MyMedR

Displaying all 5 publications

Abstract:

Sort:

Fulltext A parallel spatiotemporal saliency and discriminative online learning method for visual target tracking in aerial videos

Aghamohammadi A, Ang MC, A Sundararajan E, Weng Ng K, Mogharrebi M, Banihashem SY

PLoS One, 2018;13(2):e0192246.
PMID: 29438421 DOI: 10.1371/journal.pone.0192246

Visual tracking in aerial videos is a challenging task in computer vision and remote sensing technologies due to appearance variation difficulties. Appearance variations are caused by camera and target motion, low resolution noisy images, scale changes, and pose variations. Various approaches have been proposed to deal with appearance variation difficulties in aerial videos, and amongst these methods, the spatiotemporal saliency detection approach reported promising results in the context of moving target detection. However, it is not accurate for moving target detection when visual tracking is performed under appearance variations. In this study, a visual tracking method is proposed based on spatiotemporal saliency and discriminative online learning methods to deal with appearance variations difficulties. Temporal saliency is used to represent moving target regions, and it was extracted based on the frame difference with Sauvola local adaptive thresholding algorithms. The spatial saliency is used to represent the target appearance details in candidate moving regions. SLIC superpixel segmentation, color, and moment features can be used to compute feature uniqueness and spatial compactness of saliency measurements to detect spatial saliency. It is a time consuming process, which prompted the development of a parallel algorithm to optimize and distribute the saliency detection processes that are loaded into the multi-processors. Spatiotemporal saliency is then obtained by combining the temporal and spatial saliencies to represent moving targets. Finally, a discriminative online learning algorithm was applied to generate a sample model based on spatiotemporal saliency. This sample model is then incrementally updated to detect the target in appearance variation conditions. Experiments conducted on the VIVID dataset demonstrated that the proposed visual tracking method is effective and is computationally efficient compared to state-of-the-art methods.
Fulltext Lung Infection Segmentation for COVID-19 Pneumonia Based on a Cascade Convolutional Network from CT Images

Ranjbarzadeh R, Jafarzadeh Ghoushchi S, Bendechache M, Amirabadi A, Ab Rahman MN, Baseri Saadi S, et al.

Biomed Res Int, 2021;2021:5544742.
PMID: 33954175 DOI: 10.1155/2021/5544742

The COVID-19 pandemic is a global, national, and local public health concern which has caused a significant outbreak in all countries and regions for both males and females around the world. Automated detection of lung infections and their boundaries from medical images offers a great potential to augment the patient treatment healthcare strategies for tackling COVID-19 and its impacts. Detecting this disease from lung CT scan images is perhaps one of the fastest ways to diagnose patients. However, finding the presence of infected tissues and segment them from CT slices faces numerous challenges, including similar adjacent tissues, vague boundary, and erratic infections. To eliminate these obstacles, we propose a two-route convolutional neural network (CNN) by extracting global and local features for detecting and classifying COVID-19 infection from CT images. Each pixel from the image is classified into the normal and infected tissues. For improving the classification accuracy, we used two different strategies including fuzzy c-means clustering and local directional pattern (LDN) encoding methods to represent the input image differently. This allows us to find more complex pattern from the image. To overcome the overfitting problems due to small samples, an augmentation approach is utilized. The results demonstrated that the proposed framework achieved precision 96%, recall 97%, F score, average surface distance (ASD) of 2.8 ± 0.3 mm, and volume overlap error (VOE) of 5.6 ± 1.2%.
Global systematic review of primary immunodeficiency registries

Abolhassani H, Azizi G, Sharifi L, Yazdani R, Mohsenzadegan M, Delavari S, et al.

Expert Rev Clin Immunol, 2020 07;16(7):717-732.
PMID: 32720819 DOI: 10.1080/1744666X.2020.1801422

INTRODUCTION: During the last 4 decades, registration of patients with primary immunodeficiencies (PID) has played an essential role in different aspects of these diseases worldwide including epidemiological indexes, policymaking, quality controls of care/life, facilitation of genetic studies and clinical trials as well as improving our understanding about the natural history of the disease and the immune system function. However, due to the limitation of sustainable resources supporting these registries, inconsistency in diagnostic criteria and lack of molecular diagnosis as well as difficulties in the documentation and designing any universal platform, the global perspective of these diseases remains unclear.
AREAS COVERED: Published and unpublished studies from January 1981 to June 2020 were systematically reviewed on PubMed, Web of Science and Scopus. Additionally, the reference list of all studies was hand-searched for additional studies. This effort identified a total of 104614 registered patients and suggests identification of at least 10590 additional PID patients, mainly from countries located in Asia and Africa. Molecular defects in genes known to cause PID were identified and reported in 13852 (13.2% of all registered) patients.
EXPERT OPINION: Although these data suggest some progress in the identification and documentation of PID patients worldwide, achieving the basic requirement for the global PID burden estimation and registration of undiagnosed patients will require more reinforcement of the progress, involving both improved diagnostic facilities and neonatal screening.
Fulltext Consensus Middle East and North Africa Registry on Inborn Errors of Immunity

Aghamohammadi A, Rezaei N, Yazdani R, Delavari S, Kutukculer N, Topyildiz E, et al.

J Clin Immunol, 2021 08;41(6):1339-1351.
PMID: 34052995 DOI: 10.1007/s10875-021-01053-z

BACKGROUND: Inborn errors of immunity (IEIs) are a heterogeneous group of genetic defects of immunity, which cause high rates of morbidity and mortality mainly among children due to infectious and non-infectious complications. The IEI burden has been critically underestimated in countries from middle- and low-income regions and the majority of patients with IEI in these regions lack a molecular diagnosis.
METHODS: We analyzed the clinical, immunologic, and genetic data of IEI patients from 22 countries in the Middle East and North Africa (MENA) region. The data was collected from national registries and diverse databases such as the Asian Pacific Society for Immunodeficiencies (APSID) registry, African Society for Immunodeficiencies (ASID) registry, Jeffrey Modell Foundation (JMF) registry, J Project centers, and International Consortium on Immune Deficiency (ICID) centers.
RESULTS: We identified 17,120 patients with IEI, among which females represented 39.4%. Parental consanguinity was present in 60.5% of cases and 27.3% of the patients were from families with a confirmed previous family history of IEI. The median age of patients at the onset of disease was 36 months and the median delay in diagnosis was 41 months. The rate of registered IEI patients ranges between 0.02 and 7.58 per 100,000 population, and the lowest rates were in countries with the highest rates of disability-adjusted life years (DALY) and death rates for children. Predominantly antibody deficiencies were the most frequent IEI entities diagnosed in 41.2% of the cohort. Among 5871 patients genetically evaluated, the diagnostic yield was 83% with the majority (65.2%) having autosomal recessive defects. The mortality rate was the highest in patients with non-syndromic combined immunodeficiency (51.7%, median age: 3.5 years) and particularly in patients with mutations in specific genes associated with this phenotype (RFXANK, RAG1, and IL2RG).
CONCLUSIONS: This comprehensive registry highlights the importance of a detailed investigation of IEI patients in the MENA region. The high yield of genetic diagnosis of IEI in this region has important implications for prevention, prognosis, treatment, and resource allocation.
Fulltext Disease Progression of WHIM Syndrome in an International Cohort of 66 Pediatric and Adult Patients

Geier CB, Ellison M, Cruz R, Pawar S, Leiss-Piller A, Zmajkovicova K, et al.

J Clin Immunol, 2022 Nov;42(8):1748-1765.
PMID: 35947323 DOI: 10.1007/s10875-022-01312-7

Warts, hypogammaglobulinemia, infections, and myelokathexis (WHIM) syndrome (WS) is a combined immunodeficiency caused by gain-of-function mutations in the C-X-C chemokine receptor type 4 (CXCR4) gene. We characterize a unique international cohort of 66 patients, including 57 (86%) cases previously unreported, with variable clinical phenotypes. Of 17 distinct CXCR4 genetic variants within our cohort, 11 were novel pathogenic variants affecting 15 individuals (23%). All variants affect the same CXCR4 region and impair CXCR4 internalization resulting in hyperactive signaling. The median age of diagnosis in our cohort (5.5 years) indicates WHIM syndrome can commonly present in childhood, although some patients are not diagnosed until adulthood. The prevalence and mean age of recognition and/or onset of clinical manifestations within our cohort were infections 88%/1.6 years, neutropenia 98%/3.8 years, lymphopenia 88%/5.0 years, and warts 40%/12.1 years. However, we report greater prevalence and variety of autoimmune complications of WHIM syndrome (21.2%) than reported previously. Patients with versus without family history of WHIM syndrome were diagnosed earlier (22%, average age 1.3 years versus 78%, average age 5 years, respectively). Patients with a family history of WHIM syndrome also received earlier treatment, experienced less hospitalization, and had less end-organ damage. This observation reinforces previous reports that early treatment for WHIM syndrome improves outcomes. Only one patient died; death was attributed to complications of hematopoietic stem cell transplantation. The variable expressivity of WHIM syndrome in pediatric patients delays their diagnosis and therapy. Early-onset bacterial infections with severe neutropenia and/or lymphopenia should prompt genetic testing for WHIM syndrome, even in the absence of warts.