Evaluation of artificial intelligence models for osteoarthritis of the knee using deep learning algorithms for orthopedic radiographs

Survival analysis on subchondral bone length for total knee replacement

OBJECTIVE

Use subchondral bone length (SBL), a new MRI-derived measure that reflects the extent of cartilage loss and bone flattening, to predict the risk of progression to total knee replacement (TKR).

METHODS

We employed baseline MRI data from the Osteoarthritis Initiative (OAI), focusing on 760 men and 1214 women with bone marrow lesions (BMLs) and joint space narrowing (JSN) scores, to predict the progression to TKR. To minimize bias from analyzing both knees of a participant, only the knee with a higher Kellgren-Lawrence (KL) grade was considered, given its greater potential need for TKR. We utilized the Kaplan-Meier survival curves and Cox proportional hazards models, incorporating raw and normalized values of SBL, JSN, and BML as predictors. The study included subgroup analyses for different demographics and clinical characteristics, using models for raw and normalized SBL (merged, femoral, tibial), BML (merged, femoral, tibial), and JSN (medial and lateral compartments). Model performance was evaluated using the time-dependent area under the curve (AUC), Brier score, and Concordance index to gauge accuracy, calibration, and discriminatory power. Knee joint and region-level analyses were conducted to determine the effectiveness of SBL, JSN, and BML in predicting TKR risk.

RESULTS

The SBL model, incorporating data from both the femur and tibia, demonstrated a predictive capacity for TKR that closely matched the performance of the BML score and the JSN grade. The Concordance index of the SBL model was 0.764, closely mirroring the BML's 0.759 and slightly below JSN's 0.788. The Brier score for the SBL model stood at 0.069, showing comparability with BML's 0.073 and a minor difference from JSN's 0.067. Regarding the AUC, the SBL model achieved 0.803, nearly identical to BML's 0.802 and slightly lower than JSN's 0.827.

CONCLUSION

SBL's capacity to predict the risk of progression to TKR highlights its potential as an effective imaging biomarker for knee osteoarthritis.

Machine learning and deep learning for the diagnosis and treatment of ankylosing spondylitis- a scoping review

Background and objectives

Machine Learning (ML) and Deep Learning (DL) are novel technologies that can facilitate early diagnosis of Ankylosing Spondylitis (AS) and predict better patient-specific treatments. We aim to provide the current update on their use at different stages of AS diagnosis and treatment, describe different types of techniques used, dataset descriptions, contributions and limitations of existing work and ed to identify gaps in current knowledge for future works.

Methods

We curated the data of this review from the PubMed database. We searched the full-text articles related to the use of ML/DL in the diagnosis and treatment of AS, for the period 2013-2023. Each article was manually scrutinized to be included or excluded for this review as per its relevance.

Results

This review revealed that ML/DL technology is useful to assist and promote early diagnosis through AS patient characteristic profile creation, and identification of new AS-related biomarkers. They can help in forecasting the progression of AS and predict treatment responses to aid patient-specific treatment planning. However, there was a lack of sufficient-sized datasets sourced from multi-centres containing different types of diagnostic parameters. Also, there is less research on ML/DL-based AS treatment as compared to ML/DL-based AS diagnosis.

Conclusion

ML/DL can facilitate an early diagnosis and patient-tailored treatment for effective handling of AS. Benefits are especially higher in places with a lack of diagnostic resources and human experts. The use of ML/DL-trained models for AS diagnosis and treatment can provide the necessary support to the otherwise overwhelming healthcare systems in a cost-effective and timely way.

Comprehensive Study on Scoring and Grading Systems for Predicting the Severity of Knee Osteoarthritis

Knee Osteoarthritis (KOA) is a degenerative joint ailment characterized by cartilage loss, which can be seen using imaging modalities and converted into imaging features. The older population is the most affected by knee OA, which affects 16% of people worldwide who are 15 years of age and older. Due to cartilage tissue degradation, primary knee OA develops in older people. In contrast, joint overuse or trauma in younger people can cause secondary knee OA. Early identification of knee OA, according to research, may be a successful management tactic for the condition. Scoring scales and grading systems are important tools for the management of knee osteoarthritis as they allow clinicians to measure the progression of the disease's severity and provide suggestions on suitable treatment at identified stages. The comprehensive study reviews various subjective and objective knee evaluation scoring systems that effectively score and grade the KOA based on where defects or changes in articular cartilage occur. Recent studies reveal that AI-based approaches, such as that of DenseNet, integrating the concept of deep learning for scoring and grading the KOA, outperform various state-of-the-art methods in order to predict the KOA at an early stage.

Stratifying knee osteoarthritis features through multitask deep hybrid learning: Data from the osteoarthritis initiative

BACKGROUND AND OBJECTIVE

Knee osteoarthritis (OA) is a debilitating musculoskeletal disorder that causes functional disability. Automatic knee OA diagnosis has great potential of enabling timely and early intervention, that can potentially reverse the degenerative process of knee OA. Yet, it is a tedious task, concerning the heterogeneity of the disorder. Most of the proposed techniques demonstrated single OA diagnostic task widely based on Kellgren Lawrence (KL) standard, a composite score of only a few imaging features (i.e. osteophytes, joint space narrowing and subchondral bone changes). However, only one key disease pattern was tackled. The KL standard fails to represent disease pattern of individual OA features, particularly osteophytes, joint-space narrowing, and pain intensity that play a fundamental role in OA manifestation. In this study, we aim to develop a multitask model using convolutional neural network (CNN) feature extractors and machine learning classifiers to detect nine important OA features: KL grade, knee osteophytes (both knee, medial fibular: OSFM, medial tibial: OSTM, lateral fibular: OSFL, and lateral tibial: OSTL), joint-space narrowing (medial: JSM, and lateral: JSL), and patient-reported pain intensity from plain radiography.

METHODS

We proposed a new feature extraction method by replacing fully-connected layer with global average pooling (GAP) layer. A comparative analysis was conducted to compare the efficacy of 16 different convolutional neural network (CNN) feature extractors and three machine learning classifiers.

RESULTS

Experimental results revealed the potential of CNN feature extractors in conducting multitask diagnosis. Optimal model consisted of VGG16-GAP feature extractor and KNN classifier. This model not only outperformed the other tested models, it also outperformed the state-of-art methods with higher balanced accuracy, higher Cohen's kappa, higher F1, and lower mean squared error (MSE) in seven OA features prediction.

CONCLUSIONS

The proposed model demonstrates pain prediction on plain radiographs, as well as eight OA-related bony features. Future work should focus on exploring additional potential radiological manifestations of OA and their relation to therapeutic interventions.

Automated patellar height assessment on high-resolution radiographs with a novel deep learning-based approach

BACKGROUND

Artificial intelligence and deep learning have shown promising results in medical imaging and interpreting radiographs. Moreover, medical community shows a gaining interest in automating routine diagnostics issues and orthopedic measurements.

AIM

To verify the accuracy of automated patellar height assessment using deep learning-based bone segmentation and detection approach on high resolution radiographs.

METHODS

218 Lateral knee radiographs were included in the analysis. 82 radiographs were utilized for training and 10 other radiographs for validation of a U-Net neural network to achieve required Dice score. 92 other radiographs were used for automatic (U-Net) and manual measurements of the patellar height, quantified by Caton-Deschamps (CD) and Blackburne-Peel (BP) indexes. The detection of required bones regions on high-resolution images was done using a You Only Look Once (YOLO) neural network. The agreement between manual and automatic measurements was calculated using the interclass correlation coefficient (ICC) and the standard error for single measurement (SEM). To check U-Net's generalization the segmentation accuracy on the test set was also calculated.

RESULTS

Proximal tibia and patella was segmented with accuracy 95.9% (Dice score) by U-Net neural network on lateral knee subimages automatically detected by the YOLO network (mean Average Precision mAP greater than 0.96). The mean values of CD and BP indexes calculated by orthopedic surgeons (R#1 and R#2) was 0.93 (± 0.19) and 0.89 (± 0.19) for CD and 0.80 (± 0.17) and 0.78 (± 0.17) for BP. Automatic measurements performed by our algorithm for CD and BP indexes were 0.92 (± 0.21) and 0.75 (± 0.19), respectively. Excellent agreement between the orthopedic surgeons’ measurements and results of the algorithm has been achieved (ICC > 0.75, SEM < 0.014).

CONCLUSION

Automatic patellar height assessment can be achieved on high-resolution radiographs with the required accuracy. Determining patellar end-points and the joint line-fitting to the proximal tibia joint surface allows for accurate CD and BP index calculations. The obtained results indicate that this approach can be valuable tool in a medical practice.

Osteo-NeT: An Automated System for Predicting Knee Osteoarthritis from X-ray Images Using Transfer-Learning-Based Neural Networks Approach

Knee osteoarthritis is a challenging problem affecting many adults around the world. There are currently no medications that cure knee osteoarthritis. The only way to control the progression of knee osteoarthritis is early detection. Currently, X-ray imaging is a central technique used for the prediction of osteoarthritis. However, the manual X-ray technique is prone to errors due to the lack of expertise of radiologists. Recent studies have described the use of automated systems based on machine learning for the effective prediction of osteoarthritis from X-ray images. However, most of these techniques still need to achieve higher predictive accuracy to detect osteoarthritis at an early stage. This paper suggests a method with higher predictive accuracy that can be employed in the real world for the early detection of knee osteoarthritis. In this paper, we suggest the use of transfer learning models based on sequential convolutional neural networks (CNNs), Visual Geometry Group 16 (VGG-16), and Residual Neural Network 50 (ResNet-50) for the early detection of osteoarthritis from knee X-ray images. In our analysis, we found that all the suggested models achieved a higher level of predictive accuracy, greater than 90%, in detecting osteoarthritis. However, the best-performing model was the pretrained VGG-16 model, which achieved a training accuracy of 99% and a testing accuracy of 92%.