Automatic Localization of Landmarks in Craniomaxillofacial CBCT Images Using a Local Attention-Based Graph Convolution Network
| Autor: | Deqiang Xiao, James J. Xia, Hannah H. Deng, Chunfeng Lian, David M. Alfi, Yankun Lang, Jaime Gateno, Peng Yuan, Dinggang Shen, Steve Guofang Shen, Pew Thian Yap |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Reconstructive surgery
medicine.medical_specialty Landmark medicine.diagnostic_test Computer science business.industry Deep learning Computed tomography Article 030218 nuclear medicine & medical imaging Convolution Automatic localization 03 medical and health sciences 0302 clinical medicine medicine Graph (abstract data type) Computer vision Artificial intelligence business 030217 neurology & neurosurgery |
| Zdroj: | Med Image Comput Comput Assist Interv Medical Image Computing and Computer Assisted Intervention – MICCAI 2020 ISBN: 9783030597184 MICCAI (4) |
| Popis: | Landmark localization is an important step in quantifying craniomaxillofacial (CMF) deformities and designing treatment plans of reconstructive surgery. However, due to the severity of deformities and defects (partially missing anatomy), it is difficult to automatically and accurately localize a large set of landmarks simultaneously. In this work, we propose two cascaded networks for digitizing 60 anatomical CMF landmarks in cone-beam computed tomography (CBCT) images. The first network is a U-Net that outputs heatmaps for landmark locations and landmark features extracted with a local attention mechanism. The second network is a graph convolution network that takes the features extracted by the first network as input and determines whether each landmark exists via binary classification. We evaluated our approach on 50 sets of CBCT scans of patients with CMF deformities and compared them with state-of-the-art methods. The results indicate that our approach can achieve an average detection error of 1.47 mm with a false positive rate of 19%, outperforming related methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|