98%
921
2 minutes
20
Scaphoid nonunion advanced collapse (SNAC) is a common form of wrist arthritis, the treatment of which depends on the arthritic stage. The Vender classification serves to describe SNAC arthritis based on a single posteroanterior (PA) radiograph. The purpose of this study was to evaluate the intraobserver and interobserver agreement of the Vender classification, comparing multi versus single radiographic views. A retrospective review of patients with SNAC arthritis who underwent a proximal row carpectomy or a 4-corner fusion was performed. The included patients had 3 radiographic views of the pathologic wrist. Fifteen patients were analyzed by 5 blinded reviewers. Wrists were graded using the Vender classification first on the PA view and then using multiview radiographs. The intraobserver and interobserver agreement was determined using weighted kappa analysis. χ tests were calculated comparing the evaluation between single- versus multiview radiographs and determining a higher Vender stage. Multiview radiographs demonstrated a higher intraobserver κ compared with single-view radiographs (0.72 vs 0.66), both representing substantial agreement. The average interobserver agreement was moderate (κ of 0.48) for single view and slight (κ of 0.30) for multiview evaluation. Evaluating multiview radiographs was 6.37 times more likely to demonstrate Vender stage 3 arthritis compared with single view (odds ratio = 6.37 [confidence interval, 3.81-10.64], < .0001). Reviewing multiview radiographs more commonly yielded Vender stage 3 osteoarthritis classification. The decreased interrater reliability in the multiview analysis is likely related to the increased number of articular surfaces evaluated. Using a single PA view may underestimate the severity of arthritis present.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9112731 | PMC |
http://dx.doi.org/10.1177/1558944720937359 | DOI Listing |
J Imaging
July 2025
Science and Innovation Center "Artificial Intelligence", Astana IT University, Astana 010000, Kazakhstan.
Mammography is the main method for early detection of breast cancer, which is still a major global health concern. However, inter-reader variability and the inherent difficulty of interpreting subtle radiographic features frequently limit the accuracy of diagnosis. A thorough assessment of deep convolutional neural networks (CNNs) for automated mammogram classification is presented in this work, along with the introduction of two innovative multi-view integration techniques: Dual-Branch Ensemble (DBE) and Merged Dual-View (MDV).
View Article and Find Full Text PDFStud Health Technol Inform
August 2025
Department of Transdisciplinary Medicine, Seoul National University Hospital.
The diagnosis of craniosynostosis, a condition involving the premature fusion of cranial sutures in infants, is essential for ensuring timely treatment and optimal surgical outcomes. Current diagnostic approaches often require CT scans, which expose children to significant radiation risks. To address this, we present a novel deep learning-based model utilizing multi-view X-ray images for craniosynostosis detection.
View Article and Find Full Text PDFSci Rep
July 2025
Beijing Key Laboratory of Advanced Manufacturing Technology, College of Mechanical & Energy Engineering, Beijing University of Technology, Beijing, 100124, China.
2D/3D medical image registration is crucial for image-guided surgery and medical research. Single-view methods often lack depth information, while multiview approaches typically rely on large-scale training datasets, which may not always be available in clinical scenarios. This paper explores the feasibility of multiview registration with insufficient data.
View Article and Find Full Text PDFCardiovasc Eng Technol
August 2025
College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China.
Purpose: Aortic dissection (AD) is a rare condition with a high mortality rate, necessitating accurate and rapid diagnosis. This study develops an automated deep learning pipeline for identifying, segmenting, and Stanford subtyping AD using computed tomography angiography (CTA) images.
Methods: This pipeline consists of four interconnected modules: aorta segmentation, AD identification, true lumen (TL) and false lumen (FL) segmentation, and Stanford subtyping.
IEEE Trans Med Imaging
June 2025
Medical vision-language alignment through cross-modal contrastive learning shows promising performance in image-text matching tasks, such as retrieval and zero-shot classification. However, conventional cross-modal contrastive learning (CLIP-based) methods suffer from suboptimal visual representation capabilities, which also limits their effectiveness in vision-language alignment. In contrast, although the models pretrained via multimodal masked modeling struggle with direct cross-modal matching, they excel in visual representation.
View Article and Find Full Text PDF