Keywords: Lung, Lung, AI, UTE, scoring
Motivation: Conventional grid-based lung MRI scoring for quantifying structural lung damage is time-consuming and lacks pixel-level accuracy, which impacts workflow efficiency and subsequent clinical analysis.
Goal(s): Our goal was to reduce scoring time and improve scoring accuracy.
Approach: We developed a new Artificial intelligence-assisted Pixel-level Lung MRI scoring system, leveraging 1) deep learning to automate time-consuming lung segmentation and 2) pixel-level annotation tools to improve accuracy.
Results: Our scoring system successfully reduced scoring time from 17.5 to 8.2 minutes per participant, and our scoring was statistically more accurate than conventional grid-level scoring.
Impact: AI-assisted pixel-level scoring significantly improved the efficiency and accuracy of lung MRI quantification, which has the potential to streamline the clinical workflow of lung MRI analysis for cystic fibrosis patients and be extended to other lung diseases (e.g., bronchopulmonary dysplasia).
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords