Detection of Degenerative Changes on MR Images of the Lumbar Spine with a Convolutional Neural Network: A Feasibility Study

There is a growing interest in machine-learning algorithms supporting radiologists in their daily work. In the current study, we found that support for the indication of various lumbar degenerative changes is feasible with moderate to high accuracy using a single comprehensive CNN. Additionally, the high NPVs make this CNN a promising approach to rule out vertebral measurements in clinical practice.

Clinical Assessment of CoLumbo Deep Learning System for Central Canal Stenosis Diagnostics

This prospective study showed that the assessment of the radiologists supported by deep learning system for central stenosis classification results in high kappa agreement. The introduction into practice of such AI-based tools would precisely predict the presence of stenosis and thus decrease the observer variability in assessing lumbar spinal stenosis severity based on MRI and its relation to cross sectional spinal canal area. This would result in timely and effective surgical treatment and improved quality of life for these patients.

An artificial intelligence boost to MRI lumbar spine reporting

This prospective study evaluated the integration of the CoLumbo AI software into routine radiology workflow at a high-volume tertiary hospital. The study demonstrated that using CoLumbo significantly reduced the average MRI reporting time—from 22.99 minutes to 8.90 minutes, representing a mean time saving of over 14 minutes per case (p < 0.001). These efficiency gains were achieved without compromising diagnostic concordance between residents using the AI tool and experienced radiologists.

Preliminary data on artificial intelligence tool in magnetic resonance imaging assessment of degenerative pathologies of lumbar spine

This preliminary study evaluated the use of an AI-based software tool (CoLumbo) to support radiologists in the analysis of lumbar spine MRI scans. The findings demonstrated strong alignment between the AI-generated outputs and expert radiologist assessments across multiple spinal levels. The study emphasizes the tool’s potential to enhance consistency and support radiological workflows, particularly in standardizing spinal measurements. The authors concluded that, “This valuable tool has the potential to streamline the daily tasks conducted by radiologists, and we believe that the integration of AI will complement the work carried out in the field of radiology.”