No abstract

BackgroundIntracranial aneurysm (IA) is a nodular protrusion of the arterial wall caused by the localized abnormal enlargement of the lumen of a brain artery, which is the primary cause of subarachnoid hemorrhage. Accurate rupture risk prediction can effectively aid treatment planning, but conventional rupture risk estimation based on clinical information is subjective and time-consuming.MethodsWe propose a novel classification method based on the CTA images for differentiating aneurysms that are prone to rupture. The main contribution of this study is that the learning-based method proposed in this study leverages deep learning and radiomics features and integrates clinical information for a more accurate prediction of the risk of rupture. Specifically, we first extracted the provided aneurysm regions from the CTA images as 3D patches with the lesions located at their centers. Then, we employed an encoder using a 3D convolutional neural network (CNN) to extract complex latent features automatically. These features were then combined with radiomics features and clinical information. We further applied the LASSO regression method to find optimal features that are highly relevant to the rupture risk information, which is fed into a support vector machine (SVM) for final rupture risk prediction.ResultsThe experimental results demonstrate that our classification method can achieve accuracy and AUC scores of 89.78% and 89.09%, respectively, outperforming all the alternative methods.DiscussionOur study indicates that the incorporation of CNN and radiomics analysis can improve the prediction performance, and the selected optimal feature set can provide essential biomarkers for the determination of rupture risk, which is also of great clinical importance for individualized treatment planning and patient care of IA.

Background Lymph node metastasis is an important factor affecting the treatment and prognosis of patients with cervical cancer. However, the comparison of different algorithms and features to predict lymph node metastasis is not well understood. This study aimed to construct a non-invasive model for predicting lymph node metastasis in patients with cervical cancer based on clinical features combined with the radiomic features of magnetic resonance imaging (MRI) images. Methods A total of 180 cervical cancer patients were divided into the training set (n = 126) and testing set (n = 54). In this cross-sectional study, radiomic features of MRI images and clinical features of patients were collected. The least absolute shrinkage and selection operator (LASSO) regression was used to filter the features. Seven machine learning methods, including eXtreme Gradient Boosting (XGBoost), Logistic Regression, Multinomial Naive Bayes (MNB), Support Vector Machine (SVM), Decision Tree, Random Forest, and Gradient Boosting Decision Tree (GBDT) are used to build the models. Receiver operating characteristics (ROC) curve and area under the curve (AUC), accuracy, sensitivity, and specificity were calculated to assess the performance of the models. Results Of these 180 patients, 49 (27.22%) patients had lymph node metastases. Five of the 122 radiomic features and 3 clinical features were used to build predictive models. Compared with other models, the MNB model was the most robust, with its AUC, specificity, and accuracy on the testing set of 0.745 (95%CI: 0.740–0.750), 0.900 (95%CI: 0.807–0.993), and 0.778 (95%CI: 0.667–0.889), respectively. Furthermore, the AUCs of the MNB models with clinical features only, radiomic features only, and combined features were 0.698 (95%CI: 0.692–0.704), 0.632 (95%CI: 0.627–0.637), and 0.745 (95%CI: 0.740–0.750), respectively. Conclusion The MNB model, which combines the radiomic features of MRI images with the clinical features of the patient, can be used as a non-invasive tool for the preoperative assessment of lymph node metastasis.