In this study, we aimed to investigate quantitative differences in performance in terms of comparing the automated classification of deep vein thrombosis (DVT) using two categories of artificial intelligence algorithms: deep learning based on convolutional neural networks (CNNs) and conventional machine learning. We retrospectively enrolled 659 participants (DVT patients, 282; normal controls, 377) who were evaluated using contrast-enhanced lower extremity computed tomography (CT) venography. Conventional machine learning consists of logistic regression (LR), support vector machines (SVM), random forests (RF), and extreme gradient boosts (XGB). Deep learning based on CNN included the VGG16, VGG19, Resnet50, and Resnet152 models. According to the mean generated AUC values, we found that the CNN-based VGG16 model showed a 0.007 higher performance (0.982 ± 0.014) as compared with the XGB model (0.975 ± 0.010), which showed the highest performance among the conventional machine learning models. In the conventional machine learning-based classifications, we found that the radiomic features presenting a statistically significant effect were median values and skewness. We found that the VGG16 model within the deep learning algorithm distinguished deep vein thrombosis on CT images most accurately, with slightly higher AUC values as compared with the other AI algorithms used in this study. Our results guide research directions and medical practice.

Background: Duplication of the superficial femoral artery (SFA) is an extremely rare anatomic variation, with few case studies reported. We report one case of the duplicated SFA, discovered by both ultrasonography (US) and computed tomography angiography (CTA). We also reviewed literatures concerning 6 cases of the duplicated SFA (including our present case), and summarized the clinical and imaging features of the anatomic variation. Case presentation: A 55-year-old woman presented to our hospital with an intermittent cramp in the lateral aspect of the right leg. The patient underwent Doppler US examination on bilateral lower extremity arteries and veins to examine potential vascular abnormality. Incidentally, US discovered the duplicated left SFA and CTA of bilateral lower extremities revealed the anatomic orientation, course, length, diameter and distance of the duplicated left SFA. It was revealed to be divided into two trunks with similar luminal diameter and courses parallel. They reunited at distal thigh level. The findings of US and CTA examination did not correspond with the symptom of the patient, and the patient was discharged. Conclusion: We report a rare case of the duplicated SFA diagnosed with the combinations of US and CTA examination, which served as valuable imaging methods to detect and diagnose the vascular anatomic variation in lower extremities.

Spontaneous renal artery thrombosis is a rare cause of flank pain and can have fatal consequences. We report a case of acute renal artery thrombosis in a 61-year-old man who experienced flank pain and had no medical history. A contrast-enhanced computed tomography scan revealed total thrombotic occlusion of the left renal artery. The patient was taken to interventional radiology, and an urgent catheter-directed thrombolysis of the renal artery was performed. The procedure was successful, with the subsequent arteriogram demonstrating a substantial decrease of the thrombus extent and the recanalization of the left renal artery. This case highlights that emergency renal artery thrombolysis is an effective and safe treatment for acute occlusion of the renal artery.

유성현, et al. J Korean Soc Radiol. 2021 Jun;82:e76. https://doi.org/10.3348/jksr.2020.0157

김준성, et al. J Korean Soc Radiol. 2022 Sep;83(5):1032-1045. https://doi.org/10.3348/jksr.2021.0191