Segmentation of Lumbar Spine MRI Images for Stenosis Detection Using Patch-Based Pixel Classification Neural Network

Abnormalities and defects that can cause lumbar spinal stenosis often occur in the Intervertebral Disc (IVD) of the patient’s lumbar spine. Their automatic detection and classification require an application of an image analysis algorithm on suitable images, such as mid-sagittal images or traverse mid-height intervertebral disc slices, as inputs. Hence the process of selecting and separating these images from other medical images in the patient’s set of scans is necessary. However, the technological progress in making this process automated is still lagging behind other areas in medical image classification research. In this paper, we report the result of our investigation on the suitability and performance of different approaches of machine learning to automatically select the best traverse plane that cuts closest to the half-height of an IVD from a database of lumbar spine MRI images. This study considers images features extracted using eleven different pre-trained Deep Convolution Neural Network (DCNN) models. We investigate the effectiveness of three dimensionality-reduction techniques and three feature-selection techniques on the classification performance. We also investigate the performance of five different Machine Learning (ML) algorithms and three Fully Connected (FC) neural network learning optimizers which are used to train an image classifier with hyperparameter optimization using a wide range of hyperparameter options and values. The different combinations of methods are tested on a publicly available lumbar spine MRI dataset consisting of MRI studies of 515 patients with symptomatic back pain. Our experiment shows that applying the Support Vector Machine algorithm with a short Gaussian kernel on full-length image features extracted using a pre-trained DenseNet201 model is the best approach to use. This approach gives the minimum per-class classification performance of around 0.88 when measured using the precision and recall metrics. The median performance measured using the precision metric ranges from 0.95 to 0.99 whereas that using the recall metric ranges from 0.93 to 1.0. When only considering the L3/L4, L4/L5, and L5/S1 classes, the minimum F1-Scores range between 0.93 to 0.95, whereas the median F1-Scores range between 0.97 to 0.99.

Download Full-text

Diffusion Tensor Imaging with Quantitative Evaluation of Sciatic Nerve within the Pelvis in Patients with Noncontributory Lumbar Spine MRI in Radiculopathy

10.1055/s-0039-1692576 ◽

2019 ◽

Author(s):

M. Catania ◽

G. Foti ◽

E. Demozzi ◽

L. Romano ◽

S. Caia ◽

...

Keyword(s):

Diffusion Tensor Imaging ◽

Lumbar Spine ◽

Sciatic Nerve ◽

Quantitative Evaluation ◽

Diffusion Tensor ◽

Spine Mri

Download Full-text

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

Diagnostics ◽

10.3390/diagnostics11050902 ◽

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.

Download Full-text

Review of general practitioner direct access referrals for lumbar spine MRI

Clinical Radiology ◽

10.1016/j.crad.2013.05.010 ◽

2013 ◽

Vol 68 ◽

pp. S5

Author(s):

Christopher Watura ◽

Steven James

Keyword(s):

General Practitioner ◽

Lumbar Spine ◽

Direct Access ◽

Spine Mri

Download Full-text

The Effect of Computer-Assisted Reporting on Interreader Variability of Lumbar Spine MRI Degenerative Findings: Five Readers With 30 Disc Levels

Journal of the American College of Radiology ◽

10.1016/j.jacr.2017.12.020 ◽

2018 ◽

Vol 15 (11) ◽

pp. 1613-1619 ◽

Cited By ~ 2

Author(s):

Benjamin Wang ◽

Daniel I. Rosenthal ◽

Chun Xu ◽

Pari V. Pandharipande ◽

H. Benjamin Harvey ◽

...

Keyword(s):

Lumbar Spine ◽

Computer Assisted ◽

Spine Mri

Download Full-text

Development of Ground Truth Data for Automatic Lumbar Spine MRI Image Segmentation

2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS) ◽

10.1109/hpcc/smartcity/dss.2018.00239 ◽

2018 ◽

Cited By ~ 1

Author(s):

Friska Natalia ◽

Hira Meidia ◽

Nunik Afriliana ◽

Ala S. Al-Kafri ◽

Sud Sudirman ◽

...

Keyword(s):

Image Segmentation ◽

Lumbar Spine ◽

Ground Truth ◽

Ground Truth Data ◽

Spine Mri ◽

Mri Image

Download Full-text

Osteopetrosis - A Case Series Exploring Complications and Multidisciplinary Management

Journal of the Endocrine Society ◽

10.1210/jendso/bvab048.425 ◽

2021 ◽

Vol 5 (Supplement_1) ◽

pp. A209-A209

Author(s):

Catherine Stewart ◽

Paul Benjamin Loughrey ◽

John R Lindsay

Keyword(s):

Back Pain ◽

Lumbar Spine ◽

Medical History ◽

Scaphoid Fracture ◽

Past Medical History ◽

Dxa Scan ◽

X Ray ◽

Management Of Complications ◽

History Of ◽

Spine Mri

Abstract Background: Osteopetrosis is a group of rare inherited skeletal dysplasias, with each variant sharing the hallmark of increased bone mineral density (BMD). Abnormal osteoclast activity produces overly dense bone predisposing to fracture and skeletal deformities. Whilst no cure for these disorders exists, endocrinologists play an important role in surveillance and management of complications. Clinical Cases: A 43-year-old female had findings suggestive of increased BMD on radiographic imaging performed to investigate shoulder and back pain. X-ray of lumbar spine demonstrated a ‘rugger jersey’ spine appearance, while shoulder X-ray revealed mixed lucency and sclerosis of the humeral head. DXA scan showed T-scores of +11 at the hip and +12.5 at the lumbar spine. MRI of head displayed bilateral narrowing and elongation of the internal acoustic meatus and narrowing of the orbital foramina. Genetic assessment confirmed autosomal dominant osteopetrosis with a CLCN7 variant. Oral colecalciferol supplementation was commenced and multi-disciplinary management instigated with referral to ophthalmology and ENT teams. A 25-year-old male presented with a seven-year history of low back pain and prominent bony swelling around the tibial tuberosities and nape of neck. Past medical history included repeated left scaphoid fracture in 2008 and 2018. Recovery from his scaphoid fracture was complicated by non-union requiring bone grafting with open reduction and fixation. Plain X-rays of the spine again demonstrated ‘rugger jersey’ spine. DXA scan was notable for elevated T scores; +2.9 at hip and +5.8 lumbar spine. MRI spine showed vertebral endplate cortical thickening and sclerosis at multiple levels. The patient declined genetic testing and is under clinical review. A 62-year-old male was referred to the bone metabolism service following a DXA scan showing T scores of +11. 7 at the hip and +13 at the lumbar spine. His primary complaint was of neck pain and on MRI there was multi-level nerve root impingement secondary to facet joint hypertrophy. Past medical history was significant for a long history of widespread joint pains; previous X-ray reports described generalized bony sclerosis up to 11 years previously. Clinical and radiological monitoring continues. Conclusion: Individuals with osteopetrosis require a multidisciplinary approach to management. There is no curative treatment and mainstay of therapy is supportive with active surveillance for complications.

Download Full-text