Fully Automatic Knee Joint Segmentation and Quantitative Analysis for Osteoarthritis from Magnetic Resonance (MR) Images Using a Deep Learning Model

Tang, Xiongfeng; Guo, De‐Ming; Liu, Aie; Wu, Dijia; Liu, Jianhua; Xu, Nannan; Qin, Yanguo

doi:10.12659/msm.936733

Cited by 14 publications

(13 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic recognition and segmentation of images through CNN have been applied to medicine, including the use of MRI images to recognize the knee meniscus and anterior cruciate ligament ( 11 , 12 ). Many scholars have also studied the segmentation of knee joint cartilage in CNN ( 13–15 ), which is also the direction of our study.…”

Section: Introductionmentioning

confidence: 94%

Automated measurement and grading of knee cartilage thickness: a deep learning-based approach

Guo,

Yan,

Qin

et al. 2024

Front. Med.

View full text Add to dashboard Cite

BackgroundKnee cartilage is the most crucial structure in the knee, and the reduction of cartilage thickness is a significant factor in the occurrence and development of osteoarthritis. Measuring cartilage thickness allows for a more accurate assessment of cartilage wear, but this process is relatively time-consuming. Our objectives encompass using various DL methods to segment knee cartilage from MRIs taken with different equipment and parameters, building a DL-based model for measuring and grading knee cartilage, and establishing a standardized database of knee cartilage thickness.MethodsIn this retrospective study, we selected a mixed knee MRI dataset consisting of 700 cases from four datasets with varying cartilage thickness. We employed four convolutional neural networks—UNet, UNet++, ResUNet, and TransUNet—to train and segment the mixed dataset, leveraging an extensive array of labeled data for effective supervised learning. Subsequently, we measured and graded the thickness of knee cartilage in 12 regions. Finally, a standard knee cartilage thickness dataset was established using 291 cases with ages ranging from 20 to 45 years and a Kellgren–Lawrence grading of 0.ResultsThe validation results of network segmentation showed that TransUNet performed the best in the mixed dataset, with an overall dice similarity coefficient of 0.813 and an Intersection over Union of 0.692. The model’s mean absolute percentage error for automatic measurement and grading after segmentation was 0.831. The experiment also yielded standard knee cartilage thickness, with an average thickness of 1.98 mm for the femoral cartilage and 2.14 mm for the tibial cartilage.ConclusionBy selecting the best knee cartilage segmentation network, we built a model with a stronger generalization ability to automatically segment, measure, and grade cartilage thickness. This model can assist surgeons in more accurately and efficiently diagnosing changes in patients’ cartilage thickness.

show abstract

Section: Introductionmentioning

confidence: 94%

Automated measurement and grading of knee cartilage thickness: a deep learning-based approach

Guo,

Yan,

Qin

et al. 2024

Front. Med.

View full text Add to dashboard Cite

show abstract

“… 98 Deep learning allows learning from raw data features without requiring feature extraction techniques. The developed systems used a dynamic abnormality detection and progression framework, 99 2D and 3D convolutional neural network (CNN) algorithms with/without U-Net and with/without an encoder and a decoder in combination with simplex deformable modelling 100 – 106 or low-rank tensor-reconstructed segmentation network. 107 The role of the decoder network is to map the low-resolution encoder feature maps to full input resolution feature maps for pixel-wise classification.…”

Section: Mri Assessments Enabling Visualization and Quantification Of...mentioning

confidence: 99%

Magnetic resonance imaging assessments for knee segmentation and their use in combination with machine/deep learning as predictors of early osteoarthritis diagnosis and prognosis

Martel‐Pelletier

Paiement

Pelletier

2023

Therapeutic Advances in Musculoskeletal

View full text Add to dashboard Cite

Knee osteoarthritis (OA) is a prevalent and disabling disease that can develop over decades. This disease is heterogeneous and involves structural changes in the whole joint, encompassing multiple tissue types. Detecting OA before the onset of irreversible changes is crucial for early management, and this could be achieved by allowing knee tissue visualization and quantifying their changes over time. Although some imaging modalities are available for knee structure assessment, magnetic resonance imaging (MRI) is preferred. This narrative review looks at existing literature, first on MRI-developed approaches for evaluating knee articular tissues, and second on prediction using machine/deep-learning-based methodologies and MRI as input or outcome for early OA diagnosis and prognosis. A substantial number of MRI methodologies have been developed to assess several knee tissues in a semi-quantitative and quantitative fashion using manual, semi-automated and fully automated systems. This dynamic field has grown substantially since the advent of machine/deep learning. Another active area is predictive modelling using machine/deep-learning methodologies enabling robust early OA diagnosis/prognosis. Moreover, incorporating MRI markers as input/outcome in such predictive models is important for a more accurate OA structural diagnosis/prognosis. The main limitation of their usage is the ability to move them in rheumatology practice. In conclusion, MRI knee tissue determination and quantification provide early indicators for individuals at high risk of developing this disease or for patient prognosis. Such assessment of knee tissues, combined with the development of models/tools from machine/deep learning using, in addition to other parameters, MRI markers for early diagnosis/prognosis, will maximize opportunities for individualized risk assessment for use in clinical practice permitting precision medicine. Future efforts should be made to integrate such prediction models into open access, allowing early disease management to prevent or delay the OA outcome.

show abstract

“…This approach has also shown to be sensitive to differences in change in studies focusing on early osteoarthritis without radiographic signs of osteoarthritis [9]. Quantitative analyses of joint for osteoarthritis are not limited to cartilage morphology and have been applied on other joint tissues such as meniscus, fat-pads and bone [9,[49][50][51][52].…”

Section: Quantitative Morphologic Mri Assessment Of Articular Cartilagementioning

confidence: 99%

Advances in osteoarthritis imaging

Chalian

Roemer

Guermazi

2022

Current Opinion in Rheumatology

View full text Add to dashboard Cite

Purpose of reviewImaging plays a pivotal role for diagnosis, follow-up and stratification of osteoarthritis patients in clinical trials and research. We aim to present an overview of currently available and emerging imaging techniques for osteoarthritis assessment and provide insight into relevant benefits and pitfalls of the different modalities. Recent findingsAlthough radiography is considered sufficient for a structural diagnosis of osteoarthritis and is commonly used to define eligibility of patients for participation in clinical trials, it has inherent limitations based on the projectional nature of the technique and inherent challenges regarding reproducibility in longitudinal assessment. MRI has changed our understanding of the disease from wear and tear of cartilage to a whole organ disorder. MRI assessment of structural changes of osteoarthritis includes semi-quantitative, quantitative and compositional evaluation. Ultrasound is helpful in evaluating the degree of synovitis and has value in the assessment particularly of the patella-femoral joint. Recent development of computed tomography technology including weight-bearing systems has led to broader application of this technology in a research context. Summary Advances in MRI technology have resulted in a significant improvement in understanding osteoarthritis as a multitissue disease Keywords cartilage, compositional MRI, osteoarthritis, radiography, ultrasound && ]. Application of advanced imaging methods in large epidemiologic studies such as the Osteoarthritis Initiative (OAI, https://nda.nih.gov/oai/) and the Multicenter Osteoarthritis Study (MOST, https://most.ucsf.edu/) have added to our understanding of the natural course of

show abstract

Fully Automatic Knee Joint Segmentation and Quantitative Analysis for Osteoarthritis from Magnetic Resonance (MR) Images Using a Deep Learning Model

Cited by 14 publications

References 33 publications

Automated measurement and grading of knee cartilage thickness: a deep learning-based approach

Automated measurement and grading of knee cartilage thickness: a deep learning-based approach

Magnetic resonance imaging assessments for knee segmentation and their use in combination with machine/deep learning as predictors of early osteoarthritis diagnosis and prognosis

Advances in osteoarthritis imaging

Contact Info

Product

Resources

About