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

Abstract

Our objective was to evaluate the diagnostic performance of a convolutional neural network (CNN) trained on multiple MR imaging features of the lumbar spine, to detect a variety of different degenerative changes of the lumbar spine. One hundred and forty-six consecutive patients underwent routine clinical MRI of the lumbar spine including T2-weighted imaging and were retrospectively analyzed using a CNN 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. The assessment of a radiologist served as the diagnostic reference standard. We assessed the CNN’s diagnostic accuracy and consistency using confusion matrices and McNemar’s test. In our data, 77 disc herniations (thereof 46 further classified as extrusions), 133 disc bulgings, 35 spinal canal stenoses, 59 nerve root compressions, and 20 segments with spondylolisthesis were present in a total of 888 lumbar spine segments. The CNN 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%; 95% CI: 0.84, 0.89), extrusions (86%; 95% CI: 0.84, 0.89), bulgings (76%; 95% CI: 0.73, 0.78), spinal canal stenoses (98%; 95% CI: 0.97, 0.99), nerve root compressions (91%; 95% CI: 0.89, 0.92), and spondylolisthesis (87.61%; 95% CI: 85.26, 89.21), respectively. Our data suggest that automatic diagnosis of multiple different degenerative changes of the lumbar spine is feasible using a single comprehensive CNN. The CNN 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.

Load Measurement of the Cervical Vertebra C7 and the Head of Passengers of a Car While Driving across Uneven Terrain

“…The results of our work confirmed previously performed studies that dealt with the dynamic load of people in vehicles [ 5 , 10 , 19 , 25 , 26 ]. This issue needs to be further addressed.…”

“…As mentioned above, the dynamic loads and response of the vehicle crew are often an issue. This article develops the results of a pilot measurement carried out in 2019 [ 25 ]. An earlier pilot measurement proved the suitability of the set measuring chain as well as the suitability of the used acceleration sensors for measuring the dynamic load of the vehicle crew.…”

Editorial on Special Issue “Spine Imaging: Novel Image Acquisition Techniques and Analysis Tools”

“…According to the results of their study, the differences in BMD between subjects without and those with single or ≥2 sites of lumbar disc herniation were not statistically significant, and no associations between BMD and lumbar disc herniation were observed in either men or women [ 25 ]. The degenerative spine was also in the focus of a study by Lehnen et al, who aimed to detect a variety of different degenerative changes of the lumbar spine (including presence of disc herniation, disc bulging, spinal canal stenosis, nerve root compression, and spondylolisthesis) by means of a convolutional neural network (CNN) trained on multiple MRI-based features [ 26 ]. Including T2-weighted imaging with labeling of vertebrae and IVD segments in 146 patients, the CNN-based algorithm’s diagnostic accuracy and consistency in relation to visual radiological image reading was evaluated, revealing perfect accuracy for IVD detection and labeling (100%) and moderate to high diagnostic accuracy for the detection of disc herniations (87%) or bulgings (76%) [ 26 ].…”

“…The degenerative spine was also in the focus of a study by Lehnen et al, who aimed to detect a variety of different degenerative changes of the lumbar spine (including presence of disc herniation, disc bulging, spinal canal stenosis, nerve root compression, and spondylolisthesis) by means of a convolutional neural network (CNN) trained on multiple MRI-based features [ 26 ]. Including T2-weighted imaging with labeling of vertebrae and IVD segments in 146 patients, the CNN-based algorithm’s diagnostic accuracy and consistency in relation to visual radiological image reading was evaluated, revealing perfect accuracy for IVD detection and labeling (100%) and moderate to high diagnostic accuracy for the detection of disc herniations (87%) or bulgings (76%) [ 26 ]. Furthermore, its accuracy for the detection of spinal canal stenosis (98%), nerve root compression (91%), and spondylolisthesis (87.6%) was also high [ 26 ].…”

“…Including T2-weighted imaging with labeling of vertebrae and IVD segments in 146 patients, the CNN-based algorithm’s diagnostic accuracy and consistency in relation to visual radiological image reading was evaluated, revealing perfect accuracy for IVD detection and labeling (100%) and moderate to high diagnostic accuracy for the detection of disc herniations (87%) or bulgings (76%) [ 26 ]. Furthermore, its accuracy for the detection of spinal canal stenosis (98%), nerve root compression (91%), and spondylolisthesis (87.6%) was also high [ 26 ]. These results suggest that evaluation of the degenerative spine with support by a CNN-based algorithm may automate image assessments, thus potentially limiting time expenses and efforts by radiologists.…”