Xu Jiangchang, Zhang Dingzhong, Wang Chunliang, Zhou Huifang, Li Yinwei, Chen Xiaojun
Institute of Biomedical Manufacturing and Life Quality Engineering, State Key Laboratory of Mechanical System and Vibration, Room 925, School of Mechanical Engineering, Shanghai Jiao Tong University, Dongchuan Road 800, Minhang District, Shanghai, 200240, China.
Department of Biomedical Engineering and Health Systems, KTH Royal Institute of Technology, Stockholm, Sweden.
Int J Comput Assist Radiol Surg. 2023 Nov;18(11):2051-2062. doi: 10.1007/s11548-023-02924-z. Epub 2023 May 23.
Orbital wall segmentation is critical for orbital measurement and reconstruction. However, the orbital floor and medial wall are made up of thin walls (TW) with low gradient values, making it difficult to segment the blurred areas of the CT images. Clinically, doctors have to manually repair the missing parts of TW, which is time-consuming and laborious.
To address these issues, this paper proposes an automatic orbital wall segmentation method based on TW region supervision using a multi-scale feature search network. First of all, in the encoding branch, the densely connected atrous spatial pyramid pooling based on the residual connection is adopted to achieve a multi-scale feature search. Then, for feature enhancement, multi-scale up-sampling and residual connection are applied to perform skip connection of features in multi-scale convolution. Finally, we explore a strategy for improving the loss function based on the TW region supervision, which effectively increases the TW region segmentation accuracy.
The test results show that the proposed network performs well in terms of automatic segmentation. For the whole orbital wall region, the Dice coefficient (Dice) of segmentation accuracy reaches 96.086 ± 1.049%, the Intersection over Union (IOU) reaches 92.486 ± 1.924%, and the 95% Hausdorff distance (HD) reaches 0.509 ± 0.166 mm. For the TW region, the Dice reaches 91.470 ± 1.739%, the IOU reaches 84.327 ± 2.938%, and the 95% HD reaches 0.481 ± 0.082 mm. Compared with other segmentation networks, the proposed network improves the segmentation accuracy while filling the missing parts in the TW region.
In the proposed network, the average segmentation time of each orbital wall is only 4.05 s, obviously improving the segmentation efficiency of doctors. In the future, it may have a practical significance in clinical applications such as preoperative planning for orbital reconstruction, orbital modeling, orbital implant design, and so on.
眼眶壁分割对于眼眶测量和重建至关重要。然而，眶底和内侧壁由具有低梯度值的薄壁（TW）组成，使得难以分割CT图像的模糊区域。临床上，医生必须手动修复TW的缺失部分，这既耗时又费力。
为了解决这些问题，本文提出了一种基于多尺度特征搜索网络的TW区域监督的眼眶壁自动分割方法。首先，在编码分支中，采用基于残差连接的密集连接空洞空间金字塔池化来实现多尺度特征搜索。然后，为了进行特征增强，应用多尺度上采样和残差连接在多尺度卷积中进行特征的跳跃连接。最后，我们探索了一种基于TW区域监督的改进损失函数的策略，有效提高了TW区域的分割精度。
测试结果表明，所提出的网络在自动分割方面表现良好。对于整个眼眶壁区域，分割精度的Dice系数（Dice）达到96.086±1.049%，交并比（IOU）达到92.486±1.924%，95%豪斯多夫距离（HD）达到0.509±0.166毫米。对于TW区域，Dice达到91.470±1.739%，IOU达到84.327±2.938%，95% HD达到0.481±0.082毫米。与其他分割网络相比，所提出的网络在提高分割精度的同时，还填补了TW区域的缺失部分。
在所提出的网络中，每个眼眶壁的平均分割时间仅为4.05秒，显著提高了医生的分割效率。未来，它在眼眶重建术前规划、眼眶建模、眼眶植入物设计等临床应用中可能具有实际意义。
