Purpose: This study aimed to establish a deep learning radiomics nomogram (DLRN) based on multiparametric MR images for predicting the response to neoadjuvant chemotherapy (NACT) in patients with locally advanced cervical cancer (LACC). Methods: Patients with LACC (FIGO stage IB-IIIB) who underwent preoperative NACT were enrolled from center 1 (220 cases) and center 2 (independent external validation dataset, 65 cases). Handcrafted and deep learning-based radiomics features were extracted from T2WI, DWI and contrast-enhanced (CE)-T1WI, and radiomics signatures were built based on the optimal features. Two types of radiomics signatures and clinical features were integrated into the DLRN for prediction. The AUC, calibration curve and decision curve analysis (DCA) were employed to illustrate the performance of these models and their clinical utility. In addition, disease-free survival (DFS) was assessed by Kaplan–Meier survival curves based on the DLRN. Results: The DLRN showed favorable predictive values in differentiating responders from nonresponders to NACT with AUCs of 0.963, 0.940 and 0.910 in the three datasets, with good calibration (all p > 0.05). Furthermore, the DLRN performed better than the clinical model and handcrafted radiomics signature in all datasets (all p < 0.05) and slightly higher than the DL-based radiomics signature in the internal validation dataset (p = 0.251). DCA indicated that the DLRN has potential in clinical applications. Furthermore, the DLRN was strongly correlated with the DFS of LACC patients (HR = 0.223; p = 0.004). Conclusion: The DLRN performed well in preoperatively predicting the therapeutic response in LACC and could provide valuable information for individualized treatment.
Objectives: The ADNEX model offered a good diagnostic performance for discriminating adnexal tumors, but research comparing the abilities of the ADNEX model and MRI for characterizing adnexal tumors has not been reported to our knowledge. The aim of this study was to evaluate the diagnostic accuracy of the ultrasound-based ADNEX (Assessment of Different NEoplasias in the adneXa) model in comparison with that of magnetic resonance imaging (MRI) for differentiating benign, borderline and malignant adnexal masses.Methods: This prospective study included 529 women with adnexal masses who underwent assessment via the ADNEX model and subjective MRI analysis before surgical treatment between October 2019 and April 2022 at two hospitals. Postoperative histological diagnosis was considered the gold standard.Results: Among the 529 women, 92 (17.4%) masses were diagnosed histologically as malignant tumors, 67 (12.7%) as borderline tumors, and 370 (69.9%) as benign tumors. For the diagnosis of malignancy, including borderline tumors, overall agreement between the ADNEX model and MRI pre-operation was 84.9%. The sensitivity of the ADNEX model of 0.91 (95% confidence interval [CI]: 0.85–0.95) was similar to that of MRI (0.89, 95% CI: 0.84–0.94; P=0.717). However, the ADNEX model had a higher specificity (0.90, 95% CI: 0.87–0.93) than MRI (0.81, 95% CI: 0.77–0.85; P=0.001). The greatest sensitivity (0.96, 95% CI: 0.92–0.99) and specificity (0.94, 95% CI: 0.91–0.96) were achieved by combining the ADNEX model and subjective MRI assessment. While the total diagnostic accuracy did not differ significantly between the two methods (P=0.059), the ADNEX model showed greater diagnostic accuracy for borderline tumors (P<0.001).Conclusion: The ultrasound-based ADNEX model demonstrated excellent diagnostic performance for adnexal tumors, especially borderline tumors, compared with MRI. Accordingly, we recommend that the ADNEX model, alone or with subjective MRI assessment, should be used for pre-operative assessment of adnexal masses.