Gao Zhihong, Yu Zhuo, Zhang Xiang, Chen Chun, Pan Zhifang, Chen Xiaodong, Lin Weihong, Chen Jun, Zhuge Qichuan, Shen Xian
Zhejiang Engineering Research Center of Intelligent Medicine, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
School of Information and Safety Engineering, Zhongnan University of Economics and Law, Wuhan, China.
Front Oncol. 2023 Oct 6;13:1265366. doi: 10.3389/fonc.2023.1265366. eCollection 2023.
Gastric cancer is a highly prevalent and fatal disease. Accurate differentiation between early gastric cancer (EGC) and advanced gastric cancer (AGC) is essential for personalized treatment. Currently, the diagnostic accuracy of computerized tomography (CT) for gastric cancer staging is insufficient to meet clinical requirements. Many studies rely on manual marking of lesion areas, which is not suitable for clinical diagnosis.
In this study, we retrospectively collected data from 341 patients with gastric cancer at the First Affiliated Hospital of Wenzhou Medical University. The dataset was randomly divided into a training set (n=273) and a validation set (n=68) using an 8:2 ratio. We developed a two-stage deep learning model that enables fully automated EGC screening based on CT images. In the first stage, an unsupervised domain adaptive segmentation model was employed to automatically segment the stomach on unlabeled portal phase CT images. Subsequently, based on the results of the stomach segmentation model, the image was cropped out of the stomach area and scaled to a uniform size, and then the EGC and AGC classification models were built based on these images. The segmentation accuracy of the model was evaluated using the dice index, while the classification performance was assessed using metrics such as the area under the curve (AUC) of the receiver operating characteristic (ROC), accuracy, sensitivity, specificity, and F1 score.
The segmentation model achieved an average dice accuracy of 0.94 on the hand-segmented validation set. On the training set, the EGC screening model demonstrated an AUC, accuracy, sensitivity, specificity, and F1 score of 0.98, 0.93, 0.92, 0.92, and 0.93, respectively. On the validation set, these metrics were 0.96, 0.92, 0.90, 0.89, and 0.93, respectively. After three rounds of data regrouping, the model consistently achieved an AUC above 0.9 on both the validation set and the validation set.
The results of this study demonstrate that the proposed method can effectively screen for EGC in portal venous CT images. Furthermore, the model exhibits stability and holds promise for future clinical applications.
胃癌是一种高度流行且致命的疾病。准确区分早期胃癌（EGC）和进展期胃癌（AGC）对于个性化治疗至关重要。目前，计算机断层扫描（CT）对胃癌分期的诊断准确性不足以满足临床需求。许多研究依赖于病变区域的手动标记，这不适合临床诊断。
在本研究中，我们回顾性收集了温州医科大学附属第一医院341例胃癌患者的数据。使用8:2的比例将数据集随机分为训练集（n = 273）和验证集（n = 68）。我们开发了一种两阶段深度学习模型，能够基于CT图像进行全自动EGC筛查。在第一阶段，采用无监督域自适应分割模型在未标记的门静脉期CT图像上自动分割胃部。随后，根据胃部分割模型的结果，将图像从胃部区域裁剪出来并缩放到统一大小，然后基于这些图像构建EGC和AGC分类模型。使用骰子指数评估模型的分割准确性，而使用诸如受试者操作特征（ROC）曲线下面积（AUC）、准确性、敏感性、特异性和F1分数等指标评估分类性能。
分割模型在手动分割的验证集上平均骰子准确率达到0.94。在训练集上，EGC筛查模型的AUC、准确性、敏感性、特异性和F1分数分别为0.98、0.93、0.92、0.92和0.93。在验证集上，这些指标分别为0.96、0.92、0.90、0.89和0.93。经过三轮数据重新分组后，该模型在验证集和验证集上均始终实现AUC高于0.9。
本研究结果表明，所提出的方法能够有效地在门静脉CT图像中筛查EGC。此外，该模型具有稳定性，对未来临床应用具有前景。
