Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.2214/AJR.25.33799 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Closing the loop: nine-year outcomes of an electronic medical record-based protocol for reporting incidental imaging findings.
J Am Coll Radiol
September 2025
Chair, Department of Radiology, Northwestern University Feinberg School of Medicine, Northwestern Medicine, Chicago, IL, USA.
Introduction: Incidental findings in radiology are common, especially with rising imaging volumes. Early disease recognition can greatly improve clinical outcomes, but in low-risk cases, incidental findings often lead to overdiagnosis and overtreatment, causing harm. Robust systems are critical to promote early identification without overburdening patients or healthcare systems.
View Article and Find Full Text PDFRadiologist in the Loop: Advancing Artificial Intelligence in Radiology Through Active Learning.
AJR Am J Roentgenol
September 2025
Department of Radiology, Kingston Health Sciences Centre, Queen's University, Kingston, ON, Canada.
Development of a Large-Scale Dataset of Chest Computed Tomography Reports in Japanese and a High-Performance Finding Classification Model: Dataset Development and Validation Study.
JMIR Med Inform
August 2025
Division of Radiology and Biomedical Engineering, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan, 81 3-3815-5411.
Background: Recent advances in large language models have highlighted the need for high-quality multilingual medical datasets. Although Japan is a global leader in computed tomography (CT) scanner deployment and use, the absence of large-scale Japanese radiology datasets has hindered the development of specialized language models for medical imaging analysis. Despite the emergence of multilingual models and language-specific adaptations, the development of Japanese-specific medical language models has been constrained by a lack of comprehensive datasets, particularly in radiology.
View Article and Find Full Text PDFGM-ABS: Promptable Generalist Model Drives Active Barely Supervised Training in Specialist Model for 3D Medical Image Segmentation.
IEEE Trans Med Imaging
August 2025
Semi-supervised learning (SSL) has greatly advanced 3D medical image segmentation by alleviating the need for intensive labeling by radiologists. While previous efforts focused on model-centric advancements, the emergence of foundational generalist models like the Segment Anything Model (SAM) is expected to reshape the SSL landscape. Although these generalists usually show performance gaps relative to previous specialists in medical imaging, they possess impressive zero-shot segmentation abilities with manual prompts.
View Article and Find Full Text PDFBeyond the AP View: The Diagnostic Value of Lateral Duodenal and Colonic Assessment in Pediatric Malrotation.
Eur J Pediatr Surg
July 2025
Department of Surgery, Indiana University School of Medicine, Riley Hospital for Children at Indiana University Health, Indianapolis, Indiana, United States.
This study aimed to assess if the position of the duodenal-jejunal junction in the anteroposterior view can reliably diagnose malrotation and if atypical position of the duodenal-jejunal junction (medial to the left pedicle to midline) is associated with a low risk of narrow mesenteric root.Children diagnosed with intestinal rotational abnormalities (2007-2023) through upper gastrointestinal fluoroscopy (UGI) studies who underwent surgery were reviewed independently by two pediatric radiologists. Key observations included the duodenal-jejunal junction location in the anteroposterior view, duodenal position in the lateral view, jejunal loop position, and colon anatomy.
View Article and Find Full Text PDF