In this study, we present deep learning‐based approaches to automatic segmentation and applicator reconstruction with high accuracy and efficiency in the planning computed tomography (CT) for cervical cancer brachytherapy (BT). A novel three‐dimensional (3D) convolutional neural network (CNN) architecture was proposed and referred to as DSD‐UNET. The dataset of 91 patients received CT‐based BT of cervical cancer was used to train and test DSD‐UNET model for auto‐segmentation of high‐risk clinical target volume (HR‐CTV) and organs at risk (OARs). Automatic applicator reconstruction was achieved with DSD‐UNET‐based segmentation of applicator components followed by 3D skeletonization and polynomial curve fitting. Digitization of the channel paths for tandem and ovoid applicator in the planning CT was evaluated utilizing the data from 32 patients. Dice similarity coefficient (DSC), Jaccard Index (JI), and Hausdorff distance (HD) were used to quantitatively evaluate the accuracy. The segmentation performance of DSD‐UNET was compared with that of 3D U‐Net. Results showed that DSD‐UNET method outperformed 3D U‐Net on segmentations of all the structures. The mean DSC values of DSD‐UNET method were 86.9%, 82.9%, and 82.1% for bladder, HR‐CTV, and rectum, respectively. For the performance of automatic applicator reconstruction, outstanding segmentation accuracy was first achieved for the intrauterine and ovoid tubes (average DSC value of 92.1%, average HD value of 2.3 mm). Finally, HDs between the channel paths determined automatically and manually were 0.88 ± 0.12 mm, 0.95 ± 0.16 mm, and 0.96 ± 0.15 mm for the intrauterine, left ovoid, and right ovoid tubes, respectively. The proposed DSD‐UNET method outperformed the 3D U‐Net and could segment HR‐CTV, bladder, and rectum with relatively good accuracy. Accurate digitization of the channel paths could be achieved with the DSD‐UNET‐based method. The proposed approaches could be useful to improve the efficiency and consistency of treatment planning for cervical cancer BT.

中文翻译：

---

使用 3D 卷积神经网络自动分割和重建基于 CT 的宫颈癌近距离放射治疗


在这项研究中，我们提出了基于深度学习的自动分割和施源器重建方法，在宫颈癌近距离放射治疗（BT）的计算机断层扫描（CT）规划中具有高精度和高效率。提出了一种新颖的三维（3D）卷积神经网络（CNN）架构，称为 DSD-UNET。使用 91 名接受基于 CT 的宫颈癌 BT 患者的数据集来训练和测试 DSD-UNET 模型，以自动分割高风险临床目标体积 (HR-CTV) 和危险器官 (OAR)。通过基于 DSD-UNET 的涂药器组件分割，然后进行 3D 骨架化和多项式曲线拟合，实现了自动涂药器重建。利用 32 名患者的数据对计划 CT 中串联和卵形施源器通道路径的数字化进行了评估。使用骰子相似系数（DSC）、杰卡德指数（JI）和豪斯多夫距离（HD）来定量评估准确性。将 DSD-UNET 的分割性能与 3D U-Net 的分割性能进行比较。结果表明，DSD-UNET 方法在所有结构的分割方面优于 3D U-Net。 DSD-UNET 方法的膀胱、HR-CTV 和直肠的平均 DSC 值分别为 86.9%、82.9% 和 82.1%。对于自动施源器重建性能，首先对宫内管和卵圆形管实现了出色的分割精度（平均 DSC 值为 92.1%，平均 HD 值为 2.3 mm）。最后，自动和手动确定的宫内管、左卵圆形管和右卵圆形管的通道路径之间的 HD 分别为 0.88 ± 0.12 mm、0.95 ± 0.16 mm 和 0.96 ± 0.15 mm。 所提出的 DSD-UNET 方法优于 3D U-Net，并且可以以相对较高的精度分割 HR-CTV、膀胱和直肠。使用基于 DSD-UNET 的方法可以实现通道路径的精确数字化。所提出的方法可能有助于提高宫颈癌 BT 治疗计划的效率和一致性。