Knee osteoarthritis(OA)is a common disease that impairs knee function and causes pain.Currently,studies on the detection of knee OA mainly focus on X-ray images,but X-ray images are insensitive to the changes in knee ...Knee osteoarthritis(OA)is a common disease that impairs knee function and causes pain.Currently,studies on the detection of knee OA mainly focus on X-ray images,but X-ray images are insensitive to the changes in knee OA in the early stage.Since magnetic resonance(MR)imaging can observe the early features of knee OA,the knee OA detection algorithm based on MR image is innovatively proposed to judge whether knee OA is suffered.Firstly,the knee MR images are preprocessed before training,including a region of interest clipping,slice selection,and data augmentation.Then the data set was divided by patient-level and the knee OA was classified by the deep transfer learning method based on the DenseNet201 model.The method divides the training process into two stages.The first stage freezes all the base layers and only trains the weights of the embedding neural networks.The second stage unfreezes part of the base layers and trains the unfrozen base layers and the weights of the embedding neural network.In this step,we design a block-by-block fine-tuning strategy for training based on the dense blocks,which improves detection accuracy.We have conducted training experiments with different depth modules,and the experimental results show that gradually adding more dense blocks in the fine-tuning can make the model obtain better detection performance than only training the embedded neural network layer.We achieve an accuracy of 0.921,a sensitivity of 0.960,a precision of 0.885,a specificity of 0.891,an F1-Score of 0.912,and an MCC of 0.836.The comparative experimental results on the OAI-ZIB dataset show that the proposed method outperforms the other detection methods with the accuracy of 92.1%.展开更多
Magnetic resonance imaging(MRI) has allowed a comprehensive evaluation of articular disease, increasing the detection of early cartilage involvement, bone erosions, and edema in soft tissue and bone marrow compared to...Magnetic resonance imaging(MRI) has allowed a comprehensive evaluation of articular disease, increasing the detection of early cartilage involvement, bone erosions, and edema in soft tissue and bone marrow compared to other imaging techniques. In the era of functional imaging, new advanced MRI sequences are being successfully applied for articular evaluation in cases of inflammatory, infectious, and degenerative arthropathies. Diffusion weighted imaging, new fat suppression techniques such as DIXON, dynamic contrast enhanced-MRI, and specific T2 mapping cartilage sequences allow a better understanding of the physiopathological processes that underlie these different arthropathies. They provide valuable quantitative information that aids in their differentiation and can be used as potential biomarkers of articular disease course and treatment response.展开更多
AIM To investigate whether normal thickness cartilage in osteoarthritic knees demonstrate depletion of proteoglycan or collagen content compared to healthy knees.METHODS Magnetic resonance(MR) images were acquired fro...AIM To investigate whether normal thickness cartilage in osteoarthritic knees demonstrate depletion of proteoglycan or collagen content compared to healthy knees.METHODS Magnetic resonance(MR) images were acquired from5 subjects scheduled for total knee arthroplasty(TKA)(mean age 70 years) and 20 young healthy control subjects without knee pain(mean age 28.9 years). MR images of T1ρ mapping, T2 mapping, and fat suppressed proton-density weighted sequences were obtained.Following TKA each condyle was divided into 4 parts(distal medial, posterior medial, distal lateral, posterior lateral) for cartilage analysis. Twenty specimens(bone and cartilage blocks) were examined. For each joint,the degree and extent of cartilage destruction was determined using the Osteoarthritis Research Society International cartilage histopathology assessment system.In magnetic resonance imaging(MRI) analysis, 2 readers performed cartilage segmentation for T1ρ/T2 values and cartilage thickness measurement.RESULTS Eleven areas in MRI including normal or near normal cartilage thickness were selected. The corresponding histopathological sections demonstrated mild to moderate osteoarthritis(OA). There was no significant difference in cartilage thickness in MRI between control and advanced OA samples [medial distal condyle, P = 0.461;medial posterior condyle(MPC), P = 0.352; lateral distal condyle, P = 0.654; lateral posterior condyle, P = 0.550],suggesting arthritic specimens were morphologically similar to normal or early staged degenerative cartilage.Cartilage T2 and T1ρ values from the MPC were significantly higher among the patients with advanced OA(P= 0.043). For remaining condylar samples there was no statistical difference in T2 and T1ρ values between cases and controls but there was a trend towards higher values in advanced OA patients. CONCLUSION Though cartilage is morphologically normal or near normal, degenerative changes exist in advanced OA patients. These changes can be detected with T2 and T1ρ MRI techniques.展开更多
X-Ray knee imaging is widely used to detect knee osteoarthritis due to ease of availability and lesser cost.However,the manual categorization of knee joint disorders is time-consuming,requires an expert person,and is ...X-Ray knee imaging is widely used to detect knee osteoarthritis due to ease of availability and lesser cost.However,the manual categorization of knee joint disorders is time-consuming,requires an expert person,and is costly.This article proposes a new approach to classifying knee osteoarthritis using deep learning and a whale optimization algorithm.Two pre-trained deep learning models(Efficientnet-b0 and Densenet201)have been employed for the training and feature extraction.Deep transfer learning with fixed hyperparameter values has been employed to train both selected models on the knee X-Ray images.In the next step,fusion is performed using a canonical correlation approach and obtained a feature vector that has more information than the original feature vector.After that,an improved whale optimization algorithm is developed for dimensionality reduction.The selected features are finally passed to the machine learning algorithms such as Fine-Tuned support vector machine(SVM)and neural networks for classification purposes.The experiments of the proposed framework have been conducted on the publicly available dataset and obtained the maximum accuracy of 90.1%.Also,the system is explained using Explainable Artificial Intelligence(XAI)technique called occlusion,and results are compared with recent research.Based on the results compared with recent techniques,it is shown that the proposed method’s accuracy significantly improved.展开更多
基金The authors extend their appreciation to the Jilin Provincial Natural Science Foundation for funding this research work through Project Number(20220101128JC).
文摘Knee osteoarthritis(OA)is a common disease that impairs knee function and causes pain.Currently,studies on the detection of knee OA mainly focus on X-ray images,but X-ray images are insensitive to the changes in knee OA in the early stage.Since magnetic resonance(MR)imaging can observe the early features of knee OA,the knee OA detection algorithm based on MR image is innovatively proposed to judge whether knee OA is suffered.Firstly,the knee MR images are preprocessed before training,including a region of interest clipping,slice selection,and data augmentation.Then the data set was divided by patient-level and the knee OA was classified by the deep transfer learning method based on the DenseNet201 model.The method divides the training process into two stages.The first stage freezes all the base layers and only trains the weights of the embedding neural networks.The second stage unfreezes part of the base layers and trains the unfrozen base layers and the weights of the embedding neural network.In this step,we design a block-by-block fine-tuning strategy for training based on the dense blocks,which improves detection accuracy.We have conducted training experiments with different depth modules,and the experimental results show that gradually adding more dense blocks in the fine-tuning can make the model obtain better detection performance than only training the embedded neural network layer.We achieve an accuracy of 0.921,a sensitivity of 0.960,a precision of 0.885,a specificity of 0.891,an F1-Score of 0.912,and an MCC of 0.836.The comparative experimental results on the OAI-ZIB dataset show that the proposed method outperforms the other detection methods with the accuracy of 92.1%.
文摘Magnetic resonance imaging(MRI) has allowed a comprehensive evaluation of articular disease, increasing the detection of early cartilage involvement, bone erosions, and edema in soft tissue and bone marrow compared to other imaging techniques. In the era of functional imaging, new advanced MRI sequences are being successfully applied for articular evaluation in cases of inflammatory, infectious, and degenerative arthropathies. Diffusion weighted imaging, new fat suppression techniques such as DIXON, dynamic contrast enhanced-MRI, and specific T2 mapping cartilage sequences allow a better understanding of the physiopathological processes that underlie these different arthropathies. They provide valuable quantitative information that aids in their differentiation and can be used as potential biomarkers of articular disease course and treatment response.
基金Supported by The National Center for Research Resources and the National Center for Advancing Translational Sciences,National Institutes of Health,No.UL1 TR000153
文摘AIM To investigate whether normal thickness cartilage in osteoarthritic knees demonstrate depletion of proteoglycan or collagen content compared to healthy knees.METHODS Magnetic resonance(MR) images were acquired from5 subjects scheduled for total knee arthroplasty(TKA)(mean age 70 years) and 20 young healthy control subjects without knee pain(mean age 28.9 years). MR images of T1ρ mapping, T2 mapping, and fat suppressed proton-density weighted sequences were obtained.Following TKA each condyle was divided into 4 parts(distal medial, posterior medial, distal lateral, posterior lateral) for cartilage analysis. Twenty specimens(bone and cartilage blocks) were examined. For each joint,the degree and extent of cartilage destruction was determined using the Osteoarthritis Research Society International cartilage histopathology assessment system.In magnetic resonance imaging(MRI) analysis, 2 readers performed cartilage segmentation for T1ρ/T2 values and cartilage thickness measurement.RESULTS Eleven areas in MRI including normal or near normal cartilage thickness were selected. The corresponding histopathological sections demonstrated mild to moderate osteoarthritis(OA). There was no significant difference in cartilage thickness in MRI between control and advanced OA samples [medial distal condyle, P = 0.461;medial posterior condyle(MPC), P = 0.352; lateral distal condyle, P = 0.654; lateral posterior condyle, P = 0.550],suggesting arthritic specimens were morphologically similar to normal or early staged degenerative cartilage.Cartilage T2 and T1ρ values from the MPC were significantly higher among the patients with advanced OA(P= 0.043). For remaining condylar samples there was no statistical difference in T2 and T1ρ values between cases and controls but there was a trend towards higher values in advanced OA patients. CONCLUSION Though cartilage is morphologically normal or near normal, degenerative changes exist in advanced OA patients. These changes can be detected with T2 and T1ρ MRI techniques.
基金supported by“Human Resources Program in Energy Technology”of the Korea Institute of Energy Technology Evaluation and Planning (KETEP),granted financial resources from the Ministry of Trade,Industry&Energy,Republic of Korea.(No.20204010600090).
文摘X-Ray knee imaging is widely used to detect knee osteoarthritis due to ease of availability and lesser cost.However,the manual categorization of knee joint disorders is time-consuming,requires an expert person,and is costly.This article proposes a new approach to classifying knee osteoarthritis using deep learning and a whale optimization algorithm.Two pre-trained deep learning models(Efficientnet-b0 and Densenet201)have been employed for the training and feature extraction.Deep transfer learning with fixed hyperparameter values has been employed to train both selected models on the knee X-Ray images.In the next step,fusion is performed using a canonical correlation approach and obtained a feature vector that has more information than the original feature vector.After that,an improved whale optimization algorithm is developed for dimensionality reduction.The selected features are finally passed to the machine learning algorithms such as Fine-Tuned support vector machine(SVM)and neural networks for classification purposes.The experiments of the proposed framework have been conducted on the publicly available dataset and obtained the maximum accuracy of 90.1%.Also,the system is explained using Explainable Artificial Intelligence(XAI)technique called occlusion,and results are compared with recent research.Based on the results compared with recent techniques,it is shown that the proposed method’s accuracy significantly improved.
