BackgroundOvertreatment of axillary lymph node dissection (ALND) may occur in patients with axillary positive sentinel lymph node (SLN) but negative non-SLN (NSLN). Developing a magnetic resonance imaging (MRI)-based radiomics nomogram to predict axillary NSLN metastasis in patients with SLN-positive breast cancer could effectively decrease the probability of overtreatment and optimize a personalized axillary surgical strategy.MethodsThis retrospective study included 285 patients with positive SLN breast cancer. Fifty five of them had metastatic NSLNs and 230 had non-metastatic NSLNs. MRI-based radiomic features of primary tumors were extracted and MRI morphologic findings of the primary tumor and axillary lymph nodes were assessed. Four models, namely, a radiomics signature, an MRI-clinical nomogram, and two MRI-clinical-radiomics nomograms were established based on MRI morphologic findings, clinicopathologic characteristics, and MRI-based radiomic features to predict the NSLN status. The optimal predictors in each model were selected using the 5-fold cross-validation (CV) method. Their predictive performances were determined by the receiver operating characteristic (ROC) curves analysis. The area under the curves (AUCs) of different models was compared by the Delong test. Their discrimination capability, calibration curve, and clinical usefulness were also assessed.ResultsThe 5-fold CV analysis showed that the AUCs ranged from 0.770 to 0.847 for the radiomics signature, from 0.720 to 0.824 for the MRI-clinical nomogram, from 0.843 to 0.932 for the MRI-clinical-radiomics nomogram. The optimal predictive factors in the radiomics signature, MRI-clinical nomogram, and MRI-clinical-radiomics nomogram were one texture feature of diffusion-weighted imaging (DWI), two clinicopathologic features together with one MRI morphologic finding, and the DWI-based texture feature together with the two clinicopathologic features plus the one MRI morphologic finding, respectively. The MRI-clinical-radiomics nomogram with CA 15-3 included achieved the highest AUC compared with the radiomics signature (0.868 vs. 0.806, P <0.001) and MRI-clinical nomogram (0.868 vs. 0.761; P <0.001). In addition, the MRI-clinical-radiomics nomogram without CA 15-3 showed a higher performance than that of the radiomics signature (AUC, 0.852 vs. 0.806, P = 0.016) and the MRI-clinical nomogram (AUC, 0.852 vs. 0.761, P = 0.007). The MRI-clinical-radiomics nomograms showed good discrimination and good calibration. Decision curve analysis demonstrated that the MRI-clinical-radiomics nomograms were clinically useful.ConclusionThe MRI-clinical-radiomics nomograms developed in our study showed high predictive performance, which can be used to predict the axillary NSLN status in SLN-positive breast cancer patients before surgery.

Cardiovascular disease (CVD) is the leading cause of death among patients in China, and cardiac computed tomography (CT) is one of the most commonly used examination methods for CVD. Coronary artery CT angiography can be used for the morphologic evaluation of the coronary artery. At present, cardiac CT functional imaging has become an important direction of development of CT. At present, common CT functional imaging technologies include transluminal attenuation gradient, stress dynamic CT myocardial perfusion imaging, and CT-fractional flow reserve. These three imaging modes are introduced and analyzed in this review.

Active pulmonary tuberculosis (ATB), which is more infectious and has a higher mortality rate compared with non-active pulmonary tuberculosis (non-ATB), needs to be diagnosed accurately and timely to prevent the tuberculosis from spreading and causing deaths. However, traditional differential diagnosis methods of active pulmonary tuberculosis involve bacteriological testing, sputum culturing and radiological images reading, which is time consuming and labour intensive. Therefore, an artificial intelligence model for ATB differential diagnosis would offer great assistance in clinical practice. In this study, computer tomography (CT) scans images and corresponding clinical information of 1160 ATB patients and 1131 patients with non-ATB were collected and divided into training, validation, and testing sets. A 3-dimension (3D) Nested UNet model was utilized to delineate lung field regions in the CT images, and three different pre-trained deep learning models including 3D VGG-16, 3D EfficientNet and 3D ResNet-50 were used for classification and differential diagnosis task. We also collected an external testing set with 100 ATB cases and 100 Non-ATB cases for further validation of the model. In the internal and external testing set, the 3D ResNet-50 model outperformed other models, reaching an AUC of 0.961 and 0.946, respectively. The 3D ResNet-50 model reached even higher levels of diagnostic accuracy than experienced radiologists, while the CT images reading and diagnosing speed was 10 times faster than human experts. The model was also capable of visualizing clinician interpretable lung lesion regions important for differential diagnosis, making it a powerful tool assisting ATB diagnosis. In conclusion, we developed an auxiliary tool to differentiate active and non-active pulmonary tuberculosis, which would have broad prospects in the bedside.

Objective: To develop a CT image-based deep learning framework (3D-ResNet) as a new technology for the early warning of active and secondary pulmonary tuberculosis.Methods: Chest CT images of patients with active pulmonary tuberculosis (n=1,160) and secondary pulmonary tuberculosis (n=1,131) diagnosed via bacteriological examination were retrospectively collected to analyze differences between the clinical and imaging presentations of the two diseases. Lung field regions were presegmented by using a 3D Nested UNet model, and a 3D-ResNet model was developed for training the classification model. The data were randomly grouped at a ratio of 7:2:1 for training, validation and testing. Area under the curve (AUC), accuracy (ACC), recall and F1 scores were used as model evaluation metrics, and class activation mapping were used to evaluate the activation regions of interest.Results: Patients with active pulmonary tuberculosis were older than those with secondary pulmonary tuberculosis. Additionally, patients with active pulmonary tuberculosis were observed to cough more, and patients with secondary pulmonary tuberculosis experienced more chest pain. The differences were statistically significant (p<0.05). The AUC values of the model on the validation and test datasets were 0.948 and 0.945, respectively, with ACC values being 0.973 and 0.969, Recall values being 0.941 and 0.949 and F1 scores being 0.977 and 0.969, respectively. Conclusion: This study demonstrated that 3D-ResNet can be used as a rapid auxiliary diagnostic tool for differentiating active pulmonary tuberculosis and secondary pulmonary tuberculosis, which can help patients with active pulmonary tuberculosis in receiving timely treatment, in reducing transmission and in avoiding overtreatment. Additionally, this tool can aid secondary pulmonary tuberculosis patients who are misdiagnosed as having active pulmonary tuberculosis.