Region Proposal Network with Graph Prior and IoU-Balance Loss for Landmark Detection in 3D Ultrasound
| Autor: | Dong Ni, Yuanji Zhang, Mingrong Lin, Ruobing Huang, Chaoyu Chen, Yong Yang, Wenlong Shi, Xin Yang, Yi Xiong, Huanjia Luo, Yuhao Huang, Yankai Huang, Shengfeng Liu |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Landmark medicine.diagnostic_test business.industry Computer science Deep learning Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Pattern recognition 010501 environmental sciences 01 natural sciences Object detection 030218 nuclear medicine & medical imaging Machine Learning (cs.LG) 03 medical and health sciences 0302 clinical medicine Minimum bounding box medicine Leverage (statistics) Graph (abstract data type) 3D ultrasound Artificial intelligence business 0105 earth and related environmental sciences |
| Zdroj: | ISBI |
| DOI: | 10.48550/arxiv.2004.00207 |
| Popis: | 3D ultrasound (US) can facilitate detailed prenatal examinations for fetal growth monitoring. To analyze a 3D US volume, it is fundamental to identify anatomical landmarks of the evaluated organs accurately. Typical deep learning methods usually regress the coordinates directly or involve heatmap-matching. However, these methods struggle to deal with volumes with large sizes and the highly-varying positions and orientations of fetuses. In this work, we exploit an object detection framework to detect landmarks in 3D fetal facial US volumes. By regressing multiple parameters of the landmark-centered bounding box (B-box) with a strict criteria, the proposed model is able to pinpoint the exact location of the targeted landmarks. Specifically, the model uses a 3D region proposal network (RPN) to generate 3D candidate regions, followed by several 3D classification branches to select the best candidate. It also adopts an IoU-balance loss to improve communications between branches that benefits the learning process. Furthermore, it leverages a distance-based graph prior to regularize the training and helps to reduce false positive predictions. The performance of the proposed framework is evaluated on a 3D US dataset to detect five key fetal facial landmarks. Results showed the proposed method outperforms some of the state-of-the-art methods in efficacy and efficiency. Comment: IEEE International Symposium on Biomedical Imaging (IEEE ISBI 2020) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|