目的:在颅颌面外科,从CT图像中准确自动分割下颌骨具有重要的临床意义。然而,牙齿和髁的连接区域和模糊的边界使得该过程具有挑战性。目前,下颌骨通常由经验丰富的医生使用手动或半自动方法分割,这是耗时的,并且分割一致性差。此外,现有的自动分割方法还存在区域误判等问题,精度低,而且耗时。
方法:对于这些问题,提出了一种基于密集连通空间金字塔池化(DenseASPP)和注意力门(AG)的三维全卷积神经网络下颌骨自动分割方法。首先,DenseASPP模块被添加到网络中,用于在多个尺度上提取密集特征。此后,在每个跳过连接中都应用了AG模块,以减少无关的背景信息,并使网络专注于分割区域。最后,使用结合骰子系数和焦点损失的损失函数来解决样本类别之间的不平衡。
结果:测试结果表明,所提出的网络获得了相对较好的分割结果,骰子得分为97.588±0.425%,在95.293±0.81%的联合上相交,灵敏度为96.252±1.106%,平均表面距离为0.065±0.020mm,95%Hausdorff距离为0.491±0.021mm。与其他分割网络的比较表明,我们的网络不仅具有较高的分割精度,而且有效地减少了网络的误判。同时,表面距离误差也表明我们的分割结果相对接近地面实况。
结论:所提出的网络具有更好的分割性能,实现了下颌骨的准确自动分割。此外,一次CT扫描的分割时间为50.43s,这大大提高了医生的工作效率。这将在未来的颅颌面外科中具有现实意义。
OBJECTIVE: 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.
CONCLUSIONS: 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.