Feature Aggregation and Refinement Network for 2D Anatomical Landmark Detection
- 18 November 2022
- journal article
- research article
- Published by Springer Nature in Journal of Digital Imaging
- Vol. 36 (2) , 547-561
Abstract
Localization of anatomical landmarks is essential for clinical diagnosis, treatment planning, and research. This paper proposes a novel deep network named feature aggregation and refinement network (FARNet) for automatically detecting anatomical landmarks. FARNet employs an encoder-decoder structure architecture. To alleviate the problem of limited training data in the medical domain, we adopt a backbone network pre-trained on natural images as the encoder. The decoder includes a multi-scale feature aggregation module for multi-scale feature fusion and a feature refinement module for high-resolution heatmap regression. Coarse-to-fine supervisions are applied to the two modules to facilitate end-to-end training. We further propose a novel loss function named Exponential Weighted Center loss for accurate heatmap regression, which focuses on the losses from the pixels near landmarks and suppresses the ones from far away. We evaluate FARNet on three publicly available anatomical landmark detection datasets, including cephalometric, hand, and spine radiographs. Our network achieves state-of-the-art performances on all three datasets. Code is available at https://github.com/JuvenileInWind/FARNet.Keywords
All Related Versions
This publication has 53 references indexed in Scilit:
- Regression forests for efficient anatomy detection and localization in computed tomography scansMedical Image Analysis, 2013
- Semi-automatic construction of reference standards for evaluation of image registrationMedical Image Analysis, 2011
- Regression Forests for Efficient Anatomy Detection and Localization in CT Studies2011
- Automatic Aorta Segmentation and Valve Landmark Detection in C-Arm CT: Application to Aortic Valve Implantation2010
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Dynamic Model-Driven Quantitative and Visual Evaluation of the Aortic Valve from 4D CT2008
- Automated 2-D Cephalometric Analysis on X-ray Images by a Model-Based ApproachIEEE Transactions on Biomedical Engineering, 2006
- Automatic Landmarking of Cephalograms by Cellular Neural Networks2005
- Automatic localization of craniofacial landmarks for assisted cephalometryPattern Recognition, 2004
- Automatic Localization of Cephalometric LandmarksJournal of Biomedical Informatics, 2001