A complex network based approach for knee Osteoarthritis detection: Data from the Osteoarthritis initiative

CDK: A novel high-performance transfer feature technique for early detection of osteoarthritis

Knee osteoarthritis (OA) is a prevalent condition causing significant disability, particularly among the elderly, necessitating advancements in diagnostic methodologies to facilitate early detection and treatment. Traditional OA diagnosis, relying on radiography and physical exams, faces limitations in accuracy and objectivity. This underscores the need for more advanced diagnostic methods, such as machine learning (ML) and deep learning (DL), to improve OA detection and classification. This research introduces a novel ensemble learning approach for image data feature extraction which ingeniously combines the strengths of 2 advanced (ML) models with a (DL) method to substantially improve the accuracy of OA detection from radiographic images. This innovative strategy aims to address the limitations of traditional diagnostic tools by leveraging the enhanced sensitivity and specificity of combined ML and DL models. The methodology deployed in this study encompasses the application of 10 ML models to a comprehensive publicly available Kaggle dataset with a total of 3615 samples of knee X-ray images. Through rigorous k-fold cross-validation and meticulous hyperparameter optimization, we also included evaluation metrics like accuracy, receiver operating characteristic, precision, recall, and F1-score to assess our models' performance effectively. The proposed novel CDK (convolutional neural network, decision tree, K-nearest classifier) ensemble approach for feature extraction is designed to synergize the predictive capabilities of individual models, thereby significantly improving the detection accuracy of OA indicators within radiographic images. We applied several ML and DL approaches to the newly created feature set to evaluate performance. The CDK ensemble model outperformed state-of-the-art studies with a high-performance score of 99.72% accuracy. This remarkable achievement underscores the model's exceptional capability in the early detection of OA, highlighting its superiority in comparison to existing methods.

Multiscale-temporal Feature Extraction and boundary confusion alleviation for VAG-based fine-grained multi-grade osteoarthritis deterioration monitoring

BACKGROUND AND OBJECTIVE

Multi-grade osteoarthritis (OA) deterioration monitoring in the daily paradigm using Vibroarthrography (VAG) is very challenging due to two difficulties: (1) the composition of VAG signals is complex in the daily paradigm where friction is intensified because of weight-bearing movements. (2) VAG signal samples near the decision boundary of adjacent deterioration grades are easy to be misclassified. The majority of existing works only focus on the binary classification of OA, providing inadequate assistance in instructing physicians to develop treatment plans based on the presence or absence of OA. Thus, we propose a novel framework for fine-grained multi-grade OA deterioration monitoring in the daily paradigm.

METHODS

We propose an end-to-end deep learning framework termed Fine-grained Multi-grade OA Deterioration Monitor (FMOADM), which consists of Multiscale-temporal Feature Extraction (MTFE) and Confusion-Free Master-Slave (CF-MS) Classification. Specifically, MTFE is adopted to extract multiscale-temporal discriminative features from the complicated VAG signals. And center loss is introduced by CF-MS to alleviate confusion at the boundary of adjacent deterioration grades in the feature space. Meanwhile, a master-slave structure is proposed for further fine-grained classification, where the master classifier integrates a channel attention mechanism and the slave classifier is designed to update MTFE parameters. As a result, the proposed method ensures fine-grained multi-grade OA monitoring performance via multiscale-temporal discriminative features and boundary confusion alleviation.

RESULTS

Experimental results on the VAG-OA dataset demonstrate that our framework outperforms counterpart methods in the daily paradigm. The proposed framework achieved 78% in precision, obtaining an 8% improvement over the state-of-the-art method.

CONCLUSION

The proposed framework benefits efficient multi-grade OA deterioration monitoring, empowering physicians to develop treatment plans based on fine-grained monitoring results. It takes knee joint health monitoring in daily activities a step further toward feasible.

A semi-supervised multiview-MRI network for the detection of Knee Osteoarthritis

Knee OsteoArthritis (OA) is a prevalent chronic condition, affecting a significant proportion of the global population. Detecting knee OA is crucial as the degeneration of the knee joint is irreversible. In this paper, we introduce a semi-supervised multi-view framework and a 3D CNN model for detecting knee OA using 3D Magnetic Resonance Imaging (MRI) scans. We introduce a semi-supervised learning approach combining labeled and unlabeled data to improve the performance and generalizability of the proposed model. Experimental results show the efficacy of our proposed approach in detecting knee OA from 3D MRI scans using a large cohort of 4297 subjects. An ablation study was conducted to investigate the contributions of various components of the proposed model, providing insights into the optimal design of the model. Our results indicate the potential of the proposed approach to improve the accuracy and efficiency of OA diagnosis. The proposed framework reported an AUC of 93.20% for the detection of knee OA.

An Adaptive Early Stopping Technique for DenseNet169-Based Knee Osteoarthritis Detection Model

Knee osteoarthritis (OA) detection is an important area of research in health informatics that aims to improve the accuracy of diagnosing this debilitating condition. In this paper, we investigate the ability of DenseNet169, a deep convolutional neural network architecture, for knee osteoarthritis detection using X-ray images. We focus on the use of the DenseNet169 architecture and propose an adaptive early stopping technique that utilizes gradual cross-entropy loss estimation. The proposed approach allows for the efficient selection of the optimal number of training epochs, thus preventing overfitting. To achieve the goal of this study, the adaptive early stopping mechanism that observes the validation accuracy as a threshold was designed. Then, the gradual cross-entropy (GCE) loss estimation technique was developed and integrated to the epoch training mechanism. Both adaptive early stopping and GCE were incorporated into the DenseNet169 for the OA detection model. The performance of the model was measured using several metrics including accuracy, precision, and recall. The obtained results were compared with those obtained from the existing works. The comparison shows that the proposed model outperformed the existing solutions in terms of accuracy, precision, recall, and loss performance, which indicates that the adaptive early stopping coupled with GCE improved the ability of DenseNet169 to accurately detect knee OA.