An explainable deep learning AI model using gadoxetic acid-enhanced MRI improves sensitivity in diagnosing hepatocellular carcinoma (HCC).
Key Details
- 1The AI model was trained on 1,023 liver lesions from 839 patients using multi-phase MRI.
- 2It classified lesions as HCC or non-HCC and provided visual explanations (LI-RADS feature identification).
- 3On a test set, the model achieved AUC 0.97 for HCC diagnosis.
- 4Compared to LI-RADS 5, AI had higher sensitivity (91.6% vs. 74.8%) with similar specificity (90.7% vs. 96%).
- 5Radiologists assisted by the AI showed improved sensitivity (up to 89%) with no loss in specificity.
- 6Explainability is highlighted, aligning with regulatory emphasis on interpretable AI.
Why It Matters
This study demonstrates that explainable AI models can significantly increase diagnostic sensitivity for HCC on MRI, supporting radiologists without sacrificing specificity. The focus on explainability is crucial for regulatory compliance and clinical trust in AI tools for radiology.
Source
AuntMinnie
Related News
•Radiology Business
Experts Urge Development of Generalist Radiology AI to Cut Costs and Improve Care
Leading scientists advocate for broader, generalist radiology AI models to overcome limitations of narrow, single-task solutions.
•AuntMinnie
GE HealthCare Acquires icometrix to Bolster MRI Neurology AI
GE HealthCare is acquiring icometrix to expand its AI-powered MRI neuroimaging capabilities and integrate advanced analytics into its global product ecosystem.
•AuntMinnie
General LLMs Show Promise in Detecting Critical Findings in Radiology Reports
Stanford and Mayo Clinic Arizona researchers demonstrated that LLMs like GPT-4 can categorize critical findings in radiology reports using few-shot prompting.