UOD: Universal One-shot Detection of Anatomical Landmarks
Authors:
- S. Kevin ZhouSZS. Kevin Zhou
Preprint
Abstract
One-shot medical landmark detection gains much attention and achieves great success for its label-efficient training process. However, existing one-shot learning methods are highly specialized in a single domain and suffer domain preference heavily in the situation of multi-domain unlabeled data. Moreover, one-shot learning is not robust that it faces performance drop when annotating a sub-optimal image. To tackle these issues, we resort to developing a domain-adaptive one-shot landmark detection framework for handling multi-domain medical images, named Universal One-shot Detection (UOD). UOD consists of two stages and two corresponding universal models which are designed as combinations of domain-specific modules and domain-shared modules. In the first stage, a domain-adaptive convolution model is self-supervised learned to generate pseudo landmark labels. In the second stage, we design a domain-adaptive transformer to eliminate domain preference and build the global context for multi-domain data. Even though only one annotated sample from each domain is available for training, the domain-shared modules help UOD aggregate all one-shot samples to detect more robust and accurate landmarks. We investigated both qualitatively and quantitatively the proposed UOD on three widely-used public X-ray datasets in different anatomical domains (i.e., head, hand, chest) and obtained state-of-the-art performances in each domain. The code is available at https://github.com/heqin-zhu/UOD_universal_oneshot_detection.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Accurate scoliosis vertebral landmark localization on X-ray images via shape-constrained multi-stage cascaded CNNsFundamental Research, 2024
- Learning to Localize Cross-Anatomy Landmarks in X-Ray Images with a Universal ModelBME Frontiers, 2022
- Automated brain structures segmentation from PET/CT images based on landmark-constrained dual-modality atlas registrationPhysics in Medicine & Biology, 2021
- A Review of Deep Learning in Medical Imaging: Imaging Traits, Technology Trends, Case Studies With Progress Highlights, and Future PromisesProceedings of the IEEE, 2021
- Handbook of Medical Image Computing and Computer Assisted Intervention2020
- Integrating spatial configuration into heatmap regression based CNNs for landmark localizationMedical Image Analysis, 2019
- A benchmark for comparison of dental radiography analysis algorithmsMedical Image Analysis, 2016
- Evaluation and Comparison of Anatomical Landmark Detection Methods for Cephalometric X-Ray Images: A Grand ChallengeIEEE Transactions on Medical Imaging, 2015
- Bone age assessment of children using a digital hand atlasComputerized Medical Imaging and Graphics, 2007