Prediction of Perianal Fistula in Crohn's Disease by Computed Tomography Enterography.

BACKGROUND/AIMS:  The purpose of this study was to investigate whether computed tomography enterography can be used to predict the presence of perianal fistula in Crohn's disease patients. MATERIALS AND METHODS:  According to the presentation of perianal fistula or not, this study divided retrospectively included Crohn's disease patients into 2 groups. The disease duration, incidence of involved intestinal segments, and scoring of the activity of the lesions in all patients were statistically analyzed to explore significant factors between the 2 groups. The statistically significant findings identified in the univariate analysis were incorporated into the multivariate analysis. Logistic regression models were subsequently constructed to assess the predictive factors associated with the occurrence of perianal fistula in individuals with Crohn's disease.The contribution of each factor to the outcome variable was confirmed by the nomogram. The clinical utility of the nomogram was confirmed by calibration and decision curves. RESULTS:  There were 40 cases with perianal Crohn's disease and 58 without perianal Crohn's disease. After univariate and multivariate analysis, disease duration (early stage of Crohn's disease), ascending colon, and rectum were identified as the independent predictive factors for perianal fistula in Crohn's disease patients. The clinical utility of the nomogram was effective, which implied potential benefits for Crohn's disease patients. CONCLUSION:  Computed tomography enterography can be used to predict the presence of perianal fistula in Crohn's disease patients by analyzing the location and the stage of the disease.

Deep learning-based radiomic nomograms for predicting Ki67 expression in prostate cancer.

BACKGROUND: To explore the value of a multiparametric magnetic resonance imaging (MRI)-based deep learning model for the preoperative prediction of Ki67 expression in prostate cancer (PCa). MATERIALS: The data of 229 patients with PCa from two centers were retrospectively analyzed and divided into training, internal validation, and external validation sets. Deep learning features were extracted and selected from each patient's prostate multiparametric MRI (diffusion-weighted imaging, T2-weighted imaging, and contrast-enhanced T1-weighted imaging sequences) data to establish a deep radiomic signature and construct models for the preoperative prediction of Ki67 expression. Independent predictive risk factors were identified and incorporated into a clinical model, and the clinical and deep learning models were combined to obtain a joint model. The predictive performance of multiple deep-learning models was then evaluated. RESULTS: Seven prediction models were constructed: one clinical model, three deep learning models (the DLRS-Resnet, DLRS-Inception, and DLRS-Densenet models), and three joint models (the Nomogram-Resnet, Nomogram-Inception, and Nomogram-Densenet models). The areas under the curve (AUCs) of the clinical model in the testing, internal validation, and external validation sets were 0.794, 0.711, and 0.75, respectively. The AUCs of the deep models and joint models ranged from 0.939 to 0.993. The DeLong test revealed that the predictive performance of the deep learning models and the joint models was superior to that of the clinical model (p < 0.01). The predictive performance of the DLRS-Resnet model was inferior to that of the Nomogram-Resnet model (p < 0.01), whereas the predictive performance of the remaining deep learning models and joint models did not differ significantly. CONCLUSION: The multiple easy-to-use deep learning-based models for predicting Ki67 expression in PCa developed in this study can help physicians obtain more detailed prognostic data before a patient undergoes surgery.