Search

Surface defect detection plays an essential role in industry, and it is challenging due to the following problems: 1) the similarity between defect and nondefect texture is very high, which eventually leads to recognition or classification errors and 2) the size of defects is tiny, which are much more difficult to be detected than larger ones. To address such problems, this article proposes an adaptive image segmentation network (AIS-Net) for pixelwise segmentation of surface defects. It consists of three main parts: multishuffle-block dilated convolution (MSDC), dual attention context guidance (DACG), and adaptive category prediction (ACP) modules, where MSDC is designed to merge the multiscale defect features for avoiding the loss of tiny defect feature caused by model depth, DACG is designed to capture more contextual information from the defect feature map for locating defect regions and obtaining clear segmentation boundaries, and ACP is used to make classification and regression for predicting defect categories. Experimental results show that the proposed AIS-Net is superior to the state-of-the-art approaches on four actual surface defect datasets (NEU-DET: 98.38% ± 0.03%, DAGM: 99.25% ± 0.02%, Magnetic-tile: 98.73% ± 0.13%, and MVTec: 99.72% ± 0.02%).

The sparse collaborative tracking (SCT) method has been developed for object tracking recently, and it is very efficient and robust to various occlusions. In SCT, sparse representation (SR) plays an essential role because it needs to perform several manipulations of sparse matrix representation (SMR) or nonnegative SMR in each iteration. So one of the most challenging problems in SCT is how to efficiently solve the SMR. However, existing SR algorithms are solely developed for the vectors-based SR. They partition SMR into a set of vector-based SR problems and solve them in the level-2 BLAS (Basic Linear Algebra Subprograms) manner, i.e., matrix-vector operations, which is computationally much less efficient than the direct level-3 BLAS (direct matrix-matrix operations). To solve this problem, by extending the standard SR algorithm from the vector version to the matrix for SMR and nonnegative SMR, BLAS3-based Sparse Learning (BLAS3-SpaL) is first developed, and then the corresponding BLAS3-SpaL-based SCT method (FastSCT-BLAS3SpaL) is further developed for fast robust-object-tracking in this paper. The experiments verified that it achieves robust object tracking by reducing accumulation errors and speeds up tracking with more than double speed.

Accurate segmentation of 3D dental models derived from intra-oral scanners (IOS) is one of the key steps in many digital dental applications such as orthodontics and implants. However, it is difficult to accurately segment individual teeth and gums in 3D dental models due to the following problems: 1) the shape and appearance of adjacent teeth are very similar, which is easy to be misidentified; 2) the boundary between teeth and gums is often indistinct, especially in orthodontic patients with abnormalities such as missing and crowded teeth. To solve such problems, a Dual-Branch Geometric Attention Network (DBGANet) for 3D tooth segmentation is proposed, which can capture tooth geometric structure and detailed boundary information from multi-view geometric features encoded by 3D coordinates and normal vectors. The framework contains two branches, i.e., C-branch and N-branch. First, centroid-guided separable attention is designed in the C-branch to learn global context information by modeling the spatial dependencies of tooth point clouds, which can capture the overall geometric structure of teeth to better distinguish adjacent teeth with similar appearance. Then, Gaussian neighbor attention is designed in the N-branch to encode normal vectors to highlight detailed differences between geometric features at different points, which helps to refine the boundaries of teeth and gingiva for more accurate and smooth tooth segmentation. Extensive experiments on the real-patient datasets of 3D dental models demonstrate that the proposed DBGANet significantly outperforms state-of-the-art methods.

The fetal electrocardiogram (FECG) is of great significance for fetal monitoring during peripartum and intrapartum. However, it is difficult to extract FECG signals from the abdominal signal (ADS) due to the following issues: 1) FECG signals are always corrupted by noise and 2) the FECG signal is often masked by the high-amplitude maternal electrocardiogram (MECG). To address such problems, a correlation-aware attention CycleGAN (CAA-CycleGAN) is proposed for FECG extraction, where the autocorrelation attention encoder (ACAE) module, which can capture waveform details of FECG signals by modeling its autocorrelation in the current convolution layer, is first devised to extract FECG signals corrupted by noise; then, the cross-correlation attention residual (CCAR) module, which can enhance the FECG components by learning its cross-correlation between adjacent convolutional layers, is developed to discriminate FECG signals from MECG signals; finally, the dual-cross-correlation attention decoder (DCCAD) module, which can extract waveform features of FECG signals by exploring its dual-cross-correlation in different-level convolutional layers, is designed to extract FECG signals masked by MECG signals. Experiments demonstrate that the proposed CAA-CycleGAN can achieve excellent performance with the mean square error (MSE) of 0.082, 0.024, and 0.032 on the FECGSYNDB, ADFECGDB, and B2 LABOUR datasets, respectively, which is more accurate than the state-of-the-art methods. The project is available at https://github.com/langdecc511/ CAA-CycleGAN.

AbstractAimsTo assess the prevalence, health care resource utilization (HCRU), and economic burden of disease among Medicare beneficiaries with a principal diagnosis of osteoarthritis (OA) of the knee.Materials and methodsPatients with a principal diagnosis of knee OA were identified from the 5% noninstitutional sample file within 2009 and 2014 Medicare fee-for-service Limited Data Sets. A complete medical benefit record for each individual was generated by linking patient data across corresponding institutional claims from inpatient, outpatient, skilled nursing facility, and home health care services. The study revealed the prevalence and HCRU among Medicare knee OA patients, as well as the patient-level burden of disease by comparing HCRU and costs between knee OA patients and matched control patients.ResultsThe prevalence of principal diagnosis of knee OA among Medicare beneficiaries increased from 5.9% in 2009 to 6.2% in 2014. Total disease-related claims for the knee OA population was approximately 8 million in 2009 and 9 million in 2014. The average Medicare reimbursement per claim was $12,085 in the inpatient setting, $5,563 in skilled nursing facilities, $2,742 in home health care, $264 in the outpatient setting and $147 in noninstitutional office visits in 2014. Overall, the average total expense per knee OA patient in 2014 was $15,558, an increase of $5,364 compared to the matched control patient.ConclusionsMany Medicare beneficiaries received care for knee OA, and these patients had significantly greater HCRU than those with the absence of knee OA, totaling over $34 billion in healthcare expenditures in 2014.

Introduction

Background:Acute lymphoblastic leukemia/lymphoblastic lymphoma (ALL/LBL)are rare aggressive hematologic malignancies. Children with ALL/LBL have an overall favorable prognosis; however, adult patients (pts) have a poorer outcome. As a result, pediatric or pediatric-inspired regimens with asparaginase (ASP) have been used in adolescents and young adult (AYA) pts with ALL/LBL with promising results. Unfortunately, there are no prospective randomized studies comparing this approach with hyper-CVAD, a commonly used adult regimen not containing ASP. A meta-analysis was conducted to assess the efficacy of pediatric-inspired ASP-containing regimens compared with hyper-CVAD in treating ALL/LBL in AYA and adult pts.

AbstractAims:To estimate the long-term budget impact of expanding Medicare coverage of anti-obesity interventions among adults aged 65 and older in the US.Materials and methods:This study analyzed a representative sample of Medicare beneficiaries from the combined 2008–2016 National Health and Nutrition Examination Surveys. Population characteristics, cost and effectiveness of anti-obesity interventions, and the sustainability of weight loss in real-life were modeled to project the budgetary impact on gross Medicare outlay over 10 years. Hypothetical scenarios of 50% and 67% increases in intervention participation above base case were used to model moderate and extensive Medicare coverage expansion of intensive behavior therapy and pharmacotherapy.Results:For each Medicare beneficiary receiving anti-obesity treatment, we estimate Medicare savings of $6,842 and $7,155 over 10 years under moderate and extensive coverage utilization assumptions, respectively. The average cost of intervention is $1,798 and $1,886 per treated participant. Taking the entire Medicare population (treated and untreated) into consideration, the estimated 10-year budget savings per beneficiary are $308 and $339 under moderate and extensive assumptions, respectively. Sensitivity analysis of drug adherence rate and weight-loss efficacy indicated a potential variation of budget savings within 7% and 22% of the base case, respectively. Most of the projected cost savings come from lower utilization of ambulatory services and prescription drugs.Limitations:Due to the scarcity of studies on the efficacy of pharmacotherapy among older adults with obesity, the simulated weight loss and long-term maintenance effects were derived from clinical trial outcomes, in which older adults were mostly excluded from participation. The model did not include potential side-effects from anti-obesity medications and associated costs.Conclusions:This analysis suggests that expanding coverage of anti-obesity interventions to eligible individuals could generate $20–$23 billion budgetary savings to Medicare over 10 years.

AbstractBackground:There is a critical need to focus limited resources on sub-groups of patients with obesity where we expect the largest return on investment. This paper identifies patient sub-groups where an investment may result in larger positive economic and health outcomes.Methods:The baseline population with obesity was derived from a public survey database and divided into sub-populations defined by demographics and disease status. In 2016, a validated model was used to simulate the incidence of diabetes, absenteeism, and direct medical cost in five care settings. Research findings were derived from the difference in population outcomes with and without weight loss over 15 years. Modeled weight loss scenarios included initial 5% or 12% reduction in body mass index followed by a gradual weight regain. Additional simulations were conducted to show alternative outcomes from different time courses and maintenance scenarios.Results:Univariate analyses showed that age 45–64, pre-diabetes, female, or obesity class III are independently predictive of larger savings. After considering the correlation between these factors, multivariate analyses projected young females with obesity class I as the optimal sub-group to control obesity-related medical expenditures. In contrast, the population aged 20–35 with obesity class III will yield the best health outcomes. Also, the sub-group aged 45–54 with obesity class I will produce the biggest productivity improvement. Each additional year of weight loss maintained showed increased financial benefits.Conclusions:This paper studied the heterogeneity between many sub-populations affected by obesity and recommended different priorities for decision-makers in economic, productivity, and health realms.

AbstractBackground: Multiple sclerosis (MS) causes significant disability and diminished quality-of-life. Delayed-release dimethyl fumarate (DMF; also known as gastro-resistant DMF) is a new oral treatment for relapsing-remitting MS (RRMS) approved in the US, Australia, Canada, and Europe. Objectives: A cost-effectiveness model was developed to compare the health economic impact of DMF against other disease-modifying therapies (DMTs) as first-line RRMS treatment from a Canadian Ministry of Health perspective. Methods: A Markov cohort model was developed to simulate patients’ progression through health states based on the Kurtzke Expanded Disability Status Scale (EDSS) over a life-time horizon. Patients entered the model based on a distribution of baseline EDSS scores, from which they could progress to higher or regress to lower EDSS state, or remain in the same state. Relapses could occur at any EDSS score. Results from a mixed-treatment comparison were used to inform model inputs for disease progression and relapse rates per treatment. Costs included direct medical costs stratified by EDSS score. Utilities were accrued based on time spent in each EDSS state. Results: Compared with glatiramer acetate, DMF yielded 0.528 incremental quality-adjusted life-years (QALYs) at an incremental cost of $23 338 Canadian dollars (CAD), resulting in an incremental cost-effectiveness ratio (ICER) of CAD $44 118/QALY. The ICER for DMF compared with Rebif 44 mcg was CAD $10 672. Results were consistent across a wide range of one-way and probabilistic sensitivity analyses. Conclusions: Based on traditional cost-effectiveness thresholds in Canada (CAD $50 000–60 000), DMF can be considered a cost-effective option compared to other first-line DMTs.