期刊
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
卷 16, 期 10, 页码 1785-1794出版社
SPRINGER HEIDELBERG
DOI: 10.1007/s11548-021-02447-5
关键词
Mandible segmentation; Fully convolutional neural network; DenseASPP; Attention gates
资金
- National Key Research and Development Program of China [2017YFB1302900]
- National Natural Science Foundation of China [81971709, M-0019, 82011530141]
- Foundation of Science and Technology Commission of Shanghai Municipality [19510712200, 20490740700]
- Shanghai Jiao Tong University Foundation on Medical and Technological Joint Science Research [ZH2018ZDA15, YG2019ZDA06, ZH2018QNA23]
- 2020 Key Research project of Xiamen Municipal Government [3502Z20201030]
An automatic mandibular segmentation method based on neural network with DenseASPP and AG modules was proposed to enhance accuracy. Test results showed that the network achieved good segmentation results with high accuracy, which was close to ground truth.
Purpose In cranio-maxillofacial surgery, it is of great clinical significance to segment mandible accurately and automatically from CT images. However, the connected region and blurred boundary in teeth and condyles make the process challenging. At present, the mandible is commonly segmented by experienced doctors using manually or semi-automatic methods, which is time-consuming and has poor segmentation consistency. In addition, existing automatic segmentation methods still have problems such as region misjudgment, low accuracy, and time-consuming. Methods For these issues, an automatic mandibular segmentation method using 3d fully convolutional neural network based on densely connected atrous spatial pyramid pooling (DenseASPP) and attention gates (AG) was proposed in this paper. Firstly, the DenseASPP module was added to the network for extracting dense features at multiple scales. Thereafter, the AG module was applied in each skip connection to diminish irrelevant background information and make the network focus on segmentation regions. Finally, a loss function combining dice coefficient and focal loss was used to solve the imbalance among sample categories. Results Test results showed that the proposed network obtained a relatively good segmentation result, with a Dice score of 97.588 +/- 0.425%, Intersection over Union of 95.293 +/- 0.812%, sensitivity of 96.252 +/- 1.106%, average surface distance of 0.065 +/- 0.020 mm and 95% Hausdorff distance of 0.491 +/- 0.021 mm in segmentation accuracy. The comparison with other segmentation networks showed that our network not only had a relatively high segmentation accuracy but also effectively reduced the network's misjudgment. Meantime, the surface distance error also showed that our segmentation results were relatively close to the ground truth. Conclusion The proposed network has better segmentation performance and realizes accurate and automatic segmentation of the mandible. Furthermore, its segmentation time is 50.43 s for one CT scan, which greatly improves the doctor's work efficiency. It will have practical significance in cranio-maxillofacial surgery in the future.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据