Head and neck multi-organ auto-segmentation on CT images aided by synthetic MRI
Head and neck multi-organ auto-segmentation on CT images aided by synthetic MRI
复制标题
DOI：
10.1002/mp.14378
复制
发表时间：
2020-08-02
期刊：
影响因子：
3.8
通讯作者：
Yang, Xiaofeng
中科院分区：
文献类型：
--
作者：
Liu, Yingzi;Lei, Yang;Yang, Xiaofeng
目的 由于手动轮廓绘制过程是劳动密集型且耗时的，危及器官（OAR）的分割是放射治疗计划过程中的薄弱环节。我们的目标是开发一种合成 MR (sMR) 辅助的双金字塔网络 (DPN)，用于快速准确的头颈部多器官分割，以加快治疗计划过程。方法 45 名患者的 CT、MR 和手动轮廓对作为我们的训练数据集。十九个 OAR 是要分割的目标器官。所提出的 sMR 辅助 DPN 方法采用深度注意力策略来有效分割多个器官。使用五个指标评估 sMR 辅助 DPN 方法的性能，包括 Dice 相似系数 (DSC)、Hausdorff 距离 95% (HD95)、平均表面距离 (MSD)、残余均方距离 (RMSD) 和体积差。使用 2015 年头颈挑战数据进一步验证了我们的方法。结果所提出的方法生成的轮廓与地面实况手动轮廓非常相似，使用 2015 年头部和颈部挑战数据的 DSC 方面的令人鼓舞的定量结果证明了这一点。平均 DSC 值为 0.91 +/- 0.02、0.73 +/- 0.11、0.96 +/- 0.01、0.78 +/- 0.09/0.78 +/- 0.11、0.88 +/- 0.04/0.88 +/- 0.06 和 0.86 +/- 0.08/0.85 +/- 0.1分别针对脑干、交叉、下颌骨、左/右视神经、左/右腮腺和左/右下颌下实现。结论 我们证明了 sMR 辅助 DPN 在 CT 图像上进行头颈部多器官勾画的可行性。我们的方法在 2015 年头颈挑战数据结果上显示出优于其他方法的优势。所提出的方法可以通过快速分割多个 OAR 来显着加快治疗计划过程。
Purpose Because the manual contouring process is labor-intensive and time-consuming, segmentation of organs-at-risk (OARs) is a weak link in radiotherapy treatment planning process. Our goal was to develop a synthetic MR (sMR)-aided dual pyramid network (DPN) for rapid and accurate head and neck multi-organ segmentation in order to expedite the treatment planning process. Methods Forty-five patients' CT, MR, and manual contours pairs were included as our training dataset. Nineteen OARs were target organs to be segmented. The proposed sMR-aided DPN method featured a deep attention strategy to effectively segment multiple organs. The performance of sMR-aided DPN method was evaluated using five metrics, including Dice similarity coefficient (DSC), Hausdorff distance 95% (HD95), mean surface distance (MSD), residual mean square distance (RMSD), and volume difference. Our method was further validated using the 2015 head and neck challenge data. Results The contours generated by the proposed method closely resemble the ground truth manual contours, as evidenced by encouraging quantitative results in terms of DSC using the 2015 head and neck challenge data. Mean DSC values of 0.91 +/- 0.02, 0.73 +/- 0.11, 0.96 +/- 0.01, 0.78 +/- 0.09/0.78 +/- 0.11, 0.88 +/- 0.04/0.88 +/- 0.06 and 0.86 +/- 0.08/0.85 +/- 0.1 were achieved for brain stem, chiasm, mandible, left/right optic nerve, left/right parotid, and left/right submandibular, respectively. Conclusions We demonstrated the feasibility of sMR-aided DPN for head and neck multi-organ delineation on CT images. Our method has shown superiority over the other methods on the 2015 head and neck challenge data results. The proposed method could significantly expedite the treatment planning process by rapidly segmenting multiple OARs.