Finnish researchers developed a deep learning algorithm that accurately detects retropharyngeal edema on MRI neck scans.
Key Details
- 1Deep learning model developed at Tampere University, Finland, for neck MRI interpretation.
- 2Study included 479 patients with acute neck infections; 51% RPE-positive, 49% RPE-negative.
- 3Used axial T2-weighted water-only Dixon MRI sequences.
- 4Algorithm combined CNN-based slice categorization with patient-level classification.
- 5Model achieved high AUCs: 0.941 (slice-level) and 0.948 (patient-level), compared to radiologists.
Why It Matters
Accurate and rapid identification of retropharyngeal edema can improve management of acute neck infections and may enhance triage and treatment decisions. The high performance of this AI model highlights its potential as a clinical decision support tool in radiology workflows.
Source
AuntMinnie
Related News
•AuntMinnie
Paul Chang Discusses Foundation Models and Agentic AI at RSNA 2025
Dr. Paul Chang shares his insights on the role of foundation models and agentic AI in radiology at RSNA 2025.
•AuntMinnie
Toronto Study: LLMs Must Cite Sources for Radiology Decision Support
University of Toronto researchers found that large language models (LLMs) such as DeepSeek V3 and GPT-4o offer promising support for radiology decision-making in pancreatic cancer when their recommendations cite guideline sources.
•AuntMinnie
AI Model Using Mammograms Enhances Five-Year Breast Cancer Risk Assessment
A new image-only AI model more accurately predicts five-year breast cancer risk than breast density alone, according to multinational research presented at RSNA 2025.