Intervertebral disc classification by its degree of degeneration from T2-weighted magnetic resonance images

Castro-Mateos, Isaac; Hua, Rui; Pozo, José M.; Lazáry, Áron; Frangi, Alejandro F.

doi:10.1007/s00586-016-4654-6

Cited by 38 publications

(25 citation statements)

References 27 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also anticipate that we could also use our method and validate it against other disc degeneration classification systems [20][21][22]. Others have reported results of automated image analysis of lumbar MRI scans, but not on the scale that we have reported here [8]. In addition, these systems require human supervision but in our The second and third columns correspond to the agreement/accuracy measure, which compares the human performance (second column), i.e., the radiologist against our system (third column).…”

Section: Discussionmentioning

confidence: 85%

“…In addition, these systems require human supervision but in our The second and third columns correspond to the agreement/accuracy measure, which compares the human performance (second column), i.e., the radiologist against our system (third column). Similarly, we provide a comparison of another measure, the reliability coefficients for the radiologist and the system in the fourth and fifth columns where we use Lin's concordance correlation coefficient to evaluate reproducibility of ordinal ratings while Cohen's kappa coefficient was used for dichotomous ratings (Maji, 2013 method, there is no need to create individual descriptors for the classifier suited for each radiological score (Lootus et al [9] and Castro-Mateos et al [8]). …”

Section: Discussionmentioning

confidence: 99%

“…To this end, a number of studies have initiated work on automated systems for grading MRIs. To date, only a system for generating Pfirrmann scores has been developed [8], which requires human input.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist

et al. 2017

View full text Add to dashboard Cite

Study design Investigation of the automation of radiological features from magnetic resonance images (MRIs) of the lumbar spine. Objective To automate the process of grading lumbar intervertebral discs and vertebral bodies from MRIs. Summary of background data MR imaging is the most common imaging technique used in investigating low back pain (LBP). Various features of degradation, based on MRIs, are commonly recorded and graded, e.g., Modic change and Pfirrmann grading of intervertebral discs. Consistent scoring and grading is important for developing robust clinical systems and research. Automation facilitates this consistency and reduces the time of radiological analysis considerably and hence the expense.Methods 12,018 intervertebral discs, from 2009 patients, were graded by a radiologist and were then used to train: (1) a system to detect and label vertebrae and discs in a given scan, and (2) a convolutional neural network (CNN) model that predicts several radiological gradings. The performance of the model, in terms of class average accuracy, was compared with the intra-observer class average accuracy of the radiologist. Results The detection system achieved 95.6% accuracy in terms of disc detection and labeling. The model is able to produce predictions of multiple pathological gradings that consistently matched those of the radiologist. The model identifies 'Evidence Hotspots' that are the voxels that most contribute to the degradation scores. Conclusions Automation of radiological grading is now on par with human performance. The system can be beneficial in aiding clinical diagnoses in terms of objectivity of gradings and the speed of analysis. It can also draw the attention of a radiologist to regions of degradation. This objectivity and speed is an important stepping stone in the investigation of the relationship between MRIs and clinical diagnoses of back pain in large cohorts. Level of Evidence: Level 3.

show abstract

Section: Discussionmentioning

confidence: 85%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Safranin O–fast green staining and hematoxylin and eosin (HE) staining, respectively, were used to assess the disk degeneration. The construction of intervertebral disk and the NP cells’ morphology and cellularity was observed by another three double-blinded experienced histology researchers using a microscope (Leica), and the histology score was evaluated according to a grading scale (Han et al, 2008; Castro-Mateos et al, 2016).…”

Section: Isolation and Culturementioning

confidence: 99%

Luteoloside Inhibits IL-1β-Induced Apoptosis and Catabolism in Nucleus Pulposus Cells and Ameliorates Intervertebral Disk Degeneration

et al. 2019

View full text Add to dashboard Cite

Intervertebral disk degeneration (IDD) is the major cause of low back pain (LBP), which affects 80% of the world’s population. Interleukin 1 beta (IL-1β) is a major inflammatory factor that accelerates disk degeneration, and IL-1β levels increase in degenerative disks. It has recently been reported that luteoloside—a type of flavonoid glycoside—has anti-inflammatory properties. In the present study, we investigated the protective potential of luteoloside in IDD. We found that luteoloside maintains cell morphology and inhibits apoptosis (indicated by the reduced expression of cleaved caspase 3) in IL-1β-treated nucleus pulposus (NP) cells. It also suppresses inflammatory mediators—nitric oxide (NO), prostaglandin E2 (PGE2), tumor necrosis factor alpha (TNF-α), interleukin 6 (IL-6), cyclooxygenase 2 (COX-2), and inducible nitric oxide synthase (iNOS)—in IL-1β-treated NP cells. Furthermore, we found increased collagen II and aggrecan expression and reduced MMP13 and ADAMTS5 expression in luteoloside-treated NP cells in the presence of IL-1β. Nuclear factor (erythroid-derived 2)-like 2 (Nrf2) is involved in apoptosis, inflammation, and extracellular matrix (ECM) homeostasis. Mechanistic studies revealed that the NF-κB signaling pathway is inhibited by luteoloside, and Nrf2 is involved in the regulation of luteoloside in NF-κB signaling because Nrf2 knockdown reduced the suppressive effect of luteoloside on NF-κB signaling. We also established a puncture-induced rat IDD model and demonstrated that the persistent intraperitoneal injection of luteoloside ameliorates the progression of IDD. In conclusion, we demonstrated that luteoloside activates the Nrf2/HO-1 signaling axis and is a potential therapeutic medicine for IDD.

show abstract

“…IVD degeneration, which has been extensively investigated for years, is a main cause of low back pain [ 39 ]. Nevertheless, to date, its molecular mechanism remains largely unclear.…”

Section: Discussionmentioning

confidence: 99%

Ghrelin protects against nucleus pulposus degeneration through inhibition of NF-κB signaling pathway and activation of Akt signaling pathway

et al. 2017

Oncotarget

View full text Add to dashboard Cite

The objective of the present study was to examine the potential role of ghrelin in degeneration of nucleus pulposus (NP). Lower expression levels of ghrelin were found in human NP cells stimulated with interleukin-1β (IL-1β). Moreover, exogenous ghrelin suppressed IL-1β induced degeneration and inflammation associated biomarkers in human NP cells, including matrix metalloproteinase-13, a disintegrin and metalloproteinase with thrombospondin motifs-5, tumor necrosis factor-α and iNOS, which was possibly mediated by antagonization of NF-κB signaling. Moreover, ghrelin enhanced production of critical extracellular matrix of NP cells, including collagen 2, aggrecan, and Sox-9 in NP cells. Ghrelin also promoted NP tissue regeneration in a rabbit IVD degeneration model, which seems to be associated with growth hormone secretagogue receptor. Additionally, the protective role of ghrelin in anabolism potentially relies on activation of Akt signaling pathway. Taken together, ghrelin may represent a molecular target for prevention and treatment of intervertebral disc degeneration.

show abstract

Intervertebral disc classification by its degree of degeneration from T2-weighted magnetic resonance images

Cited by 38 publications

References 27 publications

ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist

ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist

Luteoloside Inhibits IL-1β-Induced Apoptosis and Catabolism in Nucleus Pulposus Cells and Ameliorates Intervertebral Disk Degeneration

Ghrelin protects against nucleus pulposus degeneration through inhibition of NF-κB signaling pathway and activation of Akt signaling pathway

Contact Info

Product

Resources

About