PurposeThis study was performed to evaluate the feasibility of visualizing soft tissue lesions and vascular structures using contrast-enhanced cone-beam computed tomography (CE-CBCT) after the intravenous administration of a contrast medium in an animal model.Materials and MethodsCBCT was performed on six rabbits after a contrast medium was administered using an injection dose of 2 mL/kg body weight and an injection rate of 1 mL/s via the ear vein or femoral vein under general anesthesia. Artificial soft tissue lesions were created through the transplantation of autologous fatty tissue into the salivary gland. Volume rendering reconstruction, maximum intensity projection, and multiplanar reconstruction images were reconstructed and evaluated in order to visualize soft tissue contrast and vascular structures.ResultsThe contrast enhancement of soft tissue was possible using all contrast medium injection parameters. An adequate contrast medium injection parameter for facilitating effective CE-CBCT was a 5-mL injection before exposure combined with a continuous 5-mL injection during scanning. Artificial soft tissue lesions were successfully created in the animals. The CE-CBCT images demonstrated adequate opacification of the soft tissues and vascular structures.ConclusionDespite limited soft tissue resolution, the opacification of vascular structures was observed and artificial soft tissue lesions were visualized with sufficient contrast to the surrounding structures. The vascular structures and soft tissue lesions appeared well delineated in the CE-CBCT images, which was probably due to the superior spatial resolution of CE-CBCT compared to other techniques, such as multislice computed tomography.
Convolutional neural networks (CNNs) have rapidly emerged as one of the most promising next-generation artificial intelligence (AI) in the field of medical and dental researches, which can further provide an effective diagnostic methodology allowing for detection of diseases at early age. This study was, thus, aimed to evaluate performances for apical lesion segmentation from panoramic radiographs using two CNN algorithms including U-Net and FPN. A total of 1000 panoramic radiographs showing apical lesions were separated into training (n = 800, 80%), validation (n = 100, 10%), and test (n = 100, 10%) dataset, respectively. These datasets were further incorporated to construct CNN models using two algorithms, respectively. The performances of identifying apical lesions were evaluated after calculating precision, recall, and F1-score from both CNN models. Both U-Net and FPN algorithms provided considerably good performances in identifying apical lesions in panoramic radiographs.
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.