Search

Background: Detecting molecular drivers is crucial in the management of non-small-cell lung cancer (NSCLC). This study aimed to evaluate the use of pretreatment chest computed tomography (CT) radiomics features for predicting epidermal growth factor receptor (EGFR) mutation status in NSCLC. Materials and Methods: CT images were used to develop a radiomics-based model for predicting EGFR mutation status. Two different groups were formed from the dataset, namely groups for training (n = 380) and testing (n = 86). Feature selection was performed using the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm on a radiomics platform. Machine learning methods were then applied to construct the radiomics models. Receiver operating characteristic curve analysis was conducted to assess the performance of the radiomics signature across different datasets and methods. Results: The frequency of EGFR mutation was 13.5% (58/430). A total of 1409 quantitative imaging features were extracted from CT images using the Radcloud platform. Among the six radiomics-based classifiers (k-Nearest Neighbor, Support Vector Machine (SVM), eXtreme Gradient Boosting, Random Forest, Logistic Regression, and Decision Tree), SVM demonstrated the highest area under the curve values in both the testing and training groups, reaching 0.87 and 0.98, respectively. Our model, which incorporated both clinical and radiomics data, successfully predicted EGFR mutation status with an accuracy rate of 86.9%. Conclusion: Our findings highlight the potential of radiomics features as a non-invasive predictive imaging biomarker for EGFR mutation status, which could enhance personalized treatment in NSCLC. Radiomics emerges as a valuable tool for identifying driver mutations, although further studies are necessary to validate its clinical utility in NSCLC. [ABSTRACT FROM AUTHOR]

Purpose: We aimed to assess the diagnostic performance of transluminal attenuation difference (TAD) in predicting the severity of internal carotid artery (ICA) stenosis.Methods: The study cohort consisted of 48 patients with <50% stenosis, 50%-69% stenosis, 70%-99% stenosis, and 51 controls without plaque development in ICA. A total of 143 measurements were performed through right and left internal and common carotid arteries. The TAD ratio was calculated as the difference between the mean attenuation values of the common carotid artery (CCA) and ICA, divided by the MAV of the CCA, multiplied by 100.Results: TAD ratio was significantly higher in severe (>70%) stenosis compared with control arteries and low-moderate stenosis. A TAD ratio cutoff of 4.5 predicted 70%-99% stenosis with a sensitivity of 100% and specificity of 93%. The inter- and intraobserver agreements in TAD measurements were almost perfect (ICC, 0.89-0.86).Conclusion: Assessment of TAD ratio predicts the degree of stenosis in concordance with NASCET system. [ABSTRACT FROM AUTHOR]

Purpose: We aimed to evaluate the frequency of bile duct branching pattern variations at the hepatic confluence in patients with pancreas divisum (PD).Methods: A search was performed through the hospital database using the keyword "pancreas divisum" to identify patients. The magnetic resonance cholangiopancreatography (MRCP) images of 137 patients who were diagnosed with PD between August 2011 and November 2016 were retrospectively analyzed for the presence of bile duct variations. A control group of 137 patients without PD was established among patients investigated during the same period. Variations of the biliary tract were grouped into seven types according to the McSweeney et al. classification.Results: Biliary tract variations were detected in 103 of a total of 274 patients. Fifty-eight PD patients (42.3%) and 45 control patients (32.8%) had bile duct variation at the hepatic confluence level. The patients with PD were more likely to have biliary tract variation compared with the control group; however, it was not statistically significant (P = 0.105). The most common variation in PD patients was type 3a variation (16.8%).Conclusion: MRCP studies showed atypical bile duct confluence pattern in nearly half of both PD patients and controls. There was no statistically significant difference in the frequency of anatomic variations at bile duct confluence in patients with PD versus those without PD. Derivation of these structures from different outpouchings in early embryological life may explain this insignificant difference. [ABSTRACT FROM AUTHOR]

To compare the diagnostic performance of a newly developed artificial intelligence (AI) algorithm derived from the fusion of convolution neural networks (CNN) versus human observers in the estimation of malignancy risk in pulmonary nodules. The study population consists of 158 nodules from 158 patients. All nodules (81 benign and 77 malignant) were determined to be malignant or benign by a radiologist based on pathologic assessment and/or follow-up imaging. Two radiologists and an AI platform analyzed the nodules based on the Lung-RADS classification. The two observers also noted the size, location, and morphologic features of the nodules. An intraclass correlation coefficient was calculated for both observers and the AI; ROC curve analysis was performed to determine diagnostic performances. Nodule size, presence of spiculation, and presence of fat were significantly different between the malignant and benign nodules (p < 0.001, for all three). Eighteen (11.3%) nodules were not detected and analyzed by the AI. Observer 1, observer 2, and the AI had an AUC of 0.917 ± 0.023, 0.870 ± 0.033, and 0.790 ± 0.037 in the ROC analysis of malignity probability, respectively. The observers were in almost perfect agreement for localization, nodule size, and lung-RADS classification [κ (95% CI)=0.984 (0.961–1.000), 0.978 (0.970–0.984), and 0.924 (0.878–0.970), respectively]. The performance of the fusion AI algorithm in estimating the risk of malignancy was slightly lower than the performance of the observers. Fusion AI algorithms might be applied in an assisting role, especially for inexperienced radiologists. In this study, we proposed a fusion model using four state-of-art object detectors for lung nodule detection and discrimination. The use of fusion of deep learning neural networks might be used in a supportive role for radiologists when interpreting lung nodule discrimination. [ABSTRACT FROM AUTHOR]