Hu Yifan, Zhang Yi, Tang Zeyu, Han Xin, Hong Huimin, Kong Lin, Xu Zhihan, Jiang Shanshan, Yu Xiaojin, Zhang Lei
Department of Radiology, Dongtai People's Hospital, Yancheng, China.
Department of Radiology, Nantong University Affiliated Hospital, Nantong, China.
Quant Imaging Med Surg. 2025 Mar 3;15(3):2119-2131. doi: 10.21037/qims-24-1116. Epub 2025 Feb 26.
Radiomics research in esophageal cancer (EC) has made considerable advancements. However, manual segmentation, which is relied upon in clinical and scientific workflows, remains time-consuming and inconsistent. This study aimed to develop and validate a deep learning (DL) model for the automatic detection and segmentation of EC lesions in contrast-enhanced computed tomography (CT) images.
We retrospectively collected the CT data of patients with EC confirmed by pathology from January 2017 to September 2021 at three hospitals and from individuals with a healthy esophagus. Manual labeling of EC lesions was conducted, and DL networks [no new U-Net (nnU-Net) and U-Mamba] were trained for automatic segmentation. An optimal threshold volume for EC lesion detection was determined and integrated into the postprocessing module. The performance of DL models was evaluated in internal, external, and thin-slice image test cohorts and compared with diagnoses by radiologists. The sensitivity, specificity, accuracy, Dice similarity coefficient (DSC), and Hausdorff distance (HD) were calculated.
A total of 871 patients (564 males) were included, with a median age of 67 years. DL models exhibited no significant difference from radiologists' diagnoses (P>0.05). Median DSC values for the internal, external, and thin-slice cohorts were 0.795, 0.811, and 0.797, respectively, with a corresponding HD of 9.733 mm, 7.860 mm, and 8.168 mm. An intraclass correlation coefficient greater than 0.7 was observed for 97.2% of the radiomic features extracted from thin-slice images.
The DL methods demonstrated exceptional sensitivity and robustness in EC detection and segmentation on contrast-enhanced CT images, not only reducing missed EC diagnoses but also providing radiologists with consistent lesion annotations.
食管癌（EC）的放射组学研究已取得显著进展。然而，临床和科研工作流程中依赖的手动分割仍然耗时且不一致。本研究旨在开发并验证一种深度学习（DL）模型，用于在增强计算机断层扫描（CT）图像中自动检测和分割EC病变。
我们回顾性收集了2017年1月至2021年9月期间三家医院经病理确诊的EC患者以及健康食管个体的CT数据。对EC病变进行手动标注，并训练DL网络[新型U-Net（nnU-Net）和U-Mamba]进行自动分割。确定EC病变检测的最佳阈值体积并将其整合到后处理模块中。在内部、外部和薄层图像测试队列中评估DL模型的性能，并与放射科医生的诊断结果进行比较。计算敏感性、特异性、准确性、骰子相似系数（DSC）和豪斯多夫距离（HD）。
共纳入871例患者（564例男性），中位年龄为67岁。DL模型与放射科医生的诊断结果无显著差异（P>0.05）。内部、外部和薄层队列的中位DSC值分别为0.795、0.811和0.797，相应的HD分别为9.733 mm、7.860 mm和8.168 mm。从薄层图像中提取的97.2%的放射组学特征的组内相关系数大于0.7。
DL方法在增强CT图像上的EC检测和分割中表现出卓越的敏感性和鲁棒性，不仅减少了EC诊断的漏诊，还为放射科医生提供了一致的病变标注。
