ABSTRACT
Computed tomography has gained an important role in the early diagnosis of COVID-19 pneumonia. However, the ever-increasing number of patients has overwhelmed radiology departments and has caused a reduction in quality of services. Artificial intelligence (AI) systems are the remedy to the current situation. However, the lack of application in real-world conditions has limited their consideration in clinical settings. This study validated a clinical AI system, COVIDiag, to aid radiologists in accurate and rapid evaluation of COVID-19 cases. 50 COVID-19 and 50 non-COVID-19 pneumonia cases were included from each of five centers: Argentina, Turkey, Iran, Netherlands, and Italy. The Dutch database included only 50 COVID-19 cases. The performance parameters namely sensitivity, specificity, accuracy, and area under the ROC curve (AUC) were computed for each database using COVIDiag model. The most common pattern of involvement among COVID-19 cases in all databases were bilateral involvement of upper and lower lobes with ground-glass opacities. The best sensitivity of 92.0% was recorded for the Italian database. The system achieved an AUC of 0.983, 0.914, 0.910, and 0.882 for Argentina, Turkey, Iran, and Italy, respectively. The model obtained a sensitivity of 86.0% for the Dutch database. COVIDiag model could diagnose COVID-19 pneumonia in all of cohorts with AUC of 0.921 (sensitivity, specificity, and accuracy of 88.8%, 87.0%, and 88.0%, respectively). Our study confirmed the accuracy of our proposed AI model (COVIDiag) in the diagnosis of COVID-19 cases. Furthermore, the system demonstrated consistent optimal diagnostic performance on multinational databases, which is critical to determine the generalizability and objectivity of the proposed COVIDiag model. Our results are significant as they provide real-world evidence regarding the applicability of AI systems in clinical medicine.
ABSTRACT
PURPOSE: The most important prognostic variable for early stage breast cancer is the status of axillary lymph nodes. The aim of this study was to evaluate the diagnostic accuracy of preoperative magnetic resonance imaging (MRI) for metastatic axillary lymph node in breast cancer cases with post-operative sentinel lymph node biopsy (SLNB) results. MATERIALS AND METHODS: Women aged between 21 and 73 years who were diagnosed with malignant mass lesion of the breast between 2013 and 2015 were included in this study. The preoperative MR images of patients with diagnosis of breast cancer was evaluated to determine axillary lymph node status. Axillary lymph node size, long axis to short axis ratio, lymph node contours, cortical thickness to anteroposterior diameter ratio, the presence of a fatty hilum and contrast enhancement patterns (homogenous or heterogenous) was noted. Additionally, the presence of comet tail sign which a tail extending from an enhancing breast lesion into the parenchyma and might represent ductal infiltration on post-contrast series was also noted. All data obtained from this evaluation was compared with postoperative SLNB results. RESULTS: Metastatic nodes were found to have a longer short axis when compared to reactive nodes (p = 0.042; p < 0.05). The long axis to short axis ratio was notably lower in metastatic nodes when compared to reactive nodes. Cortical thickness was higher in metastatic nodes when compared to reactive nodes (p = 0.024; p < 0.05). Comet sign was observed in 15 of metastatic nodes (73.3 %) and in one (5 %) reactive node. This difference was statistically significant (p = 0.001; p < 0.01). While fatty hilum was seen in 40 % of metastatic nodes (n = 6), it was seen in all (n = 20) reactive nodes. This difference was statistically significant (p = 0.001; p < 0.01). CONCLUSIONS: MRI is a non invasive sensitive and specific imaging modality for evaluating the axilla. We have shown that with the help of comet tail sign and status of fatty hilum contrast enhanced MRI has the highest sensitivity of 84.7 % for detecting axillary lymph node metastases (Singletary et al. in Semin Surg Oncol 21(1):53-59, 2003).
