Department of General Surgery and Laboratory of Gastric Cancer, State Key Laboratory of Biotherapy/Collaborative Innovation Center of Biotherapy and Cancer Center, West China Hospital, Sichuan University, Chengdu, China.
Gastric Cancer Center, West China Hospital, Sichuan University, Chengdu, China.
J Med Internet Res. 2024 Oct 9;26:e56851. doi: 10.2196/56851.
As part of the TNM (tumor-node-metastasis) staging system, T staging based on tumor depth is crucial for developing treatment plans. Previous studies have constructed a deep learning model based on computed tomographic (CT) radiomic signatures to predict the number of lymph node metastases and survival in patients with resected gastric cancer (GC). However, few studies have reported the combination of deep learning and radiomics in predicting T staging in GC.
This study aimed to develop a CT-based model for automatic prediction of the T stage of GC via radiomics and deep learning.
A total of 771 GC patients from 3 centers were retrospectively enrolled and divided into training, validation, and testing cohorts. Patients with GC were classified into mild (stage T1 and T2), moderate (stage T3), and severe (stage T4) groups. Three predictive models based on the labeled CT images were constructed using the radiomics features (radiomics model), deep features (deep learning model), and a combination of both (hybrid model).
The overall classification accuracy of the radiomics model was 64.3% in the internal testing data set. The deep learning model and hybrid model showed better performance than the radiomics model, with overall classification accuracies of 75.7% (P=.04) and 81.4% (P=.001), respectively. On the subtasks of binary classification of tumor severity, the areas under the curve of the radiomics, deep learning, and hybrid models were 0.875, 0.866, and 0.886 in the internal testing data set and 0.820, 0.818, and 0.972 in the external testing data set, respectively, for differentiating mild (stage T1T2) from nonmild (stage T3T4) patients, and were 0.815, 0.892, and 0.894 in the internal testing data set and 0.685, 0.808, and 0.897 in the external testing data set, respectively, for differentiating nonsevere (stage T1~T3) from severe (stage T4) patients.
The hybrid model integrating radiomics features and deep features showed favorable performance in diagnosing the pathological stage of GC.
作为 TNM（肿瘤-淋巴结-转移）分期系统的一部分，基于肿瘤深度的 T 分期对于制定治疗计划至关重要。先前的研究已经构建了基于计算机断层扫描（CT）放射组学特征的深度学习模型，用于预测接受手术治疗的胃癌患者的淋巴结转移数量和生存情况。然而，很少有研究报告将深度学习和放射组学结合起来预测胃癌的 T 分期。
本研究旨在开发一种基于 CT 的模型，通过放射组学和深度学习实现胃癌 T 分期的自动预测。
回顾性纳入来自 3 个中心的 771 例胃癌患者，将其分为训练、验证和测试队列。将胃癌患者分为轻度（T1 和 T2 期）、中度（T3 期）和重度（T4 期）组。使用标记的 CT 图像构建了 3 种基于放射组学特征的预测模型（放射组学模型）、基于深度学习特征的模型（深度学习模型）和两者结合的模型（混合模型）。
内部测试数据集的放射组学模型的整体分类准确率为 64.3%。深度学习模型和混合模型的性能优于放射组学模型，整体分类准确率分别为 75.7%（P=.04）和 81.4%（P=.001）。在肿瘤严重程度的二分类子任务中，放射组学、深度学习和混合模型在内部测试数据集的曲线下面积分别为 0.875、0.866 和 0.886，在外部测试数据集的曲线下面积分别为 0.820、0.818 和 0.972，用于区分轻度（T1T2 期）和非轻度（T3T4 期）患者，在内部测试数据集的曲线下面积分别为 0.815、0.892 和 0.894，在外部测试数据集的曲线下面积分别为 0.685、0.808 和 0.897，用于区分非重度（T1~T3 期）和重度（T4 期）患者。
结合放射组学特征和深度学习特征的混合模型在诊断胃癌的病理分期方面表现出良好的性能。
