Institute of Biomedical Manufacturing and Life Quality Engineering, State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Dongchuan Road 800, Minhang District, Shanghai, 200240, China.
Shanghai Ninth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Int J Comput Assist Radiol Surg. 2020 Sep;15(9):1457-1465. doi: 10.1007/s11548-020-02228-6. Epub 2020 Jul 16.
The analysis of the maxillary sinus (MS) can provide an assessment for many clinical diagnoses, so accurate CT image segmentation of the MS is essential. However, common segmentation methods are mainly done by experienced doctors manually, and there are some challenges such as low efficiency and precision. As for automatic methods, the initial seed points and adjustment of various parameters are required, which will affect the segmentation efficiency. Thus, accurate, efficient, and automatic segmentation method of MS is critical to promote the clinical application.
This paper proposed an automatic CT image segmentation method of MS based on VGG network and improved V-Net. The VGG network was established to classify CT slices, which can avoid the failure of CT slice segmentation without MS. Then, we proposed the improved V-Net based on edge supervision for segmenting MS regions more effectively. The edge loss was integrated into the loss of the improved V-Net, which could reduce region misjudgment and improve the automatic segmentation performance.
For the classification of CT slices with MS and without MS, the VGG network had a classification accuracy of 97.04 ± 2.03%. In the segmentation, our method obtained a better result, in which the segmentation Dice reached 94.40 ± 2.07%, the Iou (intersection over union) was 90.05 ± 3.26%, and the precision was 94.72 ± 2.64%. Compared with U-Net and V-Net, it reduced region misjudgment significantly and improved the segmentation accuracy. By analyzing the error map of 3D reconstruction, it was mainly distributed in ± 1 mm, which demonstrated that our result was quite close to the ground truth.
The segmentation of the MS can be realized efficiently, accurately, and automatically by our method. Meanwhile, it not only has a better segmentation result, but also improves the doctor's work efficiency, which will have significant impact on clinical applications in the future.
上颌窦（MS）的分析可为许多临床诊断提供评估，因此准确的 MS CT 图像分割至关重要。然而，常见的分割方法主要由经验丰富的医生手动完成，存在效率和精度低等挑战。对于自动方法，需要初始种子点和调整各种参数，这会影响分割效率。因此，准确、高效、自动的 MS 分割方法对于促进临床应用至关重要。
本文提出了一种基于 VGG 网络和改进的 V-Net 的 MS 自动 CT 图像分割方法。建立 VGG 网络对 CT 切片进行分类，可避免 MS 无 CT 切片分割失败的情况。然后，我们提出了基于边缘监督的改进 V-Net ，可以更有效地分割 MS 区域。边缘损失被整合到改进的 V-Net 的损失中，可以减少区域误判，提高自动分割性能。
对于有 MS 和无 MS 的 CT 切片分类，VGG 网络的分类准确率为 97.04±2.03%。在分割方面，我们的方法取得了更好的结果，其中分割 Dice 达到 94.40±2.07%，IoU（交并比）为 90.05±3.26%，准确率为 94.72±2.64%。与 U-Net 和 V-Net 相比，它显著减少了区域误判，提高了分割准确性。通过分析 3D 重建的误差图，误差主要分布在±1mm 内，表明我们的结果与真实值非常接近。
我们的方法可以高效、准确、自动地实现 MS 的分割。同时，它不仅具有更好的分割效果，而且提高了医生的工作效率，这将对未来的临床应用产生重大影响。
