The KNee OsteoArthritis Prediction (KNOAP2020) challenge: An image analysis challenge to predict incident symptomatic radiographic knee osteoarthritis from MRI and X-ray images

Hirvasniemi, Jukka; Runhaar, Jos; Heijden, Rianne A. van der; Zokaeinikoo, Maryam; Yang, Mingrui; Li, Xiaojuan; Tan, Jimin; Rajamohan, Haresh Rengaraj; Zhou, Yuyue; Deniz, Cem M.; Calivá, Francesco; Iriondo, Claudia; Lee, Jinhee J.; Liu, Felix; Martinez, Alejandro Morales; Namiri, Nikan K.; Pedoia, Valentina; Panfilov, Egor; Bayramoglu, Neslihan; Nguyen, Huy; Nieminen, Miika T.; Saarakkala, Simo; Tiulpin, Aleksei; Lin, Endlin; Li, Alicja; Li, Vincent; Dam, Erik B.; Chaudhari, Akshay; Kijowski, Richard; Bierma-Zeinstra, Sita M A; Oei, Edwin H.G.; Klein, Stefan

doi:10.1016/j.joca.2022.10.001

Cited by 22 publications

(28 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data used in KNAOP2020 were obtained from the Osteoarthritis Initiative (OAI) database. 42 The average age of the subjects in this dataset was over 61 years old. 42 this study constructed a model that included all OA without distinction.…”

Section: Discussionmentioning

confidence: 99%

“…42 The average age of the subjects in this dataset was over 61 years old. 42 this study constructed a model that included all OA without distinction. In the case of older subjects, the possibility of having OA in one of the body parts would be higher than that of younger subjects.…”

Section: Discussionmentioning

confidence: 99%

“…In the KNee OsteoArthritis Prediction challenge held in 2020 (KNOAP2020), various machine learning models for predicting knee OA have been submitted using X-ray and MRI image and clinical data such as age, BMI, affected side, and history of knee injury. 42 The model that showed the highest ROC AUC score in the competition was a model that applied the logistic regression algorithm using X-ray and clinical data and scored 0.636. 42 The model with the next highest ROC AUC score was an ensemble model using X-ray, MRI, and clinical data, with a score of 0.624.…”

Section: Model Evaluationmentioning

confidence: 99%

“…42 The model that showed the highest ROC AUC score in the competition was a model that applied the logistic regression algorithm using X-ray and clinical data and scored 0.636. 42 The model with the next highest ROC AUC score was an ensemble model using X-ray, MRI, and clinical data, with a score of 0.624. 42 According to Hosnijeh (2018), the ROC AUC score of the hip OA model, which was constructed by combining imaging, biochemical, and genetic variables with variables such as age, obesity, waist circumference, and gender, was between 0.67 and 0.82.…”

Section: Model Evaluationmentioning

confidence: 99%

See 3 more Smart Citations

Ensemble Approach for Predicting the Diagnosis of Osteoarthritis Using Soft Voting Classifier

Kim

2023

Preprint

View full text Add to dashboard Cite

Background: Osteoarthritis (OA) is a common degenerative disease of the joints. Risk factors for osteoarthritis include non-modifiable factors such as age and gender and modifiable factors such as physical activity. Purpose: The purpose of this study was to construct a soft voting ensemble model to predict OA diagnosis using variables related to individual characteristics and physical activity, and to identify important variables in constructing the model through permutation importance. Method: Using the RFECV technique, the variables with the best predictive performance were selected among variables, and an ensemble model combining the RandomForest, XGBoost, and LightGBM algorithms was constructed, and the predictive performance and permutation importance of each variable were evaluated. Result: The variables selected to construct the model were age, gender, grip strength, and quality of life, and the accuracy of the ensemble model was 0.828. The most important variable in constructing the model was age (0.199), followed by grip strength (0.053), quality of life (0.043), and gender (0.034). Conclusion: The performance of the model for predicting OA was relatively good, and if this model is continuously used and updated, this model could readily be used to predict OA diagnosis and the predictive performance of OA may be further improved.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Model Evaluationmentioning

confidence: 99%

Section: Model Evaluationmentioning

confidence: 99%

See 2 more Smart Citations

Ensemble Approach for Predicting the Diagnosis of Osteoarthritis Using Soft Voting Classifier

Kim

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Overall, the approaches reported by the related works and the studies published in Christodoulou et al [ 27 ], Du et al [ 28 ], Hirvasniemi et al [ 29 ], and Sharma et al [ 30 ] have utilized DL and ML techniques for diagnosis different bone disease. These methods have provided excellent job performance for binary-class classification.…”

Section: Introductionmentioning

confidence: 99%

Identifying Severity Grading of Knee Osteoarthritis from X-ray Images Using an Efficient Mixture of Deep Learning and Machine Learning Models

Ahmed

Mstafa

2022

Diagnostics

View full text Add to dashboard Cite

Recently, many diseases have negatively impacted people’s lifestyles. Among these, knee osteoarthritis (OA) has been regarded as the primary cause of activity restriction and impairment, particularly in older people. Therefore, quick, accurate, and low-cost computer-based tools for the early prediction of knee OA patients are urgently needed. In this paper, as part of addressing this issue, we developed a new method to efficiently diagnose and classify knee osteoarthritis severity based on the X-ray images to classify knee OA in (i.e., binary and multiclass) in order to study the impact of different class-based, which has not yet been addressed in previous studies. This will provide physicians with a variety of deployment options in the future. Our proposed models are basically divided into two frameworks based on applying pre-trained convolutional neural networks (CNN) for feature extraction as well as fine-tuning the pre-trained CNN using the transfer learning (TL) method. In addition, a traditional machine learning (ML) classifier is used to exploit the enriched feature space to achieve better knee OA classification performance. In the first one, we developed five classes-based models using a proposed pre-trained CNN for feature extraction, principal component analysis (PCA) for dimensionality reduction, and support vector machine (SVM) for classification. While in the second framework, a few changes were made to the steps in the first framework, the concept of TL was used to fine-tune the proposed pre-trained CNN from the first framework to fit the two classes, three classes, and four classes-based models. The proposed models are evaluated on X-ray data, and their performance is compared with the existing state-of-the-art models. It is observed through conducted experimental analysis to demonstrate the efficacy of the proposed approach in improving the classification accuracy in both multiclass and binary class-based in the OA case study. Nonetheless, the empirical results revealed that the fewer multiclass labels used, the better performance achieved, with the binary class labels outperforming all, which reached a 90.8% accuracy rate. Furthermore, the proposed models demonstrated their contribution to early classification in the first stage of the disease to help reduce its progression and improve people’s quality of life.

show abstract

Integrating Radiomics and Neural Networks for Knee Osteoarthritis Incidence Prediction

Li,

Cao,

et al. 2024

Arthritis & Rheumatology

View full text Add to dashboard Cite

ObjectiveAccurately predicting knee osteoarthritis (KOA) is essential for early detection and personalized treatment. We aimed to develop and test an MRI‐based Joint Space Radiomic Model (JS‐RM) to predict radiographic KOA incidence through neural networks by integrating meniscus and femorotibial cartilage radiomic features.MethodsIn the Osteoarthritis Initiative cohort, knees without radiographic KOA at baseline but at high risk for radiographic KOA were included. Case knees developed radiographic KOA whereas control knees did not over 4‐year. We randomly split the knees into development and test cohorts (D/T=8/2) and extracted features from baseline 3D‐DESS‐sequence MRI. Model performance was evaluated using an area under the receiver operating characteristic curve (AUC), sensitivity, and specificity in both cohorts. Nine resident surgeons performed the reader experiment without/with the JS‐RM aid.ResultsOur study included 549 knees in the development cohort (275 cases vs. 274 controls) and 137 knees in the test cohort (68 cases vs. 69 controls). In the test cohort, JS‐RM had a favorable accuracy for predicting the radiographic KOA incidence with an AUC of 0.931 (95%CI: 0.876‐0.963), a sensitivity of 84.4% (95%CI: 83.9%‐84.9%), and a specificity of 85.6% (95%CI: 85.2%‐86.0%). The mean specificity and sensitivity of resident surgeons through MRI reading in predicting radiographic KOA incidence were increased from 0.474 (95%CI: 0.333‐0.614) and 0.586 (95%CI: 0.429‐0.743) without the assistance of JS‐RM to 0.874 (95%CI: 0.847‐0.901) and 0.812 (95%CI: 0.742‐0.881) with JS‐RM assistance, respectively (p<.001).ConclusionJS‐RM integrating the features of the meniscus and cartilage showed improved predictive values in radiographic KOA incidence.

show abstract

The KNee OsteoArthritis Prediction (KNOAP2020) challenge: An image analysis challenge to predict incident symptomatic radiographic knee osteoarthritis from MRI and X-ray images

Cited by 22 publications

References 42 publications

Ensemble Approach for Predicting the Diagnosis of Osteoarthritis Using Soft Voting Classifier

Ensemble Approach for Predicting the Diagnosis of Osteoarthritis Using Soft Voting Classifier

Identifying Severity Grading of Knee Osteoarthritis from X-ray Images Using an Efficient Mixture of Deep Learning and Machine Learning Models

Integrating Radiomics and Neural Networks for Knee Osteoarthritis Incidence Prediction

Contact Info

Product

Resources

About