ObjectiveTo construct a multimodal imaging radiomics model based on enhanced CT features to predict tumor regression grade (TRG) in patients with locally advanced rectal cancer (LARC) following neoadjuvant chemoradiotherapy (NCRT). MethodsA retrospective analysis was conducted on the Database from Colorectal Cancer (DACCA) at West China Hospital of Sichuan University, including 199 LARC patients treated from October 2016 to October 2023. All patients underwent total mesorectal excision after NCRT. Clinical pathological information was collected, and radiomics features were extracted from CT images prior to NCRT. Python 3.13.0 was used for feature dimension reduction, and univariate logistic regression (LR) along with Lasso regression with 5-fold cross-validation were applied to select radiomics features. Patients were randomly divided into training and testing sets at a ratio of 7∶3 for machine learning and joint model construction. The model’s performance was evaluated using accuracy, sensitivity, specificity, and the area under the curve (AUC). Receiver operating characteristic curve (ROC), confusion matrices, and clinical decision curves (DCA) were plotted to assess the model’s performance. ResultsAmong the 199 patients, 155 (77.89%) had poor therapeutic outcomes, while 44 (22.11%) had good outcomes. Univariate LR and Lasso regression identified 8 clinical pathological features and 5 radiomic features, including 1 shape feature, 2 first-order statistical features, and 2 texture features. LR, support vector machine (SVM), random forest (RF), and eXtreme gradient boosting (XGBoost) models were established. In the training set, the AUC values of LR, SVM, RF, XGBoost models were 0.99, 0.98, 1.00, and 1.00, respectively, with accuracy rates of 0.94, 0.93, 1.00, and 1.00, sensitivity rates of 0.98, 1.00, 1.00, and 1.00, and specificity rates of 0.80, 0.67, 1.00, and 1.00, respectively. In the testing set, the AUC values of 4 models were 0.97, 0.92, 0.96, and 0.95, with accuracy rates of 0.87, 0.87, 0.88, and 0.90, sensitivity rates of 1.00, 1.00, 1.00, and 0.95, and specificity rates of 0.50, 0.50, 0.56, and 0.75. Among the models, the XGBoost model had the best performance, with the highest accuracy and specificity rates. DCA indicated clinical benefits for all 4 models. ConclusionsThe multimodal imaging radiomics model based on enhanced CT has good clinical application value in predicting the efficacy of NCRT in LARC. It can accurately predict good and poor therapeutic outcomes, providing personalized clinical surgical interventions.
ObjectiveTo analyze the association between preoperative staging (cTNM) and neoadjuvant therapy regimen decision-making and efficacy in patients with rectal cancer in the current version of Database from Colorectal Cancer (DACCA). MethodsThe data analysis for this study selected the DACCA version updated on April 20, 2024. The patient information was collected and categorized into three stages (Ⅱ, Ⅲ, and Ⅳ). The differences in neoadjuvant treatment decision-making and therapeutic effects, including gross changes, imaging changes, and tumor regression grade (TRG), were analyzed. ResultsA total of 3 158 eligible cases were collected in this study, with complete preoperative staging and neoadjuvant therapy decision-making data available for 2 370 patients. There were statistically significant differences in the overall comparison among the patients with rectal cancer in terms of the selection of combined targeted therapy, radiotherapy regimens, and the intensity of neoadjuvant chemotherapy by patients at different preoperative stages (χ²=42.239, P<0.001; χ²=41.615, P<0.001; H=1.161, P=0.004). Specifically, the proportion of patients choosing combined targeted therapy and combined radiotherapy gradually increased as the stage advanced. Among patients at different stages, the proportion of those choosing medium-course chemotherapy was the highest, and the proportion of patients choosing long-course chemotherapy was the highest among those with more advanced stages. Regarding the gross changes, imaging changes, and TRG results after neoadjuvant treatment in the patients at different preoperative stages, there were statistically significant differences in the overall comparison among patients with stage Ⅱ, Ⅲ, and Ⅳ rectal cancer (H=7.860, P=0.020; H=9.845, P=0.007; H=6.680, P=0.035). The proportion of partial response was the highest across all response metrics (macroscopic, radiographic, and TRG) in each stage. Notably, stage Ⅱ patients demonstrated the highest rate of complete response. For TRG evaluation, grade 2 (TRG2) was the most common outcome across all stages. ConclusionsData analysis from DACCA reveals that patients with advanced stages are more likely to choose chemotherapy combined with targeted therapy or radiotherapy, and had a higher proportion of intermediate range chemotherapy and the intensity of neoadjuvant chemotherapy is stronger. In terms of neoadjuvant treatment effects, the earlier the staging, the better the gross and imaging changes, and the lower the TRG level.