Abstract-This paper proposes a new approach to automatically quantify the severity of knee osteoarthritis (OA) from radiographs using deep convolutional neural networks (CNN). Clinically, knee OA severity is assessed using Kellgren & Lawrence (KL) grades, a five point scale. Previous work on automatically predicting KL grades from radiograph images were based on training shallow classifiers using a variety of hand engineered features. We demonstrate that classification accuracy can be significantly improved using deep convolutional neural network models pre-trained on ImageNet and fine-tuned on knee OA images. Furthermore, we argue that it is more appropriate to assess the accuracy of automatic knee OA severity predictions using a continuous distance-based evaluation metric like mean squared error than it is to use classification accuracy. This leads to the formulation of the prediction of KL grades as a regression problem and further improves accuracy. Results on a dataset of X-ray images and KL grades from the Osteoarthritis Initiative (OAI) show a sizable improvement over the current state-of-the-art.

Abstract. This paper introduces a new approach to automatically quantify the severity of knee OA using X-ray images. Automatically quantifying knee OA severity involves two steps: first, automatically localizing the knee joints; next, classifying the localized knee joint images. We introduce a new approach to automatically detect the knee joints using a fully convolutional neural network (FCN). We train convolutional neural networks (CNN) from scratch to automatically quantify the knee OA severity optimizing a weighted ratio of two loss functions: categorical cross-entropy and mean-squared loss. This joint training further improves the overall quantification of knee OA severity, with the added benefit of naturally producing simultaneous multi-class classification and regression outputs. Two public datasets are used to evaluate our approach, the Osteoarthritis Initiative (OAI) and the Multicenter Osteoarthritis Study (MOST), with extremely promising results that outperform existing approaches.

BackgroundLow back pain is one of the most prevalent musculoskeletal conditions in the world. Many exercise treatment options exist but few interventions have utilised free-weight resistance training. To investigate the effects of a free-weight-based resistance training intervention on pain and lumbar fat infiltration in those with chronic low back pain.MethodsThirty participants entered the study, 11 females (age=39.6±12.4 years, height=164 cm±5.3 cm, body mass=70.9±8.2 kg,) and 19 males (age=39.7±9.7 years, height=179±5.9 cm, body mass=86.6±15.9 kg). A 16-week, progressive, free-weight-based resistance training intervention was used. Participants completed three training sessions per week. Participants completed a Visual Analogue Pain Scale, Oswestry Disability Index and Euro-Qol V2 quality of life measure at baseline and every 4 weeks throughout the study. Three-dimensional kinematic and kinetic measures were used for biomechanical analysis of a bodyweight squat movement. Maximum strength was measured using an isometric mid-thigh pull, and lumbar paraspinal endurance was measured using a Biering-Sorensen test. Lumbar paraspinal fat infiltration was measured preintervention and postintervention using MRIs.ResultsPostintervention pain, disability and quality of life were all significantly improved. In addition, there was a significant reduction in fat infiltration at the L3L4 and L4L5 levels and increase in lumbar extension time to exhaustion of 18%.ConclusionsA free-weight-based resistance training intervention can be successfully utilised to improve pain, disability and quality of life in those with low back pain.

Knee osteoarthritis (KOA) is a disease that impairs knee function and causes pain. A radiologist reviews knee X-ray images and grades the severity level of the impairments according to the Kellgren and Lawrence grading scheme; a five-point ordinal scale (0–4). In this study, we used Elastic Net (EN) and Random Forests (RF) to build predictive models using patient assessment data (i.e. signs and symptoms of both knees and medication use) and a convolution neural network (CNN) trained using X-ray images only. Linear mixed effect models (LMM) were used to model the within subject correlation between the two knees. The root mean squared error for the CNN, EN, and RF models was 0.77, 0.97 and 0.94 respectively. The LMM shows similar overall prediction accuracy as the EN regression but correctly accounted for the hierarchical structure of the data resulting in more reliable inference. Useful explanatory variables were identified that could be used for patient monitoring before X-ray imaging. Our analyses suggest that the models trained for predicting the KOA severity levels achieve comparable results when modeling X-ray images and patient data. The subjectivity in the KL grade is still a primary concern.

No abstract

Abstract. Modern shared memory multiprocessor systems commonly have non-uniform memory access (NUMA) with asymmetric memory bandwidth and latency characteristics. Operating systems now provide application programmer interfaces allowing the user to perform specific thread and memory placement. To date, however, there have been relatively few detailed assessments of the importance of memory/thread placement for complex applications. This paper outlines a framework for performing memory and thread placement experiments on Solaris and Linux. Thread binding and location specific memory allocation and its verification is discussed and contrasted.Using the framework, the performance characteristics of serial versions of lmbench, Stream and various BLAS libraries (ATLAS, GOTO, ACML on Opteron/Linux and Sunperf on Opteron, UltraSPARC/Solaris) are measured on two different hardware platforms (UltraSPARC/FirePlane and Opteron/HyperTransport). A simple model describing performance as a function of memory distribution is proposed and assessed for both the Opteron and UltraSPARC.

No abstract

In this paper, a novel method of the dual-wavelength (laser-induced breakdown spectroscopy LIBS) technique using a single laser system is proposed and demonstrated. Experiments are performed using a pulsed Nd3+ : YAG laser with a pair of 355–1064 nm and also with 532–1064 nm. The shorter wavelength laser is used for ablation and plasma formation, and the fundamental wavelength (1064 nm) is used for plasma re-excitation. The proposed dual-wavelength LIBS technique is used for lunar simulant samples under different ambient pressure conditions. Various characteristic parameters, such as the emission line-intensity enhancement, plasma temperature, lifetime and plasma area, are studied. Experimental studies clearly showed the emission line-intensity enhancement up to a factor of 3. Emission lifetime showed a longer sustained emission with an increase of up to 33% for the dual-wavelength approach. A theoretical simulation based on the hydrodynamic equations is also performed for dual-wavelength ablation and re-excitation. The estimated plasma temperature and ablation plume-front velocity clearly showed an increase in dual wavelength, which is in agreement with the experimental results.