Free Ellipse Detection for Automatic Cardiac Biometrics in Fetal Echocardiography](https://mlsanity.com/paper/2109.12474/) (2021)
- [Perspective-1-Ellipsoid: Formulation, Analysis and Solutions of the Camera Pose Estimation Problem from One Ellipse-Ellipsoid Correspondence](https://mlsanity.com/paper/2208.12513/) (2022)
- [Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning](https://mlsanity.com/paper/2412.11582/) (2024)
- [3D-Aware Object Localization using Gaussian Implicit Occupancy Function](https://mlsanity.com/paper/2303.02058/) (2023)

## Abstract (arXiv)

Lesions characterized by computed tomography (CT) scans, are arguably often elliptical objects. However, current lesion detection systems are predominantly adopted from the popular Region Proposal Networks (RPNs) that only propose bounding boxes without fully leveraging the elliptical geometry of lesions. In this paper, we present Gaussian Proposal Networks (GPNs), a novel extension to RPNs, to detect lesion bounding ellipses. Instead of directly regressing the rotation angle of the ellipse as the common practice, GPN represents bounding ellipses as 2D Gaussian distributions on the image plain and minimizes the Kullback-Leibler (KL) divergence between the proposed Gaussian and the ground truth Gaussian for object localization. We show the KL divergence loss approximately incarnates the regression loss in the RPN framework when the rotation angle is 0. Experiments on the DeepLesion dataset show that GPN significantly outperforms RPN for lesion bounding ellipse detection thanks to lower localization error. GPN is open sourced at https://github.com/baidu-research/GPN