Reliability and Accuracy of Cross-sectional Radiographic Assessment of Severe Knee Osteoarthritis: Role of Training and Experience

Klara, Kristina; Collins, Jamie E.; Gurary, Ellen B.; Elman, Scott A.; Stenquist, Derek S; Losina, Elena; Katz, Jeffrey N.

doi:10.3899/jrheum.151300

Cited by 24 publications

(19 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent study aimed to determine the reliability of radiographic assessment of knee osteoarthritis (OA) by non-clinician readers compared to an experienced radiologist. 23 This study showed an intra-reader reliability among radiologist (kappa) ranged from 0.40 to 1.0 for individual radiographic features and 0.72-1.0 for Kellgren-Lawrence (K-L) grade. Inter-reader agreement among non-clinicians ranged from kappa of 0.45-0.94 for individual features, and 0.66-0.97 for K-L grade.…”

Section: Advances In Radiographic Assessment Of Knee Oamentioning

confidence: 75%

“…Performance of both these studies are comparable to human reliability. A recent study aimed to determine the reliability of radiographic assessment of knee osteoarthritis (OA) by non‐clinician readers compared to an experienced radiologist . This study showed an intra‐reader reliability among radiologist (kappa) ranged from 0.40 to 1.0 for individual radiographic features and 0.72–1.0 for Kellgren–Lawrence (K–L) grade.…”

Section: Advances In Radiographic Assessment Of Knee Oamentioning

confidence: 99%

See 1 more Smart Citation

Translation of morphological and functional musculoskeletal imaging

Pedoia

Majumdar

2018

Journal Orthopaedic Research

View full text Add to dashboard Cite

In an effort to develop quantitative biomarkers for degenerative joint disease and fill the void that exists for diagnosing, monitoring, and assessing the extent of whole joint degeneration, the past decade has been marked by a greatly increased role of noninvasive imaging. This coupled with recent advances in image processing and deep learning opens new possibilities for promising quantitative techniques. The clinical translation of quantitative imaging was previously hampered by tedious non‐scalable and subjective image analysis. Osteoarthritis (OA) diagnosis using X‐rays can be automated by the use of deep learning models and pilot studies showed feasibility of using similar techniques to reliably segment multiple musculoskeletal tissues and detect and stage the severity of morphological abnormalities in magnetic resonance imaging (MRI). Automation and more advanced feature extraction techniques have applications on larger more heterogeneous samples. Analyses based on voxel based relaxometry have shown local patterns in relaxation time elevations and local correlations with outcome variables. Bone cartilage interactions are also enhanced by the analysis of three‐dimensional bone morphology and the potential for the assessment of metabolic activity with simultaneous Positron Emission Tomography (PET)/MR systems. Novel techniques in image processing and deep learning are augmenting imaging to be a source of quantitative and reliable data and new multidimensional analytics allow us to exploit the interactions of data from various sources. In this review, we aim to summarize recent advances in quantitative imaging, the application of image processing and deep learning techniques to study knee and hip OA. ©2018 Orthopaedic Research Society. Published by Wiley Periodicals, Inc. J Orthop Res XX:XX–XX, 2018.

show abstract

Section: Advances In Radiographic Assessment Of Knee Oamentioning

confidence: 75%

Section: Advances In Radiographic Assessment Of Knee Oamentioning

confidence: 99%

Translation of morphological and functional musculoskeletal imaging

Pedoia

Majumdar

2018

Journal Orthopaedic Research

View full text Add to dashboard Cite

show abstract

“…The discrete binning of disease classes is human-engineered and the underlying biology of disease is usually more accurately described as a spectrum 4 . In addition, previous work has shown that there is substantial intra-and inter-expert variability in the annotation of both plus disease classification and KL grade 4,21,22 .…”

Section: Discussionmentioning

confidence: 99%

Siamese neural networks for continuous disease severity evaluation and change detection in medical imaging

Chang

Bearce

et al. 2020

npj Digit. Med.

View full text Add to dashboard Cite

Using medical images to evaluate disease severity and change over time is a routine and important task in clinical decision making. Grading systems are often used, but are unreliable as domain experts disagree on disease severity category thresholds. These discrete categories also do not reflect the underlying continuous spectrum of disease severity. To address these issues, we developed a convolutional Siamese neural network approach to evaluate disease severity at single time points and change between longitudinal patient visits on a continuous spectrum. We demonstrate this in two medical imaging domains: retinopathy of prematurity (ROP) in retinal photographs and osteoarthritis in knee radiographs. Our patient cohorts consist of 4861 images from 870 patients in the Imaging and Informatics in Retinopathy of Prematurity (i-ROP) cohort study and 10,012 images from 3021 patients in the Multicenter Osteoarthritis Study (MOST), both of which feature longitudinal imaging data. Multiple expert clinician raters ranked 100 retinal images and 100 knee radiographs from excluded test sets for severity of ROP and osteoarthritis, respectively. The Siamese neural network output for each image in comparison to a pool of normal reference images correlates with disease severity rank (ρ = 0.87 for ROP and ρ = 0.89 for osteoarthritis), both within and between the clinical grading categories. Thus, this output can represent the continuous spectrum of disease severity at any single time point. The difference in these outputs can be used to show change over time. Alternatively, paired images from the same patient at two time points can be directly compared using the Siamese neural network, resulting in an additional continuous measure of change between images. Importantly, our approach does not require manual localization of the pathology of interest and requires only a binary label for training (same versus different). The location of disease and site of change detected by the algorithm can be visualized using an occlusion sensitivity map-based approach. For a longitudinal binary change detection task, our Siamese neural networks achieve test set receiving operator characteristic area under the curves (AUCs) of up to 0.90 in evaluating ROP or knee osteoarthritis change, depending on the change detection strategy. The overall performance on this binary task is similar compared to a conventional convolutional deep-neural network trained for multi-class classification. Our results demonstrate that convolutional Siamese neural networks can be a powerful tool for evaluating the continuous spectrum of disease severity and change in medical imaging.npj Digital Medicine (2020) 3:48 ; https://doi.

show abstract

“…Inter-observer agreement of image quality was analyzed with a Kappa test. Levels of agreement were defined as follows: k < 0.20 indicated slight agreement; k = 0.20-0.40, fair agreement; k = 0.41-0.60, moderate agreement; k = 0.61-0.80, substantial agreement; k = 0.81-1.0, excellent agreement [5]. One-way ANOVA was used for measuring phantom size changes in three anatomy positions at different table heights.…”

Section: Discussionmentioning

confidence: 99%

How table height influences image quality and radiation dose of chest CT scans with automatic exposure control: a phantom study?

et al. 2020

View full text Add to dashboard Cite

Objective To investigate the influence of table height on image quality and radiation dose of chest CT scan with automatic exposure control (AEC) technology. Materials and methods A chest phantom was scanned with AEC technology at 11 different table heights from 100 to 200 mm with 130 mm table height (iso-center was positioned at the midaxillary line of the phantom) used as reference center position. Image quality and radiation doses at different heights were statistically analyzed. Results Compared with 130 mm table height, the radiation dose of chest CT scan changed about 15% with the table height at 160 mm, or table height at 100 mm. The trend of the tube current-time (mAs) curve at different table heights was the same. In the thoracic inlet area, mAs changed most obviously, compared to the heart area. The noise of the image at higher table heights was not significantly different from the reference table height, but lower table heights increased the noise. When the height of the table was decreased from 130 to 100 mm, the size of the measured phantom changed greatly, by 5.22%, and when the height of the table was increased from 130 to 160 mm, the measured phantom size decreased to 95.07%. The score of the subjective image quality was lower when the table height was lowered. Conclusion With table height settled between anterior axillary line and midaxillary line of the phantom, acceptable subjective image quality could be obtained with a lower radiation dose.

show abstract

Reliability and Accuracy of Cross-sectional Radiographic Assessment of Severe Knee Osteoarthritis: Role of Training and Experience

Cited by 24 publications

References 15 publications

Translation of morphological and functional musculoskeletal imaging

Translation of morphological and functional musculoskeletal imaging

Siamese neural networks for continuous disease severity evaluation and change detection in medical imaging

How table height influences image quality and radiation dose of chest CT scans with automatic exposure control: a phantom study?

Contact Info

Product

Resources

About