Meeting Banner
Abstract #1420

A machine learning method for tissue characterisation in the human thigh

Terence Jones1,2, Sarah Wayte3, Abhir Bhalerao4, Nicola Gullick5, and Charles Edward Hutchinson1,2

1Medical School, University of Warwick, Coventry, United Kingdom, 2Radiology, University Hospitals Coventry & Warwickshire NHS Trust, Coventry, United Kingdom, 3Medical Physics, University Hospitals Coventry & Warwickshire NHS Trust, Coventry, United Kingdom, 4Computer Science, University of Warwick, Coventry, United Kingdom, 5Department of Rheumatology, University Hospitals Coventry & Warwickshire NHS Trust, Coventry, United Kingdom

Inflammatory idiopathic myositis is a debilitating inflammatory muscle condition. Diagnosis relies on a battery of tests, but monitoring of disease severity can be challenging. We present a novel machine learning approach to classifying tissues using multi-parametric analysis of routine MRI sequences. A logistic regression model was trained to predict tissue type based on T1 and STIR signal intensity and 10-fold cross-validated. The system attained 93.8% sensitivity and 96.9% specificity overall (ROC area 0.991). Testing of this model showed a low level of ostensible muscle inflammation in 9/11 asymptomatic controls – likely due to misclassification of vessels.

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