ABSTRACT
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.
ABSTRACT
Objective: Preoperative identification of lymphovascular invasion (LVI) in patients with invasive breast cancer is challenging due to absence of reliable biomarkers or tools in clinical settings. We aimed to establish and validate multiparametric magnetic resonance imaging (MRI)-based radiomic models to predict the risk of lymphovascular invasion (LVI) in patients with invasive breast cancer. Methods: This retrospective study included a total of 175 patients with confirmed invasive breast cancer who had known LVI status and preoperative MRI from two tertiary centers. The patients from center 1 was randomly divided into a training set (n=99) and a validation set (n = 26), while the patients from center 2 was used as a test set (n=50). A total of 1409 radiomic features were extracted from the T2-weighted imaging (T2WI), dynamic contrast-enhanced (DCE) imaging, diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC), respectively. A three-step feature selection including SelectKBest, interclass correlation coefficients (ICC), and least absolute shrinkage and selection operator (LASSO) was performed to identify the features most associated with LVI. Subsequently, a Support Vector Machine (SVM) classifier was trained to develop single-layer radiomic models and fusion radiomic models. Model performance was evaluated and compared by the area under the curve (AUC), sensitivity, and specificity. Results: Based on one feature of wavelet-HLH_gldm_GrayLevelVariance, the ADC radiomic model achieved an AUC of 0.87 (95% confidence interval [CI]: 0.80-0.94) in the training set, 0.87 (0.70-1.00) in the validation set, and 0.77 (95%CI: 0.64-0.86) in the test set. However, the combination of radiomic features derived from other MR sequences failed to yield incremental value. Conclusions: ADC-based radiomic model demonstrated a favorable performance in predicting LVI prior to surgery in patients with invasive breast cancer. Such model holds the potential for improving clinical decision-making regarding treatment for breast cancer.
