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
Radiology Receives Declining Share of Industry Research Funding
Radiologists received only 1.1% of industry-funded research payments in 2024, with a continuing downward trend.
•AuntMinnie
GPT-4o AI Matches Radiologists in Follow-Up Imaging Recommendations
GPT-4o matched the performance of experienced radiologists and surpassed residents in recommending follow-up imaging from routine radiology reports.
•Cardiovascular Business
AI Leverages Head CTs for Automated Heart Risk Assessments
AI models can turn routine head CT scans into automated cardiovascular risk assessments, expanding the utility of radiology studies.