Adding AI to MRI-based classification systems improves return-to-play predictions for professional athletes with muscle injuries.
Key Details
- 1Research presented at RSNA explores AI augmentation of MRI for classifying sports-related thigh muscle injuries.
- 2Study involved 40 professional athletes with thigh muscle injuries, all receiving 1.5-T MRI within 72 hours of injury.
- 3Traditional systems assessed: BAMIC, MLG-R, and their integrated use.
- 4Without AI, integrated BAMIC + MLG-R showed AUC 0.984, sensitivity 96.4%, and specificity 94.4%.
- 5With AI, integrated model performance improved: AUC 0.993, sensitivity 98.2%, specificity 96.7%.
- 6Researchers recommend further, larger validation studies and refinement of deep-learning models for clinical use.
Why It Matters
This study demonstrates that AI can enhance MRI-based classification systems, potentially leading to more accurate and evidence-based decisions on athlete rehabilitation and return to play, reducing reinjury risks and improving outcomes. Broader, validated models could standardize and streamline sports injury management in radiology.
Source
AuntMinnie
Related News
•AuntMinnie
Study: Computer Vision Models Best LLMs in Chest CT Breast Abnormality Detection
Computer vision models (CVMs) surpass large language models (LLMs) in accurately labeling incidental breast abnormalities on chest CT scans.
•Radiology Business
Private Equity Backs AIRS Medical to Expand MRI AI Globally
TA Associates is investing in AIRS Medical to accelerate its global expansion of AI-powered MRI efficiency solutions.
•AuntMinnie
Deep Learning Models Rival Radiologists for Pancreatic Cancer Detection on CT
Deep-learning models achieved comparable or superior accuracy to experienced radiologists in detecting pancreatic cancer on CT scans, especially for small tumors.