RESUMO
OBJECTIVE: To investigate the value of radiomics analysis of dual-layer spectral-detector computed tomography (DLSCT)-derived iodine maps for predicting tumor deposits (TDs) preoperatively in patients with colorectal cancer (CRC). MATERIALS AND METHODS: A total of 264 pathologically confirmed CRC patients (TDs + (n = 80); TDs - (n = 184)) who underwent preoperative DLSCT from two hospitals were retrospectively enrolled, and divided into training (n = 124), testing (n = 54), and external validation cohort (n = 86). Conventional CT features and iodine concentration (IC) were analyzed and measured. Radiomics features were derived from venous phase iodine maps from DLSCT. The least absolute shrinkage and selection operator (LASSO) was performed for feature selection. Finally, a support vector machine (SVM) algorithm was employed to develop clinical, radiomics, and combined models based on the most valuable clinical parameters and radiomics features. Area under receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis were used to evaluate the model's efficacy. RESULTS: The combined model incorporating the valuable clinical parameters and radiomics features demonstrated excellent performance in predicting TDs in CRC (AUCs of 0.926, 0.881, and 0.887 in the training, testing, and external validation cohorts, respectively), which outperformed the clinical model in the training cohort and external validation cohorts (AUC: 0.839 and 0.695; p: 0.003 and 0.014) and the radiomics model in two cohorts (AUC: 0.922 and 0.792; p: 0.014 and 0.035). CONCLUSION: Radiomics analysis of DLSCT-derived iodine maps showed excellent predictive efficiency for preoperatively diagnosing TDs in CRC, and could guide clinicians in making individualized treatment strategies. CLINICAL RELEVANCE STATEMENT: The radiomics model based on DLSCT iodine maps has the potential to aid in the accurate preoperative prediction of TDs in CRC patients, offering valuable guidance for clinical decision-making. KEY POINTS: Accurately predicting TDs in CRC patients preoperatively based on conventional CT features poses a challenge. The Radiomics model based on DLSCT iodine maps outperformed conventional CT in predicting TDs. The model combing DLSCT iodine maps radiomics features and conventional CT features performed excellently in predicting TDs.
RESUMO
PURPOSE: To establish and validate an integrated model incorporating multiregional magnetic resonance imaging (MRI) radiomics features and clinical factors to predict tumor deposits (TDs) preoperatively in resectable rectal cancer (RC). METHODS: This study retrospectively included 148 resectable RC patients [TDs+ (n = 45); TDs- (n = 103)] from August 2016 to August 2022, who were divided randomly into a testing cohort (n = 45) and a training cohort (n = 103). Radiomics features were extracted from the volume of interest on T2-weighted images (T2WI) and diffusion-weighted images (DWI) from pretreatment MRI. Model construction was performed after feature selection. Finally, five classification models were developed by support vector machine (SVM) algorithm to predict TDs in resectable RC using the selected clinical factor, single-regional radiomics features (extracted from primary tumor), and multiregional radiomics features (extracted from the primary tumor and mesorectal fat). Receiver-operating characteristic (ROC) curve analysis was employed to assess the discrimination performance of the five models. The AUCs of five models were compared by DeLon's test. RESULTS: The training and testing cohorts included 31 (30.1%) and 14 (31.1%) patients with TDs, respectively. The AUCs of multiregional radiomics, single-regional radiomics, and the clinical models for predicting TDs were 0.839, 0.765, and 0.793, respectively. An integrated model incorporating multiregional radiomics features and clinical factors showed good predictive performance for predicting TDs in resectable RC (AUC, 0.931; 95% CI, 0.841-0.988), which demonstrated superiority over clinical model (P = 0.016), the single-regional radiomics model (P = 0.042), and the multiregional radiomics model (P = 0.025). CONCLUSION: An integrated model combining multiregional MRI radiomic features and clinical factors can improve prediction performance for TDs and guide clinicians in implementing treatment plans individually for resectable RC patients.
