Fully automatic knee osteoarthritis severity grading using deep neural networks with a novel ordinal loss

Chen, Pingjun; Gao, Linlin; Shi, Xiaoshuang; Allen, Kyle D.; Yang, Lin

doi:10.1016/j.compmedimag.2019.06.002

Cited by 176 publications

(120 citation statements)

References 21 publications

Supporting

Mentioning

113

Contrasting

Unclassified

Order By: Relevance

“…It has been recognized for its strengths in image classification, and as such, implementation of DL in diagnostic medicine has been heavily investigated, including the diagnosis of maxillary sinusitis with conventional radiography, detection of osteonecrosis of the femoral head with digital radiography, detection of moyamoya disease in plain skull radiography, and diagnosis of the severity of knee OA from plain radiographs [ 6 , 11 , 12 , 13 ]. To date, many studies have strived to improve the diagnostic performance, but to the best of our knowledge, they have mostly focused on using only radiologic data [ 14 ].…”

Section: Introductionmentioning

confidence: 99%

Can Additional Patient Information Improve the Diagnostic Performance of Deep Learning for the Interpretation of Knee Osteoarthritis Severity

Kim

Lee

Choi

et al. 2020

JCM

View full text Add to dashboard Cite

The study compares the diagnostic performance of deep learning (DL) with that of the former radiologist reading of the Kellgren–Lawrence (KL) grade and evaluates whether additional patient data can improve the diagnostic performance of DL. From March 2003 to February 2017, 3000 patients with 4366 knee AP radiographs were randomly selected. DL was trained using knee images and clinical information in two stages. In the first stage, DL was trained only with images and then in the second stage, it was trained with image data and clinical information. In the test set of image data, the areas under the receiver operating characteristic curve (AUC)s of the DL algorithm in diagnosing KL 0 to KL 4 were 0.91 (95% confidence interval (CI), 0.88–0.95), 0.80 (95% CI, 0.76–0.84), 0.69 (95% CI, 0.64–0.73), 0.86 (95% CI, 0.83–0.89), and 0.96 (95% CI, 0.94–0.98), respectively. In the test set with image data and additional patient information, the AUCs of the DL algorithm in diagnosing KL 0 to KL 4 were 0.97 (95% confidence interval (CI), 0.71–0.74), 0.85 (95% CI, 0.80–0.86), 0.75 (95% CI, 0.66–0.73), 0.86 (95% CI, 0.79–0.85), and 0.95 (95% CI, 0.91–0.97), respectively. The diagnostic performance of image data with additional patient information showed a statistically significantly higher AUC than image data alone in diagnosing KL 0, 1, and 2 (p-values were 0.008, 0.020, and 0.027, respectively).The diagnostic performance of DL was comparable to that of the former radiologist reading of the knee osteoarthritis KL grade. Additional patient information improved DL diagnosis in interpreting early knee osteoarthritis.

show abstract

Section: Introductionmentioning

confidence: 99%

Can Additional Patient Information Improve the Diagnostic Performance of Deep Learning for the Interpretation of Knee Osteoarthritis Severity

Kim

Lee

Choi

et al. 2020

JCM

View full text Add to dashboard Cite

show abstract

“…Recent examples are the prediction of OA progression based on radiographs by a data-driven deep learning approach. 30,31 Opportunistic Osteoporosis Screening Osteoporosis is a highly prevalent yet underdiagnosed condition. Bone-rich data from body computed tomography (CT) scans of the chest, abdomen, and pelvis that are performed for other clinical indications are seldom used yet can provide an opportunity for quantitative osteoporosis screening.…”

Section: Osteoarthritismentioning

confidence: 99%

The Value of Quantitative Musculoskeletal Imaging

Visser

Goergen

Klein

et al. 2020

Semin Musculoskelet Radiol

View full text Add to dashboard Cite

Musculoskeletal imaging is mainly based on the subjective and qualitative analysis of imaging examinations. However, integration of quantitative assessment of imaging data could increase the value of imaging in both research and clinical practice. Some imaging modalities, such as perfusion magnetic resonance imaging (MRI), diffusion MRI, or T2 mapping, are intrinsically quantitative. But conventional morphological imaging can also be analyzed through the quantification of various parameters. The quantitative data retrieved from imaging examinations can serve as biomarkers and be used to support diagnosis, determine patient prognosis, or monitor therapy.We focus on the value, or clinical utility, of quantitative imaging in the musculoskeletal field. There is currently a trend to move from volume- to value-based payments. This review contains definitions and examines the role that quantitative imaging may play in the implementation of value-based health care. The influence of artificial intelligence on the value of quantitative musculoskeletal imaging is also discussed.

show abstract

“…Antony et al [3] used fully convolutional networks for the same problem. Recently, Chen et al [9] proposed to use object detection methods to measure the knee OA severity.…”

Section: Related Workmentioning

confidence: 99%

“…1). At the test time, when comparing the performance of the full system, we used an extended set of landmarks for evaluation -0, 4, 8,9,12,15. The intuition here is to compare the landmark methods on those landmark points that are the most crucial in applications (tibial corners for landmark localization as well as tibial and femoral centers for the ROI localization).…”

Section: Evaluation and Metricsmentioning

confidence: 99%

“…Wing + mixup α = 0.75 + cutout 10% (no wd, finetune) 45.92 ± 8.79 72.39 ± 8.60 85.36 ± 4.63 90.91 ± 3.211.34 Results of the model selection for high-cost annotations on the OAI dataset. The values of PCK/recall (%) at different precision are shown as average and standard deviation for the landmarks 0,8,9,15, while the amount of outliers is calculated for all the landmarks. The comparison is done at 0.3 mm image resolution (pixel spacing).…”

mentioning

confidence: 99%

See 1 more Smart Citation

KNEEL: Knee Anatomical Landmark Localization Using Hourglass Networks

Tiulpin

Melekhov

Saarakkala

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

This paper addresses the challenge of localization of anatomical landmarks in knee X-ray images at different stages of osteoarthritis (OA). Landmark localization can be viewed as regression problem, where the landmark position is directly predicted by using the region of interest or even full-size images leading to large memory footprint, especially in case of high resolution medical images. In this work, we propose an efficient deep neural networks framework with an hourglass architecture utilizing a soft-argmax layer to directly predict normalized coordinates of the landmark points. We provide an extensive evaluation of different regularization techniques and various loss functions to understand their influence on the localization performance. Furthermore, we introduce the concept of transfer learning from low-budget annotations, and experimentally demonstrate that such approach is improving the accuracy of landmark localization. Compared to the prior methods, we validate our model on two datasets that are independent from the train data and assess the performance of the method for different stages of OA severity. The proposed approach demonstrates better generalization performance compared to the current state-of-the-art.

show abstract

Fully automatic knee osteoarthritis severity grading using deep neural networks with a novel ordinal loss

Cited by 176 publications

References 21 publications

Can Additional Patient Information Improve the Diagnostic Performance of Deep Learning for the Interpretation of Knee Osteoarthritis Severity

Can Additional Patient Information Improve the Diagnostic Performance of Deep Learning for the Interpretation of Knee Osteoarthritis Severity

The Value of Quantitative Musculoskeletal Imaging

KNEEL: Knee Anatomical Landmark Localization Using Hourglass Networks

Contact Info

Product

Resources

About