Deep learning-based algorithm for assessment of knee osteoarthritis severity in radiographs matches performance of radiologists

Swiecicki, Albert; Li, Nianyi; O’Donnell, J; Said, Nicholas; Yang, Jichen; Mather, Richard C.; Jiranek, William A.; Mazurowski, Maciej A.

doi:10.1016/j.compbiomed.2021.104334

Cited by 68 publications

(44 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of our network is generally high compared to similar recent studies. As Swiecicki et al [ 11 ] displayed in their 2021 paper, DL can now assess knee OA severity similar to radiologists. Tiulpin et al [ 23 ] recently showed a new DL approach to significantly increase detection of radiographic OA presence.…”

Section: Discussionmentioning

confidence: 99%

“…Major differences between our study and that of the above-mentioned ones are how we let the network learn from an entire image series without any preprocessing. Comparable studies often use big ImageNet datasets like that of “The Osteoarthritis Initiative (OAI)” [ 12 , 15 ] or “Multicenter Osteoarthritis Study (MOST)” [ 11 , 23 ] to train their networks. In contrast, all images used in our training set was taken from a general setting where radiographs can differ greatly in quality and even beam angels.…”

Section: Discussionmentioning

confidence: 99%

“…New technological advancement and recent progresses in medical image analysis using deep learning (DL), a form of artificial intelligence (AI) has been showing promising results in detecting knee OA and even classification of its severity based on the KL grading system [ 11 – 13 ]. Traditional machine learning (ML) has often put a lot of effort into extracting features before training the algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…This has turned out to be a hugely successful approach which opens up new ways to non-experts in the field of ML to implement their own research and applications, such as medical image analysis [ 14 ]. To the best of our knowledge, there is only a few published articles on applying DL for classifying knee OA [ 11 – 13 , 15 – 17 ]; However, these are mostly done, using pre-processed, highly optimized images.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automating classification of osteoarthritis according to Kellgren-Lawrence in the knee using deep learning in an unfiltered adult population

Olsson

Akbarian

Lind

et al. 2021

BMC Musculoskelet Disord

View full text Add to dashboard Cite

Background Prevalence for knee osteoarthritis is rising in both Sweden and globally due to increased age and obesity in the population. This has subsequently led to an increasing demand for knee arthroplasties. Correct diagnosis and classification of a knee osteoarthritis (OA) are therefore of a great interest in following-up and planning for either conservative or operative management. Most orthopedic surgeons rely on standard weight bearing radiographs of the knee. Improving the reliability and reproducibility of these interpretations could thus be hugely beneficial. Recently, deep learning which is a form of artificial intelligence (AI), has been showing promising results in interpreting radiographic images. In this study, we aim to evaluate how well an AI can classify the severity of knee OA, using entire image series and not excluding common visual disturbances such as an implant, cast and non-degenerative pathologies. Methods We selected 6103 radiographic exams of the knee taken at Danderyd University Hospital between the years 2002-2016 and manually categorized them according to the Kellgren & Lawrence grading scale (KL). We then trained a convolutional neural network (CNN) of ResNet architecture using PyTorch. We evaluated the results against a test set of 300 exams that had been reviewed independently by two senior orthopedic surgeons who settled eventual interobserver disagreements through consensus sessions. Results The CNN yielded an overall AUC of more than 0.87 for all KL grades except KL grade 2, which yielded an AUC of 0.8 and a mean AUC of 0.92. When merging adjacent KL grades, all but one group showed near perfect results with AUC > 0.95 indicating excellent performance. Conclusion We have found that we could teach a CNN to correctly diagnose and classify the severity of knee OA using the KL grading system without cleaning the input data from major visual disturbances such as implants and other pathologies.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automating classification of osteoarthritis according to Kellgren-Lawrence in the knee using deep learning in an unfiltered adult population

Olsson

Akbarian

Lind

et al. 2021

BMC Musculoskelet Disord

View full text Add to dashboard Cite

show abstract

“…The model trained using plain knee X-rays showed a multiclass accuracy of 66.7%. In addition, Swiecicki et al trained a Faster R-CNN using plain and lateral knee X-rays from the Multicenter Osteoarthritis Study dataset [30]. The multiclass accuracy of this model was 71.9%, which showed improved performance compared with the previous study conducted by Tiulpin et al…”

Section: Deep Learning For Osteoarthritis and Prediction Of Arthroplasty Implantsmentioning

confidence: 99%

Deep Learning for Orthopedic Disease Based on Medical Image Analysis: Present and Future

Lee

Chung

2022

Applied Sciences

View full text Add to dashboard Cite

Since its development, deep learning has been quickly incorporated into the field of medicine and has had a profound impact. Since 2017, many studies applying deep learning-based diagnostics in the field of orthopedics have demonstrated outstanding performance. However, most published papers have focused on disease detection or classification, leaving some unsatisfactory reports in areas such as segmentation and prediction. This review introduces research published in the field of orthopedics classified according to disease from the perspective of orthopedic surgeons, and areas of future research are discussed. This paper provides orthopedic surgeons with an overall understanding of artificial intelligence-based image analysis and the information that medical data should be treated with low prejudice, providing developers and researchers with insight into the real-world context in which clinicians are embracing medical artificial intelligence.

show abstract

Using Administrative Codes to Measure Health Care Quality

Portuondo

Harris

Massarweh

2022

JAMA

View full text Add to dashboard Cite

The US spends more annually per capita on health care than any other country, with inpatient care accounting for approximately 20% to 30% of total expenditures. 1,2 In an effort to eliminate waste, the US health care system is evolving away from fee-for-service payment models toward value-based reimbursement models. Highstakes applications of health care quality measures, such as attaching financial incentives to performance and public reporting of data regarding quality or cost, are central to the effort to optimize health care spending. Because administrative data (ie, diagnosis and procedural codes) are standardized and can be accessed at a low cost in virtually every practice setting, these codes are commonly used to construct process and outcome quality measures used in value-based payment and quality assessment programs.Although the use of administrative data for quality measurement is convenient, this approach creates opportunities to "game the system" because hospitals can optimize their coding practices to maximize reimbursement or perceived performance. [3][4][5][6] For outcome quality measures, risk adjustment has a critical role by accounting for underlying variation in the level of risk across patient populations, thereby ensuring that measurement, comparisons, and reimbursement are fair

show abstract

Deep learning-based algorithm for assessment of knee osteoarthritis severity in radiographs matches performance of radiologists

Cited by 68 publications

References 20 publications

Automating classification of osteoarthritis according to Kellgren-Lawrence in the knee using deep learning in an unfiltered adult population

Automating classification of osteoarthritis according to Kellgren-Lawrence in the knee using deep learning in an unfiltered adult population

Deep Learning for Orthopedic Disease Based on Medical Image Analysis: Present and Future

Using Administrative Codes to Measure Health Care Quality

Contact Info

Product

Resources

About