# Joint Landmark and Structure Learning for Automatic Evaluation of Developmental Dysplasia of the Hip

arXiv: https://arxiv.org/abs/2106.05458 · HTML: https://mlsanity.com/paper/2106.05458/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 48 references that are in the map.
- First posted on arXiv 10 Jun 2021.

## Builds on (most cited first, 15 of 15)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Cross-stitch Networks for Multi-task Learning](https://mlsanity.com/paper/1604.03539/) (2016)
- [YOLACT: Real-time Instance Segmentation](https://mlsanity.com/paper/1904.02689/) (2019)
- [PolarMask: Single Shot Instance Segmentation with Polar Representation](https://mlsanity.com/paper/1909.13226/) (2019)
- [Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification](https://mlsanity.com/paper/1611.05377/) (2016)
- [Learning Multiple Tasks with Multilinear Relationship Networks](https://mlsanity.com/paper/1506.02117/) (2015)
- [Deep Geodesic Learning for Segmentation and Anatomical Landmarking](https://mlsanity.com/paper/1810.04021/) (2018)
- [Robust and fully automated segmentation of mandible from CT scans](https://mlsanity.com/paper/1702.07059/) (2017)
- [End-to-end detection-segmentation network with ROI convolution](https://mlsanity.com/paper/1801.02722/) (2018)

## Built on by (most cited first, 5 of 5)

- [Measurement of Medial Elbow Joint Space using Landmark Detection](https://mlsanity.com/paper/2412.13010/) (2024)
- [Retuve: Automated Multi-Modality Analysis of Hip Dysplasia with Open Source AI](https://mlsanity.com/paper/2504.06422/) (2025)
- [Radiation-Preserving Selective Imaging for Pediatric Hip Dysplasia: A Cross-Modal Ultrasound-Xray Policy with Limited Labels](https://mlsanity.com/paper/2511.18457/) (2025)
- [A New Angle on Bones: Robust Pose Estimation in X-Ray and Ultrasound](https://mlsanity.com/paper/2606.04700/) (2026)
- [Rethinking Medical Landmark Localization with Prototype Learning-based Progressive Offset Correction](https://mlsanity.com/paper/2608.09182/) (2026)

## Abstract (arXiv)

The ultrasound (US) screening of the infant hip is vital for the early diagnosis of developmental dysplasia of the hip (DDH). The US diagnosis of DDH refers to measuring alpha and beta angles that quantify hip joint development. These two angles are calculated from key anatomical landmarks and structures of the hip. However, this measurement process is not trivial for sonographers and usually requires a thorough understanding of complex anatomical structures. In this study, we propose a multi-task framework to learn the relationships among landmarks and structures jointly and automatically evaluate DDH. Our multi-task networks are equipped with three novel modules. Firstly, we adopt Mask R-CNN as the basic framework to detect and segment key anatomical structures and add one landmark detection branch to form a new multi-task framework. Secondly, we propose a novel shape similarity loss to refine the incomplete anatomical structure prediction robustly and accurately. Thirdly, we further incorporate the landmark-structure consistent prior to ensure the consistency of the bony rim estimated from the segmented structure and the detected landmark. In our experiments, 1,231 US images of the infant hip from 632 patients are collected, of which 247 images from 126 patients are tested. The average errors in alpha and beta angles are 2.221 degrees and 2.899 degrees. About 93% and 85% estimates of alpha and beta angles have errors less than 5 degrees, respectively. Experimental results demonstrate that the proposed method can accurately and robustly realize the automatic evaluation of DDH, showing great potential for clinical application.