Background: The purpose of this study was to compare the segmentation performances of the 2D, 2.5D, and 3D networks for maxillary sinuses (MSs) and lesions inside the maxillary sinus (MSL) with variations in sizes, shapes, and locations in cone beam CT (CBCT) images under the same constraint of memory capacity.
Methods: The 2D, 2.5D, and 3D networks were compared comprehensively for the segmentation of the MS and MSL in CBCT images under the same constraint of memory capacity. MSLs were obtained by subtracting the prediction of the air region of the maxillary sinus (MSA) from that of the MS.
Results: The 2.5D network showed the highest segmentation performances for the MS and MSA compared to the 2D and 3D networks. The performances of the Jaccard coefficient, Dice similarity coefficient, precision, and recall by the 2.5D network of U-net + + reached 0.947, 0.973, 0.974, and 0.971 for the MS, respectively, and 0.787, 0.875, 0.897, and 0.858 for the MSL, respectively.
Conclusions: The 2.5D segmentation network demonstrated superior segmentation performance for various MSLs with an ensemble learning approach of combining the predictions from three orthogonal planes.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10647072 | PMC |
http://dx.doi.org/10.1186/s12903-023-03607-6 | DOI Listing |
Med Sci Monit
January 2025
Department of Oral Implantology, The Affiliated Stomatology Hospital, Jiangxi Medical College, Nanchang University, Jiangxi Province Key Laboratory of Oral Biomedicine, Jiangxi Province Clinical Research Center for Oral Disease, Nanchang, Jiangxi, China.
BACKGROUND This study included 32 patients with single missing teeth and alveolar bone defects and aimed to compare outcomes from guided bone regeneration with a gelatin/polylactic acid (GT/PLA) barrier membrane and a Guidor® bioresorbable matrix barrier dental membrane. MATERIAL AND METHODS A total of 32 participants were recruited in the clinical study, with single missing teeth and alveolar bone defects, requiring guided bone regeneration (32 missing teeth in total). They were randomly divided into the GT/PLA membrane group (experimental) and Guidor® membrane group (control) by the envelope method (n=16).
View Article and Find Full Text PDFInt J Comput Assist Radiol Surg
January 2025
Department of Medical Biophysics, University of Toronto, Toronto, Canada.
Purpose: During endovascular revascularization interventions for peripheral arterial disease, the standard modality of X-ray fluoroscopy (XRF) used for image guidance is limited in visualizing distal segments of infrapopliteal vessels. To enhance visualization of arteries, an image registration technique was developed to align pre-acquired computed tomography (CT) angiography images and to create fusion images highlighting arteries of interest.
Methods: X-ray image metadata capturing the position of the X-ray gantry initializes a multiscale iterative optimization process, which uses a local-variance masked normalized cross-correlation loss to rigidly align a digitally reconstructed radiograph (DRR) of the CT dataset with the target X-ray, using the edges of the fibula and tibia as the basis for alignment.
BMC Oral Health
January 2025
Department of Orthodontics, Case Western Reserve University School of Dental Medicine, Cleveland, OH, 44106, USA.
Background: The aim of this study was to evaluate the correlation of the volume and minimum axial area (MAA) measurements between different upper and lower boundaries used for oropharyngeal airway assessment.
Methods: Cone Beam Computed Tomography (CBCT) scans of 49 subjects taken for pre-orthognathic surgical planning were obtained retrospectively from the archives (n = 49; 32 females, 17 males; mean age = 20.9 ± 5.
BMC Oral Health
January 2025
Department of Dental Implantology, Jinan Stomatological Hospital, Jinan, 250002, Shandong, People's Republic of China.
Objective: To study the biomechanical changes induced by differences in perioral force in patients with missing anterior maxillary teeth at rest via finite element analysis (FEA).
Methods: Using conical beam CT (CBCT) images of a healthy person, models of the complete maxillary anterior dental region (Model A) and maxillary anterior dental region with a missing left maxillary central incisor (Model B) were constructed. The labial and palatine alveolar bone and tooth surface of the bilateral incisor and cusp regions were selected as the application sites, the resting perioral force was applied perpendicular to the tissue surface, and the changes in maxillary stress and displacement after the perioral force was simulated were analyzed.
BMC Oral Health
January 2025
Beijing Yakebot Technology Co., Ltd, F-616-West Building, Yonghe Plaza, No. 28 Andingmen Dongdajie, DongCheng District, Beijing, 100007, China.
Background: The surgical complexity associated with the palatal roots of maxillary molars was considerably elevated. Previous studies on the relationships between maxillary molar roots and the maxillary sinus or cortical plates have focused on individual root observation without considering the positional relationship between buccal and palatal roots or analysing the surgical pathway of maxillary molar palatal roots. This study aimed to investigate the relationship between maxillary molar palatal roots and adjacent anatomical structures to provide a reference for performing palatal roots endodontic microsurgery.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!