University Hospital Bonn in Germany and German Center for Neurodegenerative Disease have evaluated the diagnostic performance of CoLumbo AI software

May/20/2021

Smart Soft Ltd, a CoLumbo automated MRI lumbar spine assistant system developer, is pleased to announce that a feasibility study was published in MDPI peer-reviewed journal (Basel, Switzerland) by researchers from University Hospital in Bonn, Germany and German Center for Neurodegenerative Diseases.

The study’s objective was to evaluate the diagnostic performance of a convolutional neural network (CNN) – CoLumbo trained on multiple MR imaging features of the lumbar spine to detect a variety of different degenerative changes.

One hundred and forty-six patients underwent routine clinical MRI of the lumbar spine and were retrospectively analyzed by CoLumbo for detection and labeling of vertebrae, disc segments, as well as presence of disc herniation, disc bulging, spinal canal stenosis, nerve root compression, and spondylolisthesis.

CoLumbo’s diagnostic accuracy and consistency were assessed using confusion matrices and McNemar’s test.

CoLumbo yielded a perfect accuracy score for intervertebral disc detection and labeling (100%), and moderate to high diagnostic accuracy for the detection of disc herniations (87%), extrusions (86%), bulgings (76%), spinal canal stenoses (98%), nerve root compressions (91%), and spondylolisthesis (87.61%).

The data from the researchers suggest that automatic diagnosis of multiple different degenerative changes of the lumbar spine is feasible using a single comprehensive CNN – CoLumbo. CoLumbo provides high diagnostic accuracy for intervertebral disc labeling and detection of clinically relevant degenerative changes such as spinal canal stenosis and disc extrusion of the lumbar spine.

For more information visit: https://www.mdpi.com/2075-4418/11/5/902

C01026/20.05.2021