在医学图像上精确勾画食管大体肿瘤体积（GTV）可以促进食管癌的放疗效果。这项工作旨在探索有效的基于学习的方法来解决食管 GTV 具有挑战性的自动分割问题。通过采用渐进层次推理机制（PHRM），我们设计了一个简单而有效的两阶段深度框架：ConVMLP-ResU-Net。其中，前端ConVMLP集成了卷积（ConV）和多层感知器（MLP）来捕获局部和长距离的空间信息，从而使ConVMLP在食管GTV的位置和粗略形状预测方面表现出色。根据PHRM的要求，前端ConVMLP应具有较强的泛化能力，以保证后端ResU-Net具有正确有效的推理。因此，提出了一种条件控制训练算法来控制 ConVMLP 的训练过程，以获得鲁棒的前端。之后，后端 ResU-Net 受益于 ConVMLP 生成的掩模来进行更精细的扩展分割以输出最终结果。对临床队列进行了广泛的实验，其中包括 1138 对 18F-FDG 正电子发射断层扫描/计算机断层扫描 (PET/CT) 图像。我们报告的 Dice 相似系数、豪斯多夫距离和平均表面距离分别为 0.82±0.13、4.31±7.91 毫米和 1.42±3.69 毫米。预测的轮廓在视觉上与地面真实情况有很好的一致性。设计的 ConVMLP 易于通过正确的初始形状预测来定位食管 GTV，从而有助于后端 ResU-Net 的更精细分割。定性和定量结果都验证了所提出方法的有效性。© 2023。澳大利亚物理科学家和医学工程师学院。

The precise delineation of esophageal gross tumor volume (GTV) on medical images can promote the radiotherapy effect of esophagus cancer. This work is intended to explore effective learning-based methods to tackle the challenging auto-segmentation problem of esophageal GTV. By employing the progressive hierarchical reasoning mechanism (PHRM), we devised a simple yet effective two-stage deep framework, ConVMLP-ResU-Net. Thereinto, the front-end ConVMLP integrates convolution (ConV) and multi-layer perceptrons (MLP) to capture localized and long-range spatial information, thus making ConVMLP excel in the location and coarse shape prediction of esophageal GTV. According to the PHRM, the front-end ConVMLP should have a strong generalization ability to ensure that the back-end ResU-Net has correct and valid reasoning. Therefore, a condition control training algorithm was proposed to control the training process of ConVMLP for a robust front end. Afterward, the back-end ResU-Net benefits from the yielded mask by ConVMLP to conduct a finer expansive segmentation to output the final result. Extensive experiments were carried out on a clinical cohort, which included 1138 pairs of 18F-FDG positron emission tomography/computed tomography (PET/CT) images. We report the Dice similarity coefficient, Hausdorff distance, and Mean surface distance as 0.82 ± 0.13, 4.31 ± 7.91 mm, and 1.42 ± 3.69 mm, respectively. The predicted contours visually have good agreements with the ground truths. The devised ConVMLP is apt at locating the esophageal GTV with correct initial shape prediction and hence facilitates the finer segmentation of the back-end ResU-Net. Both the qualitative and quantitative results validate the effectiveness of the proposed method.© 2023. Australasian College of Physical Scientists and Engineers in Medicine.