The detection and segmentation of thrombi are essential for monitoring the disease progression of abdominal aortic aneurysms (AAAs) and for patient care and management. As they have inherent capabilities to learn complex features, deep convolutional neural networks (CNNs) have been recently introduced to improve thrombus detection and segmentation. However, investigations into the use of CNN methods is in the early stages and most of the existing methods are heavily concerned with the segmentation of thrombi, which only works after they have been detected. In this work, we propose a fully automated method for the whole process of the detection and segmentation of thrombi, which is based on a well-established mask region-based convolutional neural network (Mask R-CNN) framework that we improve with optimized loss functions. The combined use of complete intersection over union (CIoU) and smooth L1 loss was designed for accurate thrombus detection and then thrombus segmentation was improved with a modified focal loss. We evaluated our method against 60 clinically approved patient studies (i.e., computed tomography angiography (CTA) image volume data) by conducting 4-fold cross-validation. The results of comparisons to multiple other state-of-the-art methods suggested the superior performance of our method, which achieved the highest F1 score for thrombus detection (0.9197) and outperformed most metrics for thrombus segmentation.
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.
Purpose: To report a case of delayed splenic rupture after percutaneous transsplenic portal vein stent deployment. Case Report: A 72-year-old male patient presented at a medical center with abdominal pain and reduced liver function according to laboratory tests. Due to a history of right hemihepatectomy and left portal vein occlusion, the percutaneous transhepatic approach was considered inappropriate. Instead, percutaneous transsplenic access was selected as a suitable procedure for portal vein catheterization. Eight days following the procedure, the patient developed abdominal pain, and a computed tomography scan showed a small splenic pseudoaneurysm that was underappreciated at the time. Patient suffered acute splenic rupture 32 days post-procedure. Subsequent embolization was performed, achieving complete hemostasis. Conclusion: The transsplenic approach should be considered when the transhepatic or transjugular approach is unfeasible or difficult to implement. A careful plugging of the puncture tract is necessary to prevent or minimize hemorrhage from the splenic access tract. In addition, careful serial follow-up computed tomography should be used to evaluate the splenic puncture tract.
Purpose To evaluate the safety, efficacy, and long-term outcome of bronchial artery embolization (BAE) in the treatment of non-massive hemoptysis and the prognostic factors associated with recurrent bleeding. Materials and methods From March 2005 to September 2014, BAE was performed in 233 patients with non-massive hemoptysis. All patients had a history of persistent or recurrent hemoptysis despite conservative medical treatment. We assessed the technical and clinical success, recurrence, prognostic factors related to recurrent bleeding, recurrence-free survival rate, additional treatment, and major complications in all the patients. Results Technical success was achieved in 224 patients (96.1%), and clinical success was obtained in 219 (94.0%) of the 233 patients. In addition, 64 patients (27.5%) presented hemoptysis recurrence with median time of 197 days after embolization. Tuberculosis sequelae and presence of aberrant bronchial artery or non-bronchial systemic collaterals were significantly related to recurrent bleeding (p < 0.05). The use of Histoacryl-based embolic materials significantly reduced the recurrent bleeding rate (p < 0.05). Patient who had a tuberculosis sequelae showed a significantly lower recurrence-free survival rate (p = 0.013). Presence of aberrant bronchial artery or non-bronchial systemic collaterals showed a statistically significant correlation with recurrence-free survival rate (p = 0.021). No patients had major complications during follow-up. Conclusions BAE is a safe and effective treatment to manage non-massive hemoptysis. The procedure may offer a better long-term control of recurrent hemoptysis and quality of life than conservative therapy alone.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.