Radiomics analysis of dual-energy CT-derived iodine maps for differentiating between T1/2 and T3/4a in gastric...

To investigate the value of radiomic analysis of dual-energy CT (DECT)-derived iodine maps (IMs) for the differentiation between T1/2 and T3/4a stage tumors in gastric cancer (GC).

A total of 263 patients who received upfront surgery and were pathologically confirmed with gastric adenocarcinoma were enrolled in this study. Dual-phase enhanced CT scans with gemstone spectral imaging (GSI) mode were performed within two weeks before surgery. 151 patients were retrospectively collected for the training (n = 105) and validation (n = 46) cohorts, and 112 patients were prospectively collected for the external test1 (n = 68) and external test2 (n = 44) cohorts. According to the postoperative pathological T stage, patients were classified into T1/2 and T3/4a stage groups. Clinical characteristics were recorded and quantitative iodine concentration (IC) of tumors was measured. Radiomics features were extracted from the venous phase (VP) IMs by three-dimensional region of interest (3D-ROI) segmentation. Feature selection was performed using the least absolute shrinkage and selection operator. Four machine learning algorithms, including random forest, logistic regression, naive Bayes, and support vector machine, were used to construct radiomics models. Finally, the most valuable clinical characteristics, DECT parameters, and the best radiomics model were combined to build a nomogram. The diagnostic performance of nomogram was evaluated by the area under receiver operating characteristic curve (AUC), calibration curve, and decision curve.

The nomogram combined tumor clinical T stage (cT), tumor thickness, venous-phase iodine concentration (ICVP), normalized arterial-phase iodine concentration (nICAP), and Radscore (derived from logistic regression model). This integrated model demonstrated favorable performance in the differentiation between T1/2 and T3/4a stage tumors in GC, with AUCs of 0.892 (95 %CI: 0.829-0.956), 0.846 (95 %CI: 0.734-0.958), 0.894 (95 %CI: 0.818-0.970) and 0.821 (95 %CI: 0.689-0.952) observed for the training, validation, external test 1, and external test 2 cohorts, respectively. Hosmer-Lemeshow test showed a good fit (all P > 0.05). Decision curves confirmed that the nomogram provided more net clinical benefit than the default simple strategy over a wide range of threshold probabilities.

We have developed and validated a multidimensional personalized nomogram that integrates a radiomics model based on DECT-derived IMs, DECT quantitative parameters, and traditional clinical features. The proposed model demonstrated favorable performance in preoperative identification of T3/4a stage tumors in GC.