Knee Osteoarthritis(KOA)is a degenerative knee joint disease caused by‘wear and tear’of ligaments between the femur and tibial bones.Clinically,KOA is classified into four grades ranging from 1 to 4 based on the deg...Knee Osteoarthritis(KOA)is a degenerative knee joint disease caused by‘wear and tear’of ligaments between the femur and tibial bones.Clinically,KOA is classified into four grades ranging from 1 to 4 based on the degradation of the ligament in between these two bones and causes suffering from impaired movement.Identifying this space between bones through the anterior view of a knee X-ray image is solely subjective and challenging.Automatic classification of this process helps in the selection of suitable treatment processes and customized knee implants.In this research,a new automatic classification of KOA images based on unsupervised local center of mass(LCM)segmentation method and deep Siamese Convolutional Neural Network(CNN)is presented.First-order statistics and the GLCM matrix are used to extract KOA anatomical Features from segmented images.The network is trained on our clinical data with 75 iterations with automaticweight updates to improve its validation accuracy.The assessment performed on the LCM segmented KOA images shows that our network can efficiently detect knee osteoarthritis,achieving about 93.2%accuracy along with multi-class classification accuracy of 72.01%and quadratic weighted Kappa of 0.86.展开更多
The authors consider a compound Cox model of insurance risk with the additional economic assumption of a positive interest rate. As the authors note a duality result relating a compound Cox model of insurance risk wit...The authors consider a compound Cox model of insurance risk with the additional economic assumption of a positive interest rate. As the authors note a duality result relating a compound Cox model of insurance risk with a positive interest rate and a double shot noise process, the authors analyze a double shot noise process systematically for its theoretical distributional properties, based on the piecewise deterministic Markov process theory, and the martingale methodology. The authors also obtain the moments of aggregate accumulated/discounted claims where the claim arrival process follows a Cox process with shot noise intensity. Removing the parameters in a double shot noise process gradually, the authors show that it becomes a compound Cox process with shot noise intensity, a single shot noise process and a compound Poisson process. Numerical comparisons are shown between the moments （i.e. means and variances） of a compound Poisson model and their counterparts of a compound Cox model with/without considering a positive interest rate. For that purpose, the authors assume that claim sizes and primary event sizes follow an exponential distribution, respectively.展开更多
基金The authors extend their appreciation to the Deputyship of Research and Innovation,Ministry of Education in Saudi Arabia for funding this research work through the Project Number IFP-2020-42.
文摘Knee Osteoarthritis(KOA)is a degenerative knee joint disease caused by‘wear and tear’of ligaments between the femur and tibial bones.Clinically,KOA is classified into four grades ranging from 1 to 4 based on the degradation of the ligament in between these two bones and causes suffering from impaired movement.Identifying this space between bones through the anterior view of a knee X-ray image is solely subjective and challenging.Automatic classification of this process helps in the selection of suitable treatment processes and customized knee implants.In this research,a new automatic classification of KOA images based on unsupervised local center of mass(LCM)segmentation method and deep Siamese Convolutional Neural Network(CNN)is presented.First-order statistics and the GLCM matrix are used to extract KOA anatomical Features from segmented images.The network is trained on our clinical data with 75 iterations with automaticweight updates to improve its validation accuracy.The assessment performed on the LCM segmented KOA images shows that our network can efficiently detect knee osteoarthritis,achieving about 93.2%accuracy along with multi-class classification accuracy of 72.01%and quadratic weighted Kappa of 0.86.
文摘The authors consider a compound Cox model of insurance risk with the additional economic assumption of a positive interest rate. As the authors note a duality result relating a compound Cox model of insurance risk with a positive interest rate and a double shot noise process, the authors analyze a double shot noise process systematically for its theoretical distributional properties, based on the piecewise deterministic Markov process theory, and the martingale methodology. The authors also obtain the moments of aggregate accumulated/discounted claims where the claim arrival process follows a Cox process with shot noise intensity. Removing the parameters in a double shot noise process gradually, the authors show that it becomes a compound Cox process with shot noise intensity, a single shot noise process and a compound Poisson process. Numerical comparisons are shown between the moments （i.e. means and variances） of a compound Poisson model and their counterparts of a compound Cox model with/without considering a positive interest rate. For that purpose, the authors assume that claim sizes and primary event sizes follow an exponential distribution, respectively.
