Meeting Banner
Abstract #3238

The Use of Quantitative Metrics and Machine Learning to Predict Radiologist Interpretations of Image Quality and Artifacts

Lucas McCullum1, John Wood2, Maria Gule-Monroe3, Ho-Ling Anthony Liu4, Melissa Chen3, Komal Shah3, Noah Nathan Chasen3, Vinodh Kumar3, Ping Hou4, Jason Stafford4, Caroline Chung5, Moiz Ahmad4, Christopher Walker4, and Joshua Yung4
1Medical Physics, MD Anderson Cancer Center, Houston, TX, United States, 2Enterprise Development and Integration, MD Anderson Cancer Center, Houston, TX, United States, 3Neuroradiology, MD Anderson Cancer Center, Houston, TX, United States, 4Imaging Physics, MD Anderson Cancer Center, Houston, TX, United States, 5Data Governance & Provenance, MD Anderson Cancer Center, Houston, TX, United States

Synopsis

Keywords: Machine Learning/Artificial Intelligence, Data Analysis, Image QualityA dataset of 3D-GRE and 3D-TSE brain 3T post contrast T1-weighted images as part of a quality improvement project were collected and shown to five neuro-radiologists who evaluated each sequence for image quality and artifacts. The same scans were processed using the MRQy tool for objective, quantitative image quality metrics. Using the combined radiologist and quantitative metrics dataset, a decision tree classifier with a bagging ensemble approach was trained to predict radiologist assessment using the quantitative metrics. The resulting AUCs for each classification task were above 0.7 for all combinations of sufficiently represented classes and qualitative image metrics.

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.

Click here for more information on becoming a member.

Keywords