Search

Significance: Secondary lymphedema is a debilitating disease caused by lymphatic dysfunction characterized by chronic swelling, dysregulated inflammation, disfigurement, and compromised wound heali...

SIGNIFICANCE: Lymphedema is a common disease that affects hundreds of millions of people worldwide with significant financial and social burdens. Despite increasing prevalence and associated morbidities, the mainstay treatment of lymphedema is largely palliative without an effective cure due to incomplete understanding of the disease. RECENT ADVANCES: Recent studies have described key histological and pathological processes that contribute to the progression of lymphedema, including lymphatic stasis, inflammation, adipose tissue deposition, and fibrosis. This review aims to highlight cellular and molecular mechanisms involved in each of these pathological processes. CRITICAL ISSUES: Despite recent advances in the understanding of the pathophysiology of lymphedema, cellular and molecular mechanisms underlying the disease remains elusive due to its complex nature. FUTURE DIRECTIONS: Additional research is needed to gain a better insight into the cellular and molecular mechanisms underlying the pathophysiology of lymphedema, which will guide the development of therapeutic strategies that target specific pathology of the disease.

Background & Aims The obesity epidemic has increased the risk of non-alcoholic fatty liver disease (NAFLD) in both the general and chronic hepatitis B (CHB) populations. Our study aims to determine the prevalence of NAFLD in CHB patients based on controlled attenuation parameter (CAP), and the epidemiological, clinical and virological factors associated with severe hepatic steatosis. Methods The Canadian Hepatitis B Network cohort was utilized to provide a cross-sectional description of demographics, comorbidities, antiviral treatment, and HBV tests. Liver fibrosis and steatosis were measured by transient elastography (TE) and CAP, respectively. Any grade and severe steatosis were defined as CAP >248 and >280 dB/m, respectively. Advanced liver fibrosis was defined as TE measurement > 10.7kPa. Results In 1178 CHB patients (median age 47.4, 57.7% males, 75.7% Asian, 13% African, 6.5% White, 86% HBeAg negative, median HBV DNA of 2.44 log10IU/mL, 42.7% receiving treatment), the prevalence of any grade and severe steatosis was 53% and 36%, respectively. In the multivariate analysis, obesity was a significant predictor for severe steatosis (aOR 5.046, 95% CI: 1.22-20.93). Severe steatosis was a determinant associated with viral load (aOR 0.385, 95% CI: 0.20-0.75, p Conclusion In this large multi-ethnic CHB population, hepatic steatosis is common. Severe steatosis is independently associated with higher fibrosis, but negatively with HBV DNA, regardless of antiviral therapy history.

The clinical and demographic characteristics that predict antiretroviral efficacy among patients co-infected with HIV and hepatitis B virus (HBV) remain poorly defined. We evaluated HIV virological suppression and rebound in a cohort of HIV-HBV co-infected patients initiated on antiretroviral therapy.A retrospective cohort analysis was performed with Canadian Observation Cohort Collaboration data. Cox proportional hazards models were used to determine the factors associated with time to virological suppression and time to virological rebound.HBV status was available for 2,419 participants. A total of 8% were HBV co-infected, of whom 95% achieved virological suppression. After virological suppression, 29% of HIV-HBV co-infected participants experienced HIV virological rebound. HBV co-infection itself did not predict virological suppression or rebound risk. The rate of virological suppression was lower among patients with a history of injection drug use or baseline CD4 cell counts of199 cells per cubic millimetre. Low baseline HIV RNA and men-who-have-sex-with-men status were significantly associated with a higher rate of virological suppression. Injection drug use and non-White race predicted viral rebound.HBV co-infected HIV patients achieve similar antiretroviral outcomes as those living with HIV mono-infection. Equitable treatment outcomes may be approached by targeting resources to key subpopulations living with HIV-HBV co-infection.Les caractéristiques cliniques et démographiques prédictives de l’efficacité antirétrovirale chez les patients co-infectés par le virus de l’immunodéficience humaine (VIH) et le virus de l’hépatite B (VHB) demeurent mal définies. Les chercheurs ont évalué la suppression et le rebond virologiques du VIH dans une cohorte de patients co-infectés par le VIH et le VHB chez qui on avait entrepris un traitement antirétroviral.Les chercheurs ont réalisé une analyse rétrospective de cohorte à l’aide des données de laLes chercheurs ont obtenu le statut de VHB de 2 419 participants. Au total, 8 % étaient co-infectés par le VHB, dont 95 % présentaient une suppression virologique. Après la suppression virologique, 29 % des participants co-infectés par le VIH et le VHB ont subi un rebond virologique du VIH. En elle-même, la co-infection par le VHB n’était pas prédictive de la suppression virologique ou du risque de rebond. Le taux de suppression virologique était plus faible chez les patients ayant des antécédents de consommation de drogues injectables ou une numération des cellules CD4 de référence de moins de 199 cellules par millimètre cube. Un ARN du VIH de référence bas et les hommes ayant des relations sexuelles avec des hommes étaient associés de manière significative avec un taux plus élevé de suppression virologique. La consommation de drogues injectables et les races non blanches étaient prédictives d’un rebond viral.Les patients atteints du VHB co-infectés par le VIH obtenaient des résultats antirétroviraux semblables à ceux qui étaient seulement infectés par le VIH. On peut anticiper des résultats cliniques équitables des traitements en ciblant les ressources vers les sous-populations atteintes d’une co-infection par le VIH et le VHB.

Background Skin cancer continues to be the most frequently diagnosed form of cancer in the U.S., with not only significant effects on health and well-being but also significant economic costs associated with treatment. A crucial step to the treatment and management of skin cancer is effective early detection with key screening approaches such as dermoscopy examinations, leading to stronger recovery prognoses. Motivated by the advances of deep learning and inspired by the open source initiatives in the research community, in this study we introduce Cancer-Net SCa, a suite of deep neural network designs tailored for the detection of skin cancer from dermoscopy images that is open source and available to the general public. To the best of the authors’ knowledge, Cancer-Net SCa comprises the first machine-driven design of deep neural network architectures tailored specifically for skin cancer detection, one of which leverages attention condensers for an efficient self-attention design. Results We investigate and audit the behaviour of Cancer-Net SCa in a responsible and transparent manner through explainability-driven performance validation. All the proposed designs achieved improved accuracy when compared to the ResNet-50 architecture while also achieving significantly reduced architectural and computational complexity. In addition, when evaluating the decision making process of the networks, it can be seen that diagnostically relevant critical factors are leveraged rather than irrelevant visual indicators and imaging artifacts. Conclusion The proposed Cancer-Net SCa designs achieve strong skin cancer detection performance on the International Skin Imaging Collaboration (ISIC) dataset, while providing a strong balance between computation and architectural efficiency and accuracy. While Cancer-Net SCa is not a production-ready screening solution, the hope is that the release of Cancer-Net SCa in open source, open access form will encourage researchers, clinicians, and citizen data scientists alike to leverage and build upon them.

We present a method to infer a dense depth map from a color image and associated sparse depth measurements. Our main contribution lies in the design of an annealing process for determining co-visibility (occlusions, disocclusions) and the degree of regularization to impose on the model. We show that regularization and co-visibility are related via the fitness (residual) of model to data and both can be unified into a single framework to improve the learning process. Our method is an adaptive weighting scheme that guides optimization by measuring the residual at each pixel location over each training step for (i) estimating a soft visibility mask and (ii) determining the amount of regularization. We demonstrate the effectiveness our method by applying it to several recent unsupervised depth completion methods and improving their performance on public benchmark datasets, without incurring additional trainable parameters or increase in inference time. Code available at: https://github.com/alexklwong/adaframe-depth-completion.

Background Despite the current highly effective therapies with direct-acting antiviral agents (DAAs), some patients with chronic hepatitis C virus (HCV) infection still do not achieve sustained virological response (SVR) and require retreatment. Sofosbuvir/velpatasvir/voxilaprevir (SVV) is recommended as the first-line retreatment option for most patients. The aim of this study was to evaluate the efficacy of SVV as salvage therapy after at least one course of DAA. Methods Data were collected on all HCV-infected patients who failed DAAs and were prescribed SVV from a prospective Canadian registry (CANUHC) including 17 sites across Canada. Factors associated with failure to achieve SVR with SVV therapy and the utility of RAS testing and ribavirin use were evaluated. Results A total of 128 patients received SVV after non-SVR with DAA treatment: 80% male, median age 57.5 (31–86), 44% cirrhotic, and 17 patients post liver transplant. First line regimens included: sofosbuvir/velpatasvir (27.3%), sofosbuvir/ledipasvir (26.5%), grazoprevir/elbasvir (12.5%), other (33.5%). Ribavirin was added to SVV in 26 patients due to past sofosbuvir/velpatasvir use (n = 8), complex resistance associated substitution profiles (n = 16) and/or cirrhosis (n = 9). Overall SVR rate was 96% (123/128). Of 35 patients who previously failed sofosbuvir/velpatasvir, 31 (88.5%) achieved SVR compared to 92 of 93 (99%) among those receiving any other regimen (P = .01). Conclusions Similar to reports from phase 3 clinical trials, SVV proved highly effective as salvage therapy for patients who failed a previous DAA therapy. Those who failed SVV had at least 2 of the following factors: genotype 3, presence of cirrhosis, past liver transplantation, past exposure to sofosbuvir/velpatasvir and/or complex resistance profiles.

Background: Lymphedema is a condition characterized by dysfunction of the lymphatic system resulting in chronic, progressive soft tissue edema that can negatively impact individuals' function, self-image, and quality of life. Understanding of the disease process has evolved significantly in the past two decades with advances in diagnostic modalities and surgical techniques revolutionizing prior treatment algorithms. Methods and Results: We reviewed our current approach at the University of Southern California to improving outcomes in lymphedema treatment. Given the complexity of this medical condition, patients are best served by a multidisciplinary approach. At our institution, this involves a collaborative effort between bench researchers, lymphatic therapists, medical physicians, and lymphedema surgeons. Basic science and translational research provide further understanding into the underlying mechanisms of lymphangiogenesis and the possibility for potential therapeutic interventions. Our surgical algorithms require patients to undergo a thorough diagnostic evaluation and consultation with certified lymphatic therapists prior to undergoing either physiologic or debulking operations. Patients are followed clinically following any interventions. Further community outreach and education is carried out in order to improve upon early diagnosis and symptom recognition. Conclusions: Optimizing lymphedema care requires a collaborative interplay between researchers, physicians, and therapists. Additionally, patient and provider education on early disease recognition and treatment options is an equally critical aspect of improving patient outcomes.

Why can’t neural networks (NN) forecast better? In the major super-forecasting competitions, NN have typically under-performed when compared to traditional statistical methods. When they have performed well, the underlying methods have been ensembles of NN and statistical methods. Forecasting stock markets, medical, infrastructure dynamics, social activity or pandemics each have their own challenges. In this study, we evaluate the strengths of a collection of methods for forecasting pandemics such as Covid-19 using NN, statistical methods as well as parameterized mechanistic models. Forecasts of epidemics can inform public health response and decision making, so accurate forecasting is crucial for general public notification, timing and spatial targeting of intervention. We show that NN typically under-perform in forecasting Covid-19 active cases which can be attributed to the lack of training data which is common for forecasts. Our test data consists of the top ten countries for active Covid-19 cases early in the pandemic and is represented as a Time Series (TS). We found that Statistical methods outperform NN for most cases. Albeit, NN are still good pattern finders and we suggest that there are perhaps more productive ways other than purely data driven models of using NN to help produce better forecasts.

A critical step for computer vision-driven hockey ice rink localization from broadcast video is the automatic segmentation of lines on the rink. While the leveraging of segmentation methods for sports field localization has been previously explored, the design of deep neural networks for segmenting ice rink lines has not been well studied. Furthermore, the exploration of efficient architecture designs is very important given the operational requirements of real-time sports analytics. Motivated by this, BenderNet and RingerNet, two highly efficient deep neural network architectures, have been designed specifically for ice rink line segmentation. Experiments on a dataset of annotated NHL broadcast video demonstrate high accuracy while maintaining high model efficiency, thus making the proposed methods well-suited for real-time ice hockey rink localization.

Multi-scale image decomposition (MID) is a fundamental task in computer vision and image processing that involves the transformation of an image into a hierarchical representation comprising of different levels of visual granularity from coarse structures to fine details. A well-engineered MID disentangles the image signal into meaningful components which can be used in a variety of applications such as image denoising, image compression, and object classification. Traditional MID approaches such as wavelet transforms tackle the problem through carefully designed basis functions under rigid decomposition structure assumptions. However, as the information distribution varies from one type of image content to another, rigid decomposition assumptions lead to inefficiently representation, i.e., some scales can contain little to no information. To address this issue, we present Deep Residual Transform (DRT), a data-driven MID strategy where the input signal is transformed into a hierarchy of non-linear representations at different scales, with each representation being independently learned as the representational residual of previous scales at a user-controlled detail level. As such, the proposed DRT progressively disentangles scale information from the original signal by sequentially learning residual representations. The decomposition flexibility of this approach allows for highly tailored representations cater to specific types of image content, and results in greater representational efficiency and compactness. In this study, we realize the proposed transform by leveraging a hierarchy of sequentially trained autoencoders. To explore the efficacy of the proposed DRT, we leverage two datasets comprising of very different types of image content: 1) CelebFaces and 2) Cityscapes. Experimental results show that the proposed DRT achieved highly efficient information decomposition on both datasets amid their very different visual granularity characteristics.

Due to shared modes of exposure, HIV-HBV co-infection is common worldwide. Increased knowledge of the demographic and clinical characteristics of the co-infected population will allow us to optimize our approach to management of both infections in clinical practice. The Canadian Hepatitis B Network Cohort was utilized to conduct a cross-sectional evaluation of the demographic, biochemical, fibrotic and treatment characteristics of HIV-HBV patients and a comparator HBV group. From a total of 5996 HBV-infected patients, 335 HIV-HBV patients were identified. HIV-HBV patients were characterized by older median age, higher male and lower Asian proportion, more advanced fibrosis and higher anti-HBV therapy use (91% vs. 30%) than the HBV-positive / HIV seronegative comparator group. A history of reported high-risk exposure activities (drug use, high-risk sexual contact) was more common in HIV-HBV patients. HIV-HBV patients with reported high-risk exposure activities had higher male proportion, more Caucasian ethnicity and higher prevalence of cirrhosis than HIV-HBV patients born in an endemic country. In the main cohort, age ≥60 years, male sex, elevated ALT, the presence of comorbidity and HCV seropositivity were independent predictors of significant fibrosis. HIV seropositivity was not an independent predictor of advanced fibrosis (adj OR 0.75 [95%CI: 0.34-1.67]). In conclusion, Canadian co-infected patients differed considerably from those with mono-infection. Furthermore, HIV-HBV-infected patients who report high-risk behaviours and those born in endemic countries represent two distinct subpopulations, which should be considered when engaging these patients in care.

Neural architecture search has proven to be highly effective in the design of efficient convolutional neural networks that are better suited for mobile deployment than hand-designed networks. Hypothesizing that neural architecture search holds great potential for human pose estimation, we explore the application of neuroevolution, a form of neural architecture search inspired by biological evolution, in the design of 2D human pose networks for the first time. Additionally, we propose a new weight transfer scheme that enables us to accelerate neuroevolution in a flexible manner. Our method produces network designs that are more efficient and more accurate than state-of-the-art hand-designed networks. In fact, the generated networks process images at higher resolutions using less computation than previous hand-designed networks at lower resolutions, allowing us to push the boundaries of 2D human pose estimation. Our base network designed via neuroevolution, which we refer to as EvoPose2D-S, achieves comparable accuracy to SimpleBaseline while being 50% faster and $12.7\times $ smaller in terms of file size. Our largest network, EvoPose2D-L, achieves new state-of-the-art accuracy on the Microsoft COCO Keypoints benchmark, is $4.3\times $ smaller than its nearest competitor, and has similar inference speed. The code is publicly available at https://github.com/wmcnally/evopose2d.

Although accurate training and initialization information is difficult to acquire, unsupervised hyperspectral subpixel mapping (SPM) without relying on this predefined information is an insufficiently addressed research issue. This letter presents a novel Bayesian approach for unsupervised SPM of hyperspectral imagery (HSI) based on the Markov random field (MRF) and a band-weighted discrete spectral mixture model (BDSMM), with the following key characteristics. First, this is an unsupervised approach that allows adjustment of abundance and endmember information adaptively for less relying on algorithm initialization. Second, this approach consists of the BDSMM for accommodating the noise heterogeneity and the hidden label field of subpixels in HSI. The BDSMM also integrates SPM into the spectral mixture analysis and allows enhanced SPM by fully exploring the endmember-abundance patterns in HSI. Third, the MRF and BDSMM are integrated into a Bayesian framework to use both the spatial and spectral information efficiently, and an expectation-maximization (EM) approach is designed to solve the model by iteratively estimating the endmembers and the label field. Experiments on both simulated and real HSI demonstrate that the proposed algorithm can yield better performance than traditional methods.

Phase 3 clinical studies showed non-inferiority of long-acting intramuscular cabotegravir and rilpivirine dosed every 4 weeks to oral antiretroviral therapy. Important phase 2 results of every 8 weeks dosing, and supportive modelling, underpin further evaluation of every 8 weeks dosing in this trial, which has the potential to offer greater convenience. Our objective was to compare the week 48 antiviral efficacy of cabotegravir plus rilpivirine long-acting dosed every 8 weeks with that of every 4 weeks dosing.ATLAS-2M is an ongoing, randomised, multicentre (13 countries; Australia, Argentina, Canada, France, Germany, Italy, Mexico, Russia, South Africa, South Korea, Spain, Sweden, and the USA), open-label, phase 3b, non-inferiority study of cabotegravir plus rilpivirine long-acting maintenance therapy administered intramuscularly every 8 weeks (cabotegravir 600 mg plus rilpivirine 900 mg) or every 4 weeks (cabotegravir 400 mg plus rilpivirine 600 mg) to treatment-experienced adults living with HIV-1. Eligible newly recruited individuals must have received an uninterrupted first or second oral standard-of-care regimen for at least 6 months without virological failure and be aged 18 years or older. Eligible participants from the ATLAS trial, from both the oral standard-of-care and long-acting groups, must have completed the 52-week comparative phase with an ATLAS-2M screening plasma HIV-1 RNA less than 50 copies per mL. Participants were randomly assigned 1:1 to receive cabotegravir plus rilpivirine long-acting every 8 weeks or every 4 weeks. The randomisation schedule was generated by means of the GlaxoSmithKline validated randomisation software RANDALL NG. The primary endpoint at week 48 was HIV-1 RNA ≥50 copies per mL (Snapshot, intention-to-treat exposed), with a non-inferiority margin of 4%. The trial is registered at ClinicalTrials.gov, NCT03299049 and is ongoing.Screening occurred between Oct 27, 2017, and May 31, 2018. Of 1149 individuals screened, 1045 participants were randomised to the every 8 weeks (n=522) or every 4 weeks (n=523) groups; 37% (n=391) transitioned from every 4 weeks cabotegravir plus rilpivirine long-acting in ATLAS. Median participant age was 42 years (IQR 34-50); 27% (n=280) female at birth; 73% (n=763) white race. Cabotegravir plus rilpivirine long-acting every 8 weeks was non-inferior to dosing every 4 weeks (HIV-1 RNA ≥50 copies per mL; 2% vs 1%) with an adjusted treatment difference of 0·8 (95% CI -0·6-2·2). There were eight (2%, every 8 weeks group) and two (1%, every 4 weeks group) confirmed virological failures (two sequential measures ≥200 copies per mL). For the every 8 weeks group, five (63%) of eight had archived non-nucleoside reverse transcriptase inhibitor resistance-associated mutations to rilpivirine at baseline. The safety profile was similar between dosing groups, with 844 (81%) of 1045 participants having adverse events (excluding injection site reactions); no treatment-related deaths occurred.The efficacy and safety profiles of dosing every 8 weeks and dosing every 4 weeks were similar. These results support the use of cabotegravir plus rilpivirine long-acting administered every 2 months as a therapeutic option for people living with HIV-1.ViiV Healthcare and Janssen.

People developing transient low back pain during standing have altered control of their spine and hips during standing tasks, but the transfer of these responses to other tasks has not been assessed. This study used video fluoroscopy to assess lumbar spine intervertebral kinematics of people who do and do not develop standing-induced low back pain during a seated chair-tilting task. A total of 9 females and 8 males were categorized as pain developers (5 females and 3 males) or nonpain developers (4 females and 5 males) using a 2-hour standing exposure; pain developers reported transient low back pain and nonpain developers did not. Participants were imaged with sagittal plane fluoroscopy at 25 Hz while cyclically tilting their pelvises anteriorly and posteriorly on an unstable chair. Intervertebral angles, relative contributions, and anterior–posterior translations were measured for the L3/L4, L4/L5, and L5/S1 joints and compared between sexes, pain groups, joints, and tilting directions. Female pain developers experienced more extension in their L5/S1 joints in both tilting directions compared with female nonpain developers, a finding not present in males. The specificity in intervertebral kinematics to sex-pain group combinations suggests that these subgroups of pain developers and nonpain developers may implement different control strategies.

Soft tissue sarcomas are a heterogenous group of malignant tumors that represent approximately 1% of adult malignancies. Although these tumors occur throughout the body, the majority involved the lower extremity. Management may involve amputation but more commonly often includes wide local resection by an oncologic surgeon and involvement of a plastic surgeon for reconstruction of larger and more complex defects. Postoperative wound complications are challenging for the surgeon and patient but also impact management of adjuvant chemotherapy and radiation therapy. To explore risk factors for wound complications, we reviewed our single-institution experience of lower-extremity soft tissue sarcomas from April 2009 to September 2016. We identified 127 patients for retrospective review and analysis. The proportion of patients with wound complications in the cohort was 43.3%. Most notably, compared with patients without wound complications, patients with wound complications had a higher proportion of immediate reconstruction (34.5% vs 15.3%; P = 0.05) and a marginally higher proportion who received neoadjuvant radiation (30.9% vs 16.7%; P = 0.06).

Objectives To determine the time to CD4 : CD8 ratio normalization among Canadian adults living with HIV in the modern ART era. To identify characteristics associated with ratio normalization. Patients and methods Retrospective analysis of the Canadian Observational Cohort (CANOC), an interprovincial cohort of ART-naive adults living with HIV, recruited from 11 treatment centres across Canada. We studied participants initiating ART between 1 January 2011 and 31 December 2016 with baseline CD4 : CD8 ratio Results Among 3218 participants, 909 (28%) normalized during a median 2.6 years of follow-up. Participants with higher baseline CD4+ T-cell count were more likely to achieve normalization; the probability of normalization by 5 years was 0.68 (95% CI 0.62–0.74) for those with baseline CD4+ T-cell count >500 cells/mm3 compared with 0.16 (95% CI 0.11–0.21) for those with ≤200 cells/mm3 (P Conclusions Early ART initiation, at higher baseline CD4+ T-cell counts, has the greatest impact on CD4 : CD8 ratio normalization. Our study supports current treatment guidelines recommending immediate ART start, with no difference in ratio normalization observed based on ART class used.

Although efficient hyperspectral image (HSI) denoising relies on complete and accurate description and modeling the spatial–spectral signal in HSI, the current approaches do not fully account for key characteristics of HSI, i.e., the mixed spectra effect, the spatial nonstationarity effect, and noise variance heterogeneity effect. To address this issue, this article presents a linear spectral mixture model with nonlocal means constraint (LSMM-NLMC), with the following advantages. First, LSMM-NLMC can effectively learn the signal in mixed pixels in HSI by estimating clean endmembers and abundances for image restoration. Second, LSMM-NLMC can efficiently address nonstationary spatial correlation effect by imposing NLMC on the latent scene signal. Last, LSMM-NLMC provides accurate noise characterization by accounting for noise variance heterogeneity effect using a band-dependent noise model and a band-weighted Mahalanobis distance for similarity measurement. A novel optimization method based on the expectation–maximization (EM) algorithm and the purified means approach is used to efficiently solve the resulting maximum a posterior (MAP) problem. The experiments on both simulated and real HSI data sets demonstrate that the visual quality and denoising accuracy are significantly improved by the proposed LSMM-NLMC compared with previous methods.

Vehicle Make and Model Recognition (VMMR) systems provide a fully automatic framework to recognize and classify different vehicle models. Several approaches have been proposed to address this challenge; however, they can perform in restricted conditions. Here, in this paper, we formulate the VMMR as a fine-grained classification problem and propose a new configurable on-road VMMR framework. We benefit from the unsupervised feature learning methods, and in more details, we employ Locality-constraint Linear Coding (LLC) method as a fast feature encoder for encoding the input SIFT features. The proposed method can perform in real environments of different conditions. This framework can recognize 50 models of vehicles and has the advantage to classify every other vehicle not belonging to one of the specified 50 classes as an unknown vehicle. The proposed VMMR framework can be configured to become faster or more accurate based on the application domain. The proposed approach is examined on two datasets, including Iranian on-road vehicle (IORV) dataset and CompuCar dataset. The IORV dataset contains images of 50 models of vehicles captured in real situations by traffic-cameras in different weather and lighting conditions. The experimental results show the advantage of the real-time configuration of the proposed framework over the state-of-the-art methods on the IORV datatset and comparable results on CompuCar dataset with 97.5% and 98.4% accuracies, respectively and acceptable running time.

Background Noninvasive markers of liver fibrosis such as aspartate aminotransferase-to-platelet ratio (APRI) and transient elastography (TE) have largely replaced liver biopsy for staging hepatitis C virus (HCV). As there is little longitudinal data, we compared changes in these markers before and after sustained virologic response (SVR) in human immunodeficiency virus (HIV)-HCV coinfected patients. Methods Participants from the Canadian Coinfection Cohort study who achieved SVR after a first treatment with either interferon/ribavirin or direct acting antivirals (DAAs), with at least 1 pre- and posttreatment fibrosis measure were selected. Changes in APRI or TE (DAA era only) were modeled using a generalized additive mixed model, assuming a gamma distribution and adjusting for sex, age at HCV acquisition, duration of HCV infection, and time-dependent body mass index, binge drinking, and detectable HIV RNA. Results Of 1981 patients, 151 achieved SVR with interferon and 553 with DAAs; 94 and 382 met inclusion criteria, respectively. In the DAA era, APRI increased (0.03 units/year; 95% credible interval (CrI): −.05, .12) before, declined dramatically during, and then changed minimally (−0.03 units/year; 95% CrI: −.06, .01) after treatment. TE values, however, increased (0.74 kPa/year; 95% CrI: .36, 1.14) before treatment, changed little by the end of treatment, and then declined (−0.55 kPa/year; 95% CrI: −.80, −.31) after SVR. Conclusions TE should be the preferred noninvasive tool for monitoring fibrosis regression following cure. Future studies should assess the risk of liver-related outcomes such as hepatocellular carcinoma according to trajectories of fibrosis regression measured using TE to determine if and when it will become safe to discontinue screening.

Objective To develop and implement a point-of-care digital solution to streamline the creation and maintenance of wound care product formularies and promote cost-effective wound management. Methods Researchers used Design Thinking methodology to develop the Formulary Module, a point-of-care digital solution within a clinical and reimbursement decision support web application for wound care and hyperbaric clinicians. The module was implemented in a US hospital-based outpatient wound clinic as follows: A baseline list of products was established, with brands automatically grouped by product category. Brands within each dressing category were compared, and redundancy eliminated. Study authors assessed the financial impact of formulary implementation in the wound clinic by comparing inventory expenditure before and after implementation. Results Implementation of the digital Formulary Module resulted in a 36% decrease in products (67 to 43 across 22 types), 38.73% decrease in the monthly average dollar spent on chargeable products, 29.56% decrease in the average dollar amount spent on chargeable products per patient visit, and increased staff efficiency. Conclusions The Formulary Module has the potential to increase the adoption of cost-effective practices in wound care significantly.

Background An individual is considered HIV positive when a confirmatory HIV-1/HIV-2 differentiation test returns positive following an initial reactive antigen/antibody combination screen. Falsely reactive HIV screens have been reported in patients with various concomitant infectious and autoimmune conditions. Falsely positive confirmatory HIV differentiation assays are seen less frequently, but have been observed in cases of pregnancy, pulmonary embolism, and malaria. Case presentation A healthy 27 year-old man was referred after a reactive ADVIA Centaur® HIV Ag/Ab screen and positive Bio-Rad Geenius™ HIV 1/2 Confirmatory assay, suggesting HIV-1 infection. The patient’s HIV viral load was undetectable prior to initiation of antiretroviral therapy, and remained undetectable on subsequent testing after initiation of antiretroviral therapy. Both Centaur® and Geenius™ tests were repeated and returned reactive. As this patient was believed to be at low risk of acquiring HIV infection, samples were additionally run on Genscreen™ HIV-1 Ag assay and Fujirebio Inno-LIA™ HIV-1/2 score, with both returning non-reactive. For confirmation, the patient’s proviral HIV DNA testing was negative, confirming the initial results as being falsely positive. The patient disclosed that he had been using a variety of anabolic steroids before and during the time of HIV testing. Discussion and conclusions The erroneous diagnosis of HIV can result in decreased quality of life and adverse effects of antiretroviral therapy if initiated, hence the importance of interpreting the results of HIV testing in the context of an individual patient. This reports suggests a potential association between the use of anabolic steroids and falsely-reactive HIV testing.

Advance knowledge of soil water content (SWC) in the soil wetting layer of crop irrigation can help develop more reasonable irrigation plans and improve the efficiency of agricultural irrigation water use. To improve the accuracy of predicting SWC at multiple depths, the ResBiLSTM model was proposed, in which continuous meteorological and SWC data were gridded and transformed as model inputs, and then high-dimensional spatial and time series features were extracted by ResNet and BiLSTM, respectively, and integrated by a meta-learner. Meteorological, SWC and growth stage records data from seven typical maize monitoring stations in Hebei Province, China, during the 2016-2018 summer maize planting process were utilized for the training, evaluation and testing of the ResBiLSTM model, with model prediction targets set at 20cm, 30cm, 40cm and 50cm depths. Experimental results showed that: 1) ResBiLSTM model could achieve better model fit and prediction of meteorological and SWC data at all growth stages, with R2 within [0.818, 0.991], average MAE within [0.79%, 2.00%], and the overall prediction accuracy ranked as follows: anthesis maturity stage > seedling stage > tassel stage; 2) The average MSE of the ResBiLSTM model for the prediction of SWC in the next 1-6 days was within [3.91%, 15.82%], and the prediction accuracy decreased with the extension of the prediction time; 3) Compared with the classical machine learning model and related deep learning models, the ResBiLSTM model was able to obtain better prediction accuracy performance.

Robotic leg prostheses and exoskeletons can provide powered locomotor assistance to older adults and/or persons with physical disabilities. However, the current locomotion mode recognition systems being developed for automated high-level control and decision-making rely on mechanical, inertial, and/or neuromuscular sensors, which inherently have limited prediction horizons (i.e., analogous to walking blindfolded). Inspired by the human vision-locomotor control system, we developed an environment classification system powered by computer vision and deep learning to predict the oncoming walking environments prior to physical interaction, therein allowing for more accurate and robust high-level control decisions. In this study, we first reviewed the development of our “ExoNet” database—the largest and most diverse open-source dataset of wearable camera images of indoor and outdoor real-world walking environments, which were annotated using a hierarchical labeling architecture. We then trained and tested over a dozen state-of-the-art deep convolutional neural networks (CNNs) on the ExoNet database for image classification and automatic feature engineering, including: EfficientNetB0, InceptionV3, MobileNet, MobileNetV2, VGG16, VGG19, Xception, ResNet50, ResNet101, ResNet152, DenseNet121, DenseNet169, and DenseNet201. Finally, we quantitatively compared the benchmarked CNN architectures and their environment classification predictions using an operational metric called “NetScore,” which balances the image classification accuracy with the computational and memory storage requirements (i.e., important for onboard real-time inference with mobile computing devices). Our comparative analyses showed that the EfficientNetB0 network achieves the highest test accuracy; VGG16 the fastest inference time; and MobileNetV2 the best NetScore, which can inform the optimal architecture design or selection depending on the desired performance. Overall, this study provides a large-scale benchmark and reference for next-generation environment classification systems for robotic leg prostheses and exoskeletons.

Robotic exoskeletons require human control and decision making to switch between different locomotion modes, which can be inconvenient and cognitively demanding. To support the development of automated locomotion mode recognition systems (i.e., high-level controllers), we designed an environment recognition system using computer vision and deep learning. We collected over 5.6 million images of indoor and outdoor real-world walking environments using a wearable camera system, of which ~923,000 images were annotated using a 12-class hierarchical labelling architecture (called the ExoNet database). We then trained and tested the EfficientNetB0 convolutional neural network, designed for efficiency using neural architecture search, to predict the different walking environments. Our environment recognition system achieved ~73% image classification accuracy. While these preliminary results benchmark Efficient-NetB0 on the ExoNet database, further research is needed to compare different image classification algorithms to develop an accurate and real-time environment-adaptive locomotion mode recognition system for robotic exoskeleton control.

The outbreak of the novel coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been continuously affecting human lives and communities around the world in many ways, from cities under lockdown to new social experiences. Although in most cases COVID-19 results in mild illness, it has drawn global attention due to the extremely contagious nature of SARS-CoV-2. Governments and healthcare professionals, along with people and society as a whole, have taken any measures to break the chain of transition and flatten the epidemic curve. In this study, we used multiple data sources, i.e., PubMed and ArXiv, and built several machine learning models to characterize the landscape of current COVID-19 research by identifying the latent topics and analyzing the temporal evolution of the extracted research themes, publications similarity, and sentiments, within the time-frame of January- May 2020. Our findings confirm the types of research available in PubMed and ArXiv differ significantly, with the former exhibiting greater diversity in terms of COVID-19 related issues and the latter focusing more on intelligent systems/tools to predict/diagnose COVID-19. The special attention of the research community to the high-risk groups and people with complications was also confirmed.

Atrial fibrillation (AF) is the most common arrhythmia, but an estimated 30% of patients with AF are unaware of their conditions. The purpose of this work is to design a model for AF screening from facial videos, with a focus on addressing typical motion disturbances in our real life, such as head movements and expression changes. This model detects a pulse signal from the skin color changes in a facial video by a convolution neural network, incorporating a phase-driven attention mechanism to suppress motion signals in the space domain. It then encodes the pulse signal into discriminative features for AF classification by a coding neural network, using a de-noise coding strategy to improve the robustness of the features to motion signals in the time domain. The proposed model was tested on a dataset containing 1200 samples of 100 AF patients and 100 non-AF subjects. Experimental results demonstrated that VidAF had significant robustness to facial motions, predicting clean pulse signals with the mean absolute error of inter-pulse intervals less than 100 milliseconds. Besides, the model achieved promising performance in AF identification, showing an accuracy of more than 90% in multiple challenging scenarios. VidAF provides a more convenient and cost-effective approach for opportunistic AF screening in the community.

BACKGROUND: Preoperative anxiety is a common phenomenon in plastic surgery that has been associated with numerous negative patient outcomes. Little is known about the preferences of plastic surgeons regarding management of patient preoperative anxiety OBJECTIVE: To determine the preferences of plastic surgeons regarding the assessment and reduction of adult preoperative patient anxiety in their primary practice setting. METHODS: The membership of the American Council of Academic Plastic Surgeons (ACAPS) was surveyed using an anonymous, online questionnaire from April to June of 2020. RESULTS: A total of 100 participants from a membership of 532 responded (19%). The majority of respondents (63%) did not formally assess patient anxiety but supported the use of standardized scales to measure anxiety (57%). Most plastic surgeons preferred patient education (81%), family member presence (69%), and visit from the anesthesiologist (54%) to reduce patient anxiety. Plastic surgeons also allocated the most responsibility to anesthesiologists (63%) and plastic surgeons (62%) to reduce preoperative anxiety. DISCUSSION: Most plastic surgeon members of ACAPS did not assess their patients’ anxieties preoperatively but appeared willing to use anxiety scales. Plastic surgeons also supported several measures to reduce anxiety, especially patient education, family member preferences, and anesthesiologist visits. Although plastic surgeons appeared to hold multiple parties responsible to manage preoperative anxiety, they held themselves and anesthesiologists most responsible. Future studies are needed to determine whether these views cohere with those of other healthcare providers and whether these preferences change for pediatric patients. LEVEL OF EVIDENCE V: This journal requires that authors assign a level of evidence to each article. For a full description of these evidence-based medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266.

In the years since the COMPASS dataset initiative was begun, many important research questions have been investigated using its large amount of health information pertaining to high school students across Canada, with findings guiding many decisions made by policy makers [1]. However, to use traditional statistical methods, specific data points must be selected by researchers to include in the analysis, leading to possible unexpected relationships and connections across the study's 280 data points being missed. As well, most analysis is done on a per-student basis, while policies are often implemented at the school level, so understanding behaviours across a school's population can make it easier for school decision makers to interpret findings. Motivated by these goals, this study introduces a novel deep learning-driven aggregate embedding method to determine group-level representations for individual schools from student-level survey responses based on architecture introduced in Variational Autoencoders [2]. This study aims to produce a method which allows for new patterns to be identified in the COMPASS data and for the resulting embedded representations to be applied in future analysis.

The recognition of microplastics (MPs) in environmental samples via FT-IR is challenging due to a plethora of factors can lead to significant variances in measured spectra. Conventional library search approaches compare the observed spectrum with spectra in reference libraries, which will lead to errors due the variance in spectra. Motivated to tackle this challenge, this study explores the feasibility of leveraging deep learning for automatic MP recognition via FT-IR spectroscopy. More specifically, a deep convolution neural network (CNN) architecture, referred to here as PlasticNet, is introduced for the purpose of automatic MP recognition. PlasticNet was trained on a large corpus of FT-IR spectra of different plastic types in order to learn discriminative spectral features characterizing each plastic type. Experimental results showed that PlasticNet was capable of recognizing between MPs in an effective way and at a faster speed compared with libary search.

The COVID-19 pandemic continues to have a tremendous impact on patients and healthcare systems around the world. To combat this disease, there is a need for effective screening tools to identify patients infected with COVID-19, and to this end CT imaging has been proposed as a key screening method to complement RT-PCR testing. Early studies have reported abnormalities in chest CT images which are characteristic of COVID-19 infection, but these abnormalities may be difficult to distinguish from abnormalities caused by other lung conditions. Motivated by this, we introduce COVIDNet-CT, a deep convolutional neural network architecture tailored for detection of COVID-19 cases from chest CT images. We also introduce COVIDx-CT, a CT image dataset comprising 104,009 images across 1,489 patient cases. Finally, we leverage explainability to investigate the decision-making behaviour of COVIDNet-CT and ensure that COVIDNet-CT makes predictions based on relevant indicators in CT images.

In order to develop solutions for automatic ice rink localization from broadcast video, a dataset with ground truth homographies is required. Hockey broadcast video does not tend to provide camera parameters for each frame, which means that they must be gathered manually. A novel tool for collecting ground truth transforms through point correspondences between each frame and an overhead view of the ice rink is presented in this paper. Through collaboration with the users of the tool, we have added features to improve accuracy and efficiency, especially in frames with few lines on the playing surface visible. A dataset of 4,262 frames has been collected, which will be used for research into automatic camera calibration techniques.

As the COVID-19 pandemic continues to devastate globally, one promising field of research is machine learning-driven computer vision to streamline various parts of the COVID-19 clinical workflow. These machine learning methods are typically stand-alone models designed without consideration for the integration necessary for real-world application workflows. In this study, we take a machine learning and systems (MLSys) perspective to design a system for COVID-19 patient screening with the clinical workflow in mind. The COVID-Net system is comprised of the continuously evolving COVIDx dataset, COVID-Net deep neural network for COVID-19 patient detection, and COVID-Net S deep neural networks for disease severity scoring for COVID-19 positive patient cases. The deep neural networks within the COVID-Net system possess state-of-the-art performance, and are designed to be integrated within a user interface (UI) for clinical decision support with automatic report generation to assist clinicians in their treatment decisions., 4 pages

BACKGROUND: Alcohol use and hepatitis C virus (HCV) are two leading causes of liver disease. Alcohol use is prevalent among the HCV-infected population and accelerates the progression of HCV-related liver disease. Despite barriers to care faced by HCV-infected patients who use alcohol, few studies have analyzed uptake of direct-acting antiviral (DAA) treatment. OBJECTIVE: We compared rates of treatment uptake and sustained virological response (SVR) between patients with and without alcohol use. METHODS: Prospective data were obtained from the Canadian Network Undertaking against Hepatitis C (CANUHC) cohort. Consenting patients assessed for DAA treatment between January 2016 and December 2019 were included. Demographic and clinical characteristics were compared between patients with and without alcohol use by means of t-tests, χ2 tests, and Fisher’s Exact Tests. Univariate and multivariate analyses were used to determine predictors of SVR and treatment initiation. RESULTS: Current alcohol use was reported for 217 of 725 (30%) patients. The proportion of patients initiating DAA treatment did not vary by alcohol use status (82% versus 83%; p = 0.99). SVR rate was similar between patients with alcohol use and patients without alcohol use (92% versus 94%; p = 0.45). Univariate and multivariate analysis found no association between alcohol use and SVR or treatment initiation. CONCLUSION: Patients engaged in HCV treatment have highly favourable treatment uptake and outcomes regardless of alcohol use. Public health interventions should be directed toward facilitating access to care for all patients irrespective of alcohol use. Research into high-level alcohol use and DAA outcomes is needed.

As radiation therapy is used as an adjuvant treatment in an increasing number of women during the management of breast cancer, radiation therapy and its well-known adverse effects pose additional challenges for breast reconstruction. The purpose of this review is to examine recent data on outcomes of various breast reconstruction methods in the setting of radiation therapy and help surgeons and oncologists as well as patients with their decision-making process. Breast reconstruction methods can be categorized into autologous-, implant-, and tissue expander/implant-based, each with its distinct advantages and disadvantages. Autologous and tissue expander/implant are preferred when radiation therapy is expected based on surgical, aesthetic, and patient satisfaction. Use of latissimus dorsi flaps and acellular dermal matrix with tissue expander/implant has shown several advantages to traditional methods. For patients who have a high likelihood of requiring postmastectomy radiation therapy, choosing a breast reconstruction method depends on multiple factors. Patients and surgeons should be aware of the impact of radiation therapy so that they can make a well-informed decision.

Although recommendations help guide surgeons’ mesh choice in abdominal wall reconstruction (AWR), financial and institutional pressures may play a bigger role. Standardization of an AWR algorithm may help reduce costs and change mesh preferences. We performed a retrospective review of high- and low-risk patients who underwent inpatient AWR between 2014 and 2016. High risk was defined as immunosuppression and/or history of infection/contamination. Patients were stratified by the type of mesh as biologic/biosynthetic or synthetic. These cohorts were analyzed for outcome, complications, and cost. One hundred twelve patients underwent complex AWR. The recurrence rate at two years was not statistically different between high- and low-risk cohorts. No significant difference was found in the recurrence rate between biologic and synthetic meshes when comparing both high- and low-risk cohorts. The average cost of biologic mesh was $9,414.80 versus $524.60 for synthetic. The estimated cost saved when using synthetic mesh for low-risk patients was $295,391.20. In conclusion, recurrence rates for complex AWR seem to be unrelated to mesh selection. There seems to be an excess use of biologic mesh in low-risk patients, adding significant cost. Implementing a critical process to evaluate indications for biologic mesh use could decrease costs without impacting the quality of care, thus improving the overall value of AWR.

The tremendous potential exhibited by deep learning is often offset by architectural and computational complexity, making widespread deployment a challenge for edge scenarios such as mobile and other consumer devices. To tackle this challenge, we explore the following idea: Can we learn generative machines to automatically generate deep neural networks with efficient network architectures? In this study, we introduce the idea of generative synthesis, which is premised on the intricate interplay between a generator-inquisitor pair that work in tandem to garner insights and learn to generate highly efficient deep neural networks that best satisfies operational requirements. Experimental results for image classification, semantic segmentation, and object detection tasks illustrate the efficacy of generative synthesis (GenSynth) in producing generators that automatically generate highly efficient deep neural networks (which we nickname FermiNets with higher model efficiency and lower computational costs (reaching $\gt 10\times $>10× more efficient and fewer multiply-accumulate operations than several tested state-of-the-art networks), as well as higher energy efficiency (reaching $\gt 4\times $>4× improvements in image inferences per joule consumed on a Nvidia Tegra X2 mobile processor). As such, GenSynth can be a powerful, generalised approach for accelerating and improving the building of deep neural networks for on-device edge scenarios.

Despeckling of synthetic aperture radar (SAR) is a known research challenge. A novel solution to this problem has been developed and evaluated via an iterative maximum a posterior estimation incorporating a Bayesian joint decorrelation and despeckling based on a correlation model. This model realistically explores the physical correlation process of SAR speckle noise and is determined automatically via Bayesian estimation in the log-Fourier domain. A patchwise computation is used to account for the spatial nonstationarity associated with SAR image data. The proposed approach is compared to the existing despeckling techniques using both simulated and real SAR data, and the experimental results demonstrate the improvement in preserving the structural details while suppressing speckle noise.

Background High costs of direct-acting antivirals (DAAs) have led health-care insurers to limit access worldwide. Using a natural experiment, we evaluated the impact of removing fibrosis stage restrictions on hepatitis C (HCV) treatment initiation rates among people living with human immunodeficiency virus (HIV), and then examined who was left to be treated. Methods Using data from the Canadian HIV-HCV Coinfection Cohort, we applied a difference-in-differences approach. Changes in treatment initiation rates following the removal of fibrosis stage restrictions were assessed using a negative binomial regression with generalized estimating equations. The policy change was then specifically assessed among people who inject drugs (PWID). We then identified the characteristics of participants who remained to be treated using a modified Poisson regression. Results Between 2010–2018, there were a total of 585 HCV initiations among 1130 eligible participants. After removing fibrosis stage restrictions, DAA initiations increased by 1.8-fold (95% confidence interval [CI] 1.3–2.4) controlling for time-invariant differences and secular trends. Among PWID the impact appeared even stronger, with an adjusted incidence rate ratio of 3.6 (95% CI 1.8–7.4). However, this increased treatment uptake was not sustained. At 1 year following universal access, treatment rates declined to 0.8 (95% CI .5–1.1). Marginalized participants (PWID and those of indigenous ethnicity) and those disengaged from care were more likely to remain HCV RNA positive. Conclusions After the removal of fibrosis restrictions, HCV treatment initiations nearly doubled immediately, but this treatment rate was not sustained. To meet the World Health Organization elimination targets, the minimization of structural barriers and adoption of tailored interventions are needed to engage and treat all vulnerable populations., People coinfected with human immunodeficiency virus and hepatitis C virus were 1.8 times more likely to initiate treatments after fibrosis stage restrictions were removed, after controlling for temporal trends. Marginalized populations and those disengaged from care remain to be treated.

The computational complexity of leveraging deep neural networks for extracting deep feature representations is a significant barrier to its widespread adoption. This is particularly a bottleneck for use in embedded devices and application such as self-driving cars. One promising strategy to addressing the complexity issue is the notion of evolutionary synthesis of deep neural networks. It was demonstrated that it successfully produces highly efficient deep neural networks while retaining modeling performance. Here, we further extend upon the evolutionary synthesis strategy for achieving efficient feature extraction. A stress-induced evolutionary synthesis framework is proposed where the stress signals are imposed upon the synapses of a deep neural network during training step. This process induces stress and steers the synthesis process towards the production of more efficient deep neural networks over successive generations. As a result, it improves model fidelity at a greater efficiency. Applying stress during the training phase helps a network to adopt itself for the changes which would happen at the evolution step. The proposed stress-induced evolutionary synthesis approach is evaluated on a variety of different deep neural network architectures (LeNet5, AlexNet, and YOLOv2), different tasks (object classification and object detection) to synthesize efficient StressedNets over multiple generations. Experimental results demonstrate the efficacy of the proposed framework to synthesize StressedNets with significant improvement in network architecture efficiency (e.g., 40 × for AlexNet and 33 × for YOLOv2). It is also shown the speed improvements by the synthesized networks (e.g., 5.5 × inference speed-up for YOLOv2 on an Nvidia Tegra X1 mobile processor).

Speed limit violation by vehicles is one of the most frequent reasons for road crashes, which take the lives of many people every year, resulting in an increasing demand for video-based vehicle speed estimation systems. One of the biggest challenges to achieve monocular video-based vehicle speed estimation is the projection displacement difference (PDD) problem, where there is a plane disparity between street-level indicators and above-plane feature points of vehicles, thus resulting in unreliable speed estimates. In this paper, a novel motion plane-based approach for vehicle speed estimation is proposed, which addresses the problem of PDD. In the proposed method, we consider the center of a vehicle license plate as the vehicle reference point and estimate the hypothetical plane (named motion plane), on which license plate moves. Subsequently, the plate position is mapped on the motion plane and the displacement is then calculated, thus mitigating the effects of PPD. To estimate the motion plane, a texture-based shape-from-template technique is used. Unlike existing methods, the proposed method needs neither to apply any indicator nor to use any information about extrinsic parameters of the camera. Furthermore, since all the license plates are approximately located on a flat plane, the motion plane can be estimated by using several extracted 3-D points. Experimental results show that the proposed method performs better than the state-of-the-art vehicle speed estimation methods, illustrating the efficacy of this approach for achieving reliable vehicle speed estimation.

Objective: Lung cancer is the leading cause of cancer-related death worldwide. Computer-aided diagnosis (CAD) systems have shown significant promise in recent years for facilitating the effective detection and classification of abnormal lung nodules in computed tomography (CT) scans. While hand-engineered radiomic features have been traditionally used for lung cancer prediction, there have been significant recent successes achieving state-of-the-art results in the area of discovery radiomics. Here, radiomic sequencers comprising of highly discriminative radiomic features are discovered directly from archival medical data. However, the interpretation of predictions made using such radiomic sequencers remains a challenge. Method: A novel end-to-end interpretable discovery radiomics-driven lung cancer prediction pipeline has been designed, build, and tested. The radiomic sequencer being discovered possesses a deep architecture comprised of stacked interpretable sequencing cells (SISC). Results: The SISC architecture is shown to outperform previous approaches while providing more insight in to its decision making process. Conclusion: The SISC radiomic sequencer is able to achieve state-of-the-art results in lung cancer prediction, and also offers prediction interpretability in the form of critical response maps. Significance: The critical response maps are useful for not only validating the predictions of the proposed SISC radiomic sequencer, but also provide improved radiologist-machine collaboration for effective diagnosis., First two authors have equal contribution

Background Optimal treatment for patients with HCV genotype-3 infection and liver cirrhosis remains a medical priority. Daclatasvir+sofosbuvir and ribavirin is a recommended option for such patients, but clinical trial data are lacking for treatment >16 weeks. Methods This was a single-arm, Phase III study of daclatasvir+sofosbuvir+ribavirin for 24 weeks in patients with compensated cirrhosis and HCV genotype-3 infection. The primary end point was sustained virological response at post-treatment week 12 (SVR12); the primary objective was to demonstrate statistical superiority to historical SVR12 data for 12 weeks’ daclatasvir+sofosbuvir without ribavirin in genotype-3-infected patients with cirrhosis (95% CI lower bound >79.0%). Results A total of 78 patients were treated (54 treatment-naive, 24 treatment-experienced including 8 with prior sofosbuvir exposure). SVR12 was achieved by 87% (68/78; 95% CI 77.7, 93.7%) of patients in the primary analysis of central laboratory data. One additional patient achieved SVR12 by local testing resulting in an overall SVR12 rate of 88% (95% CI 79.2, 94.6%) and the lower bound of the 95% CI above the historical threshold. SVR12 rates were 93% (50/54) for treatment-naive and 79% (19/24) for treatment-experienced patients. Of the nine non-SVR12 patients, four were lost to follow-up, two relapsed (both sofosbuvir-experienced), two had end-of-treatment virological failure and one discontinued early. There were no unexpected safety signals; only one patient discontinued for an adverse event. Conclusions Daclatasvir+sofosbuvir+ribavirin for 24 weeks was well tolerated and efficacious in HCV genotype-3-infected patients with compensated cirrhosis, with SVR12 outcomes comparable to previously reported outcomes in patients treated with this regimen for 12–16 weeks.

Objective: Radiomics-driven Computer Aided Diagnosis (CAD) has shown considerable promise in recent years as a potential tool for improving clinical decision support in medical oncology, particularly those based around the concept of Discovery Radiomics, where radiomic sequencers are discovered through the analysis of medical imaging data. One of the main limitations with current CAD approaches is that it is very difficult to gain insight or rationale as to how decisions are made, thus limiting their utility to clinicians. Methods: In this study, we propose CLEAR-DR, a novel interpretable CAD system based on the notion of CLass-Enhanced Attentive Response Discovery Radiomics for the purpose of clinical decision support for diabetic retinopathy. Results: In addition to disease grading via the discovered deep radiomic sequencer, the CLEAR-DR system also produces a visual interpretation of the decision-making process to provide better insight and understanding into the decision-making process of the system. Conclusion: We demonstrate the effectiveness and utility of the proposed CLEAR-DR system of enhancing the interpretability of diagnostic grading results for the application of diabetic retinopathy grading. Significance: CLEAR-DR can act as a potential powerful tool to address the uninterpretability issue of current CAD systems, thus improving their utility to clinicians.

Harmful algae blooms are a growing global concern since they negatively affect the quality of drinking water. The gold-standard process to identify and enumerate algae requires highly trained professionals to manually observe algae under a microscope. Therefore, an automated approach to identify and enumerate these micro-organisms is needed. This research investigates the feasibility of leveraging machine learning and fluorescence-based spectral-morphological features to enable the identification of six different algae types in an automated fashion. A custom multi-band fluorescence imaging microscope is used to capture fluorescence data of water samples at six different excitation wavelengths ranging from 405 to 530 nm. Automated data processing and segmentation were performed on the captured data to isolate different micro-organisms from the water sample. Different morphological and spectral fluorescence features are then extracted from the isolated micro-organism imaging data and is used to train neural network classification models. The experimental results using three different neural network classification models (one trained on morphological features, one trained on fluorescence-based spectral features, and one trained on fluorescence-based spectral-morphological features) showed that the use of either fluorescence-based spectral features or fluorescence-based spectral-morphological features to train neural network classification models led to statistically significant improvements in identification accuracy when compared to the use of morphological features (with average identification accuracies of 95.7% ± 3.5% and 96.1% ± 1.5%, respectively). These preliminary results are promising and illustrate the feasibility of leveraging machine learning and fluorescence-based spectral-morphological features as a viable method for automated identification of different algae types.

The world is still struggling in controlling and containing the spread of the COVID-19 pandemic caused by the SARS-CoV-2 virus. The medical conditions associated with SARS-CoV-2 infections have resulted in a surge in the number of patients at clinics and hospitals, leading to a significantly increased strain on healthcare resources. As such, an important part of managing patients with SARS-CoV-2 infections within the clinical workflow is severity assessment, which is often conducted with the use of chest x-ray (CXR) images. In this work, we introduce COVID-Net CXR-S, a convolutional neural network for predicting the airspace severity of a SARS-CoV-2 positive patient based on a CXR image of the patient's chest. More specifically, we leveraged transfer learning to transfer representational knowledge gained from over 16,000 CXR images from a multinational cohort of over 15,000 patient cases into a custom network architecture for severity assessment. Experimental results with a multi-national patient cohort curated by the Radiological Society of North America (RSNA) RICORD initiative showed that the proposed COVID-Net CXR-S has potential to be a powerful tool for computer-aided severity assessment of CXR images of COVID-19 positive patients. Furthermore, radiologist validation on select cases by two board-certified radiologists with over 10 and 19 years of experience, respectively, showed consistency between radiologist interpretation and critical factors leveraged by COVID-Net CXR-S for severity assessment. While not a production-ready solution, the ultimate goal for the open source release of COVID-Net CXR-S is to act as a catalyst for clinical scientists, machine learning researchers, as well as citizen scientists to develop innovative new clinical decision support solutions for helping clinicians around the world manage the continuing pandemic.

We assessed the relationship between tobacco smoking and immunologic and virologic response among people living with HIV (PLWH) initiating combination antiretroviral therapy (cART) in the Canadian HIV Observational Cohort (CANOC). Positive immunologic and virologic response, respectively, were defined as ≥50 cells/mm