Computer-aided diagnosis of lumbar disc pathology from clinical lower spine MRI

Alomari, Raja’ S.; Corso, Jason J.; Chaudhary, Vipin; Dhillon, Gurmeet

doi:10.1007/s11548-009-0396-9

Cited by 50 publications

(21 citation statements)

References 16 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Note the summation is over a very large set of possible assignments . We model it as a Gibbs distribution (4) (5) (6) where is a pixel on the lattice , is the intensity level of the pixel , , are tunable parameters, the notation denotes the set of neighboring elements on the disc chain. , , and are the partition functions that make the normalizing constant for the Gibbs distribution for each model, respectively.…”

Section: B Two-level Modelmentioning

confidence: 99%

Labeling of Lumbar Discs Using Both Pixel- and Object-Level Features With a Two-Level Probabilistic Model

Alomari

Corso

Chaudhary

2011

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Abstract-Backbone anatomical structure detection and labeling is a necessary step for various analysis tasks of the vertebral column. Appearance, shape and geometry measurements are necessary for abnormality detection locally at each disc and vertebrae (such as herniation) as well as globally for the whole spine (such as spinal scoliosis). We propose a two-level probabilistic model for the localization of discs from clinical magnetic resonance imaging (MRI) data that captures both pixel-and object-level features. Using a Gibbs distribution, we model appearance and spatial information at the pixel level, and at the object level, we model the spatial distribution of the discs and the relative distances between them. We use generalized expectation-maximization for optimization, which achieves efficient convergence of disc labels. Our two-level model allows the assumption of conditional independence at the pixel-level to enhance efficiency while maintaining robustness. We use a dataset that contains 105 MRI clinical normal and abnormal cases for the lumbar area. We thoroughly test our model and achieve encouraging results on normal and abnormal cases.

show abstract

Section: B Two-level Modelmentioning

confidence: 99%

Labeling of Lumbar Discs Using Both Pixel- and Object-Level Features With a Two-Level Probabilistic Model

Alomari

Corso

Chaudhary

2011

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…7,8 The purpose of the segmentation is to provide robust and automated tools for further diagnosis tasks such as our previous work. [9][10][11] Probabilistic graphical models have been used for spine localization and labeling such as Schmidt et al 7 whose work focuses on the whole spine and Alomari et al 8 focusing only on lumbar area. Their models incorporated both appearance and space information of the discs to localize and label the discs from MRI.…”

Section: Previous Workmentioning

confidence: 99%

Automatic lumbar vertebra segmentation from clinical CT for wedge compression fracture diagnosis

et al. 2011

Self Cite

View full text Add to dashboard Cite

Lumbar vertebral fractures vary greatly in types and causes and usually result from severe trauma or pathological conditions such as osteoporosis. Lumbar wedge compression fractures are amongst the most common ones where the vertebra is severely compressed forming a wedge shape and causing pain and pressure on the nerve roots and the spine. Since vertebral segmentation is the first step in any automated diagnosis task, we present a fully automated method for robustly localizing and segmenting the vertebrae for preparation of vertebral fracture diagnosis. Our segmentation method consists of five main steps towards the CAD(Computer-Aided Diagnosis) system: 1) Localization of the intervertebral discs. 2) Localization of the vertebral skeleton. 3) Segmentation of the individual vertebra. 4) Detection of the vertebrae center line and 5) Detection of the vertebrae major boundary points. Our segmentation results are promising with an average error of 1.5mm (modified Hausdorff distance metric) on 50 clinical CT cases i.e. a total of 250 lumbar vertebrae. We also present promising preliminary results for automatic wedge compression fracture diagnosis on 15 cases, 7 of which have one or more vertebral compression fracture, and obtain an accuracy of 97.33%.

show abstract

“…The AUC of 0.92 for combination marker for diagnosis was comparable with the accuracy of existing CAD systems. 17 Moreover, we used a large number of lumbar discs for validation. We plan to extend the diagnosis study on other spine regions in the future for wider area diagnosis and prognosis.…”

Section: New and Discussionmentioning

confidence: 99%

Prognosis of intervertebral disc loss from diagnosis of degenerative disc disease

Li¹,

Lin²,

Tay³

et al. 2015

SPIE Proceedings

View full text Add to dashboard Cite

Degenerative Disc Diseas (DDD) is one of the most common causes of low back pain, and is a major factor in limiting the quality of life of an individual usually as they enter older stages of life, the disc degeneration reduces the shock absorption available which in turn causes pain. Disc loss is one of the central processes in the pathogenesis of DDD. In this study, we investigated whether the image texture features quantified from magnetic resonance imaging (MRI) could be appropriate markers for diagnosis of DDD and prognosis of inter-vertebral disc loss. The main objective is to use simple image based biomarkers to perform prognosis of spinal diseases using non-invasive procedures. Our results from 65 subjects proved the higher success rates of the combination marker compared to the individual markers and in the future, we will extend the study to other spine regions to allow prognosis and diagnosis of DDD for a wider region.

show abstract

Computer-aided diagnosis of lumbar disc pathology from clinical lower spine MRI

Cited by 50 publications

References 16 publications

Labeling of Lumbar Discs Using Both Pixel- and Object-Level Features With a Two-Level Probabilistic Model

Labeling of Lumbar Discs Using Both Pixel- and Object-Level Features With a Two-Level Probabilistic Model

Automatic lumbar vertebra segmentation from clinical CT for wedge compression fracture diagnosis

Prognosis of intervertebral disc loss from diagnosis of degenerative disc disease

Contact Info

Product

Resources

About