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

Diagnostics ◽  
2021 ◽  
Vol 11 (5) ◽  
pp. 902
Author(s):  
Nils Christian Lehnen ◽  
Robert Haase ◽  
Jennifer Faber ◽  
Theodor Rüber ◽  
Hartmut Vatter ◽  
...  
Keyword(s):  
Neural Network ◽  
Lumbar Spine ◽  
Diagnostic Accuracy ◽  
Nerve Root ◽  
Spinal Canal ◽  
Spinal Canal Stenosis ◽  
Degenerative Changes ◽  
High Diagnostic Accuracy ◽  
Canal Stenosis ◽  
Disc Herniations

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.

Diagnostic Advancement of Axial Loaded Lumbar Spine MRI in Patients With Clinically Suspected Central Spinal Canal Stenosis

Spine ◽  
2013 ◽  
Vol 38 (21) ◽  
pp. E1342-E1347 ◽  
Author(s):  
Yeo Koon Kim ◽  
Joon Woo Lee ◽  
Hyun-Jib Kim ◽  
Jin S. Yeom ◽  
Heung Sik Kang
Keyword(s):  
Lumbar Spine ◽  
Spinal Canal ◽  
Spinal Canal Stenosis ◽  
Canal Stenosis ◽  
Spine Mri

Changes in the Microhemodynamics of Nerve Root Retraction in Patients With Lumbar Spinal Canal Stenosis

Spine ◽  
2002 ◽  
Vol 27 (24) ◽  
pp. 2844-2849 ◽  
Author(s):  
Akira Dezawa ◽  
Kazutoshi Unno ◽  
Tomojiro Yamane ◽  
Hiroshi Miki
Keyword(s):  
Nerve Root ◽  
Spinal Canal ◽  
Spinal Canal Stenosis ◽  
Lumbar Spinal Canal Stenosis ◽  
Canal Stenosis ◽  
Lumbar Spinal Canal ◽  
Lumbar Spinal

scholarly journals Selectively Decompressive Nerve Root Surgery for Degenerative Lateral Lumbar Spinal Canal Stenosis in Elderly Patients

2014 ◽  
Vol 4 (1_suppl) ◽  
pp. s-0034-1376696-s-0034-1376696
Author(s):  
H. Zhou ◽  
D. Cao ◽  
S. Feng ◽  
G. Ning ◽  
C. Zhang ◽  
...  
Keyword(s):  
Elderly Patients ◽  
Nerve Root ◽  
Spinal Canal ◽  
Spinal Canal Stenosis ◽  
Lumbar Spinal Canal Stenosis ◽  
Canal Stenosis ◽  
Lumbar Spinal Canal ◽  
Lumbar Spinal

Incidental durotomy during lumbar spine surgery: risk factors and anatomic locations

2013 ◽  
Vol 18 (2) ◽  
pp. 165-169 ◽  
Author(s):  
Yoshimasa Takahashi ◽  
Tetsuro Sato ◽  
Hironori Hyodo ◽  
Tomomaro Kawamata ◽  
Eiji Takahashi ◽  
...  
Keyword(s):  
Lumbar Spine ◽  
Spine Surgery ◽  
Spinal Canal ◽  
Degenerative Spondylolisthesis ◽  
Spinal Canal Stenosis ◽  
Lumbar Spine Surgery ◽  
Dural Tear ◽  
Canal Stenosis ◽  
Lumbar Spinal ◽  
Incidental Durotomy

Object Incidental durotomy (dural tear) is a common complication of lumbar spine surgery. The purpose of this study was to clarify the anatomical location of and the specific causative factors for incidental durotomy during primary lumbar spine surgery. Methods The authors retrospectively reviewed 1014 consecutive cases involving patients (412 women and 602 men; mean age 57 years; age range 11–97 years) who underwent a surgical procedure for treatment of degenerative lumbar spinal disease at their institution between 2002 and 2008. In total, 1261 disc levels were treated surgically. Disease at the treated levels included 544 disc herniations, 453 instances of spinal canal stenosis without spondylolisthesis, 188 instances of lumbar spinal canal stenosis with spondylolisthesis (degenerative spondylolisthesis), 49 instances of combined stenosis (stenosis with disc herniation), and 22 juxtafacet cysts. In 5 of the treated levels, the condition was classified as “other” disease. Treatment included fenestration with discectomy in 547 levels, fenestration alone in 626, fenestration with resection of juxtafacet cysts in 22, unilateral recapping laminoplasty in 20, posterolateral spinal fusion or posterior lumbar interbody fusion in 17, microscopic discectomy with tubular retractor in 14, and “other” in 15. Results Unintended durotomy occurred in 4% of cases and in 3.3% of disc levels. The incidence of dural tear was significantly higher in women (5.6%) than in men (3%). The incidence of dural tear was 2% in disc levels with lumbar disc herniation, 1.8% with lumbar spinal canal stenosis without spondylolisthesis, 9% with degenerative spondylolisthesis, and 18.2% with juxtafacet cysts; the incidence was significantly higher in levels with degenerative spondylolisthesis or levels with juxtafacet cysts, than in those with other diseases. Incidental durotomy occurred in 4 critical anatomical zones, namely, the caudal margin of the cranial lamina, cranial margin of the caudal lamina, herniated disc level, and medial aspect of the facet joint adjacent to the insertion of the hypertrophic ligamentum flavum. Conclusions Risk factors for unintended durotomy were female sex, older age, degenerative spondylolisthesis, and juxtafacet cysts. In this study, the authors identified 4 high-risk anatomical zones that spine surgeons should be aware of to avoid dural tears.

Paleopathological Features of the Cervical Spine in the Early Middle Ages: Natural History of Degenerative Diseases

Neurosurgery ◽  
2003 ◽  
Vol 53 (6) ◽  
pp. 1418-1424 ◽  
Author(s):  
Jochen Weber ◽  
Alfred Czarnetzki ◽  
Axel Spring
Keyword(s):  
Cervical Spine ◽  
Middle Ages ◽  
Spinal Canal ◽  
Spinal Canal Stenosis ◽  
Degenerative Disease ◽  
Degenerative Changes ◽  
Facet Joints ◽  
Early Middle Ages ◽  
Canal Stenosis ◽  
Cervical Spinal Canal

Abstract OBJECTIVE Trauma and degenerative joint disease are the most common pathological conditions observed in archaeological skeletal remains. We describe the prevalence of different types of cervical bone diseases observed in the early Middle Ages (6th to 8th centuries AD). METHODS Human skeletons were excavated from Germanic row graves in southwestern Germany. One hundred ninety-six cervical spines thus obtained were examined for bone disease. The degenerative changes were classified into Grades 1 (marginal osteophytes), 2 (uneven joint surfaces), and 3 (osseous ankylosis). Cervical spinal canal stenosis was defined as anteroposterior diameters of <11 mm and intervertebral foraminal stenosis as <3.0 mm in the smallest diameter. RESULTS Of the skeletons, 27.5% demonstrated degenerative changes of the cervical spine. The mean age of the skeletons at the time of death was 33.4 years, compared with 43.7 years for those with degenerative disease. Degenerative changes of the vertebral bodies (usually Grades 1 and 2) were most common in the C5–C6 (12.4%, P < 0.05) and C6–C7 (15.3%, P < 0.05) segments. The medial (6.1%) and lateral (0.6%) atlantoaxial joints were rarely involved in degenerative disease. The facet joints from C3–C4 to C6–C7 demonstrated degenerative changes (usually Grades 1 and 2) in 8.0 to 11.8% of cases. The C2–C3 facet joints were significantly involved in degenerative disease in 19.7% of cases (P < 0.05), one-fourth of which demonstrated osseous ankylosis. We observed cervical spinal canal stenosis in 5 skeletons (2.6%) and osseous intervertebral foraminal stenoses in 12 (6.1%). Isolated cases of other pathological processes, i.e., spondylitis ankylopoietica, occipitalization of the atlas and axis, and an odontoid fracture with pseudoarthrosis, were also recorded. CONCLUSION In the early Middle Ages, the prevalence of degenerative cervical spine disease was the same as that observed today. The C2–C3 facet joints demonstrated high rates of degenerative disease.

scholarly journals Radiation Protection: Do We Need to Scan the Whole Lumbar Spine in Suspected Lumbar Spine Stenosis?

2021 ◽  
Vol 8 (2) ◽  
Author(s):  
Tack D ◽  
◽  
Preziosi M ◽  
Cornil A ◽  
Bohy P ◽  
...  
Keyword(s):  
Lumbar Spine ◽  
Healthy Volunteers ◽  
Spinal Canal ◽  
Substantial Reduction ◽  
Spinal Canal Stenosis ◽  
Canal Stenosis ◽  
Anteroposterior Diameter ◽  
Canal Diameter ◽  
Scan Length ◽  
Rule Out

Objectives: To test two hypotheses that the scan length could be reduced in patients younger than an age threshold below which lumbar stenosis in the two upper lumbar levels never occurs, and that an anteroposterior spinal canal diameter cut-off at the level of the L3 pedicles could rule out a congenital stenosis at the L1 and/or L2 levels. Methods: MR examinations of 55 healthy volunteers and 200 patients with suspected spinal canal stenosis were included. The anteroposterior diameter of the spinal canal was measured at each pedicle and each disk levels by two readers who also subjectively assessed the presence of stenosis. Results: Degenerative spinal canal stenosis never occurs at the upper two lumbar disk levels in patients younger than 55 years. The anteroposterior diameter of the spinal canal diminished from L1 to L3 in both healthy volunteers and patients. An anteroposterior diameter of the spinal canal at the L3 pedicles level ≥11 mm excluded a diameter <10 mm at L1 and/or L2 pedicles levels. Conclusion: A substantial reduction of the radiation dose from CT could be achieved by limiting the scan length from L3 to S1 in patients younger than 55 years provided that the anteroposterior diameter of the spinal canal is >11 mm at the L3 pedicles level.

Sign in / Sign up

Export Citation Format

Share Document