Learning to Localize Cross-Anatomy Landmarks in X-Ray Images with a Universal Model

Abstract

Objective and Impact Statement . In this work, we develop a universal anatomical landmark detection model which learns once from multiple datasets corresponding to different anatomical regions. Compared with the conventional model trained on a single dataset, this universal model not only is more light weighted and easier to train but also improves the accuracy of the anatomical landmark location. Introduction . The accurate and automatic localization of anatomical landmarks plays an essential role in medical image analysis. However, recent deep learning-based methods only utilize limited data from a single dataset. It is promising and desirable to build a model learned from different regions which harnesses the power of big data. Methods . Our model consists of a local network and a global network, which capture local features and global features, respectively. The local network is a fully convolutional network built up with depth-wise separable convolutions, and the global network uses dilated convolution to enlarge the receptive field to model global dependencies. Results . We evaluate our model on four 2D X-ray image datasets totaling 1710 images and 72 landmarks in four anatomical regions. Extensive experimental results show that our model improves the detection accuracy compared to the state-of-the-art methods. Conclusion . Our model makes the first attempt to train a single network on multiple datasets for landmark detection. Experimental results qualitatively and quantitatively show that our proposed model performs better than other models trained on multiple datasets and even better than models trained on a single dataset separately.

Multi-Scale Semantic Fusion of a Large Receptive Field for Irregular Pelvic X-Ray Landmark Detection

“…It becomes evident that our method not only demonstrates commendable accuracy but also exhibits robustness on the intricate dataset presented in this paper. Despite the fact that our pelvis sample size surpasses that of Zhu et al [36], the MRE has experienced an increase of 1.75mm, and the STD has similarly risen by 7.947mm. This once again underscores the challenge of effectively learning complex pelvic X-ray data in real clinical scenarios.…”

“…The achieved detection accuracy was 5.6 ± 4.5mm. Zhu et al [36] developed a universal anatomical landmark detection model that learned once from multiple data sets corresponding to different anatomical regions. The model consists of a local network and a global network, which capture local features and global features, respectively.…”

A rhodamine coumarin-derived fluorescence probe that selectively detects Fe3+ and measures radiation doses

“…4 In addition, ionizing radiation is commonly utilized in various industries, such as agriculture, medicine, and national defense. [5][6][7][8] However, overexposure to ionizing radiation can lead to severe issues, such as acute radiation syndrome, cutaneous radiation injuries, and potentially fatal cancer. [9][10][11] Therefore, it is crucial to develop a sensor that can precisely measure the concentration of Fe 3+ and radiation doses.…”