Circle Representation for Medical Object Detection

10/22/2021
by   Ethan H. Nguyen, et al.
0

Box representation has been extensively used for object detection in computer vision. Such representation is efficacious but not necessarily optimized for biomedical objects (e.g., glomeruli), which play an essential role in renal pathology. In this paper, we propose a simple circle representation for medical object detection and introduce CircleNet, an anchor-free detection framework. Compared with the conventional bounding box representation, the proposed bounding circle representation innovates in three-fold: (1) it is optimized for ball-shaped biomedical objects; (2) The circle representation reduced the degree of freedom compared with box representation; (3) It is naturally more rotation invariant. When detecting glomeruli and nuclei on pathological images, the proposed circle representation achieved superior detection performance and be more rotation-invariant, compared with the bounding box. The code has been made publicly available: https://github.com/hrlblab/CircleNet

READ FULL TEXT

page 2

page 5

page 7

research
06/03/2020

CircleNet: Anchor-free Detection with Circle Representation

Object detection networks are powerful in computer vision, but not neces...
research
09/28/2021

Towards Rotation Invariance in Object Detection

Rotation augmentations generally improve a model's invariance/equivarian...
research
11/26/2017

Learning a Rotation Invariant Detector with Rotatable Bounding Box

Detection of arbitrarily rotated objects is a challenging task due to th...
research
08/30/2023

CircleFormer: Circular Nuclei Detection in Whole Slide Images with Circle Queries and Attention

Both CNN-based and Transformer-based object detection with bounding box ...
research
05/22/2023

nnDetection for Intracranial Aneurysms Detection and Localization

Intracranial aneurysms are a commonly occurring and life-threatening con...
research
05/06/2022

Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection

Dark environment becomes a challenge for computer vision algorithms owin...
research
11/02/2022

CircleSnake: Instance Segmentation with Circle Representation

Circle representation has recently been introduced as a medical imaging ...

Please sign up or login with your details

Forgot password? Click here to reset