MRI spine data inform radiomic models for osteoporosis

By AuntMinnie.com staff writers

May 7, 2020 -- Radiomic models developed using lumbar spine MRI data can be used to detect osteoporosis, according to a study published May 6 in Academic Radiology.

Signal intensity in MRI of the lumbar spine corresponds to bone mineral density, making the modality a useful tool for developing ways to diagnose bone disease, wrote a team led by Dr. Li He of the First Hospital of Hebei Medical University in Shijiazhuang, China. He and colleagues conducted a study that included 109 patients who underwent both dual-energy x-ray absorptiometry (DEXA) and MRI of the lumbar spine.

Of the total patient cohort, 38 had normal results on DEXA, 32 had osteopenia, and 39 had osteoporosis. The researchers extracted 792 radiomic features from MRI lumbar segmentation images and developed a radiomic classification model that consisted of normal spine versus osteopenia, normal versus osteoporosis, and osteopenia versus osteoporosis. The model was based on T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and T1WI plus T2WI MRI data; the team compared the model's performance with DEXA results using the receiver operating characteristic (ROC) curve measure.

When DEXA results were compared with the radiomic models based on lumbar MRI data, the researchers found the following ROC measures:

  • Normal versus osteopenia: ROC of 0.772 (T1WI), 0.772 (T1WI), and 0.810 (T1WI plus T2WI)
  • Normal versus osteoporosis: ROC of 0.724 (T1WI), 0.682 (T1WI), and 0.797 (T1WI plus T2WI)
  • Osteopenia versus osteoporosis: ROC of 0.730 (T1WI), 0.734 (T1WI), and 0.769 (T1WI plus T2WI)

"Radiomic models established based on lumbar spine MRI can be used to detect osteoporosis," the researchers concluded.


Copyright © 2020 AuntMinnie.com
 

To read this and get access to all of the exclusive content on AuntMinnie.com create a free account or sign-in now.

Member Sign In:
MemberID or Email Address:  
Do you have a AuntMinnie.com password?
No, I want a free membership.
Yes, I have a password:  
Forgot your password?
Sign in using your social networking account:
Sign in using your social networking
account: