Hand Pose Estimation for Pediatric Bone Age Assessment
We present a new experimental framework for the task of Bone Age Assessment (BAA) based on a local analysis of anatomical Regions Of Interest (ROIs) of hand radiographs. For this purpose, we introduce the Radiological Hand Pose Estimation (RHPE) Dataset, composed of 6,288 hand radiographs from a population that is different from the currently available BAA datasets. We provide Bone Age groundtruths annotated by two expert radiologists as well as bounding boxes and keypoints denoting anatomical ROIs annotated by multiple trained subjects. In addition to RHPE, we provide bounding boxes and ROIs annotations for the publicly available BAA dataset by the Radiological Society of North America (RSNA) . We propose a new experimental framework with hand detection and hand pose estimation as new tasks to extract local information for BAA methods. Thanks to its fine-grained and precisely localized annotations, our dataset will allow to exploit local information to push forward automated BAA algorithms. Additionally, we conduct experiments with state-of-the-art methods in each of the new tasks. Our proposed model, named BoNet, leverages local information and significantly outperforms state-of-the-art methods in BAA. We provide the RHPE dataset with the corresponding annotations, as well as the trained models, the source code for BoNet and the additional annotations created for the RSNA dataset.
KeywordsBone Age Assessment Computer aided diagnosis Hand radiograph Regions Of Interest
This project was partially funded by Colciencias grant 841-2017. The authors thank Edgar Margffoy-Tuay for his support in developing the annotation server and the students of IBIO-3470 at Uniandes for their help as annotators.
Supplementary material 2 (mp4 14995 KB)
- 1.Cicero, M., Bilbily, A.: Machine learning and the future of radiology: how we won the 2017 RSNA ML challenge (2017)Google Scholar
- 4.Ge, L., Cai, Y., Weng, J., Yuan, J.: Hand PointNet: 3D hand pose estimation using point sets. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8417–8426 (2018)Google Scholar
- 7.Gilsanz, V., Ratib, O.: Hand Bone Age: A Digital Atlas of Skeletal Maturity. Springer, Heidelberg (2005)Google Scholar
- 8.Greulich, W.W., Pyle, S.I., Todd, T.W.: Radiographic Atlas of Skeletal Development of the Hand and Wrist, vol. 2. Stanford University Press, Palo Alto (1959)Google Scholar
- 11.He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
- 12.Iglovikov, V.I., Rakhlin, A., Kalinin, A.A., Shvets, A.A.: Paediatric bone age assessment using deep convolutional neural networks. In: Stoyanov, D., et al. (eds.) DLMIA/ML-CDS -2018. LNCS, vol. 11045, pp. 300–308. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00889-5_34CrossRefGoogle Scholar
- 14.Massa, F., Girshick, R.: maskrcnn-benchmark: fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch (2018)Google Scholar
- 15.Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 91–99 (2015)Google Scholar
- 16.Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27–30 June 2016, pp. 2818–2826 (2016). https://doi.org/10.1109/CVPR.2016.308