A5069788317- Berry genetics and cultivation research
- Plant Physiology and Cultivation Studies
- Plant Disease Management Techniques
- Plant Pathogens and Fungal Diseases
- Horticultural and Viticultural Research
- AI in cancer detection
- Growth and nutrition in plants
- Plant Pathogens and Resistance
- Radiomics and Machine Learning in Medical Imaging
- Cell Image Analysis Techniques
- Medical Imaging Techniques and Applications
- Yeasts and Rust Fungi Studies
- Plant Pathogenic Bacteria Studies
- Plant tissue culture and regeneration
- Agriculture, Plant Science, Crop Management
- Wine Industry and Tourism
- Powdery Mildew Fungal Diseases
- Insect-Plant Interactions and Control
- Fermentation and Sensory Analysis
- Postharvest Quality and Shelf Life Management
- Banana Cultivation and Research
- COVID-19 epidemiological studies
- Phytoplasmas and Hemiptera pathogens
- Medical Image Segmentation Techniques
- Body Image and Dysmorphia Studies
Southwestern Medical Center
2020-2025
The University of Texas Southwestern Medical Center
2019-2025
Creative Commons
2022
Kentville Research and Development Centre
2005-2017
Agriculture and Agri-Food Canada
2005-2017
Virginia Tech
2017
Cornell University
2017
University of Kentucky
2017
University of Minnesota
2017
University of Wisconsin–Extension
2017
Purpose In this preliminary study, recently developed unsupervised nonlinear dimension reduction (DR) and data representation techniques were applied to computer‐extracted breast lesion feature spaces across three separate imaging modalities: Ultrasound (U.S.) with 1126 cases, dynamic contrast enhanced magnetic resonance 356 full‐field digital mammography 245 cases. Two methods for DR explored: Laplacian eigenmaps [M. Belkin P. Niyogi, “Laplacian dimensionality representation,” Neural...
Deep learning has emerged as the technique of choice for identifying hidden patterns in cell imaging data but is often criticized "black box." Here, we employ a generative neural network combination with supervised machine to classify patient-derived melanoma xenografts "efficient" or "inefficient" metastatic, validate predictions regarding lines unknown metastatic efficiency mouse xenografts, and use generate silico images that amplify critical predictive properties. These exaggerated...
Haskap (Lonicera caerulea L.) berries have long been used for their health promoting properties against chronic conditions. The current study investigated the effect of Canadian haskap berry extracts on pro-inflammatory cytokines using a human monocytic cell line THP-1 derived macrophages stimulated by lipopolysaccharide. Methanol from different growing locations in Canada were prepared and characterized total phenolic profile colorimetric assays liquid chromatography—Mass spectrometry...
Feature extraction is a critical component of medical image analysis. Many computer-aided diagnosis approaches employ hand-designed, heuristic lesion extracted features. An alternative approach to learn features directly from images. In this preliminary study, we explored the use Adaptive Deconvolutional Networks (ADN) for learning high-level in diagnostic breast mass images with potential application (CADx) and content-based retrieval (CBIR). ADNs (Zeiler, et. al., 2011), are...
Grapes are one of the world's most valuable crops and made into wine. belong to genus Vitis, which includes over 60 inter-fertile species. The common grape cultivars derive their entire ancestry from species Vitis vinifera, but wild relatives have also been exploited create hybrid cultivars, often with increased disease resistance. We evaluate genetic some widely grown commercial hybrids North America Europe. Using genotyping-by-sequencing (GBS), we generated 2482 SNPs 56 indels 7 V. 64...
Extracting structured data from free-text medical records is laborious and error-prone. Traditional rule-based early neural network methods often struggle with domain complexity require extensive tuning. Large language models (LLMs) offer a promising solution but must be tailored to nuanced clinical knowledge complex, multipart entities. We developed flexible, end-to-end LLM pipeline extract diagnoses, per-specimen anatomical-sites, procedures, histology, detailed immunohistochemistry...
Objective Assessing medical student performance in Structured Clinical Examinations (OSCEs) is labor intensive, requiring trained evaluators to review 15 minute long videos. The physical examination period constitutes only a small portion of these Automated segmentation OSCE videos could significantly streamline the evaluation process by detecting this exam for targeted evaluation. Current video analysis approaches struggle with recordings due computational constraints and challenges...
The COVID-19 pandemic has challenged the United States' existing national public health informatics infrastructure. This report details factors that have contributed to data inaccuracies and reporting delays their effect on modeling monitoring of pandemic.
The goal of this study was to determine the level genetic diversity and relatedness among 16 strawberry (Fragaria H ananassa Duch.) cultivars 11 breeding lines developed in Canada, using Inter Simple Sequence Repeat (ISSR) markers. Seventeen primers generated 225 polymorphic ISSR-PCR bands. Cluster analysis by unweighted pair-group method with arithmetic averages (UPGMA) revealed a substantial degree similarity genotypes ranging from 63 77% that were agreement principal coordinate (PCO)...
Lymphatic abnormalities are observed in several types of kidney disease, but the relationship between renal lymphatic system and function is unclear. The discovery lymphatic-specific proteins, advances microscopy, available genetic mouse models provide tools to help elucidate role lymphatics physiology disease.We utilized a model containing missense mutation Vegfr3 (dubbed Chy ) that abrogates its kinase ability. Chy/+ mice were examined for developmental kidney-specific outcomes. Control...
In this pilot study, the authors examined associations between image-based phenotypes and genomic biomarkers. The potential genetic contribution of UGT2B genes to interindividual variation in breast density mammographic parenchymal patterns is demonstrated by performing an association study biomarkers [single-nucleotide polymorphism (SNP) genotypes].This candidate-gene approach included 179 subjects for whom both mammograms blood DNA samples had been obtained. full-field digital were...
Cell segmentation is the fundamental task. Only by segmenting, can we define quantitative spatial unit for collecting measurements to draw biological conclusions. Deep learning has revolutionized 2D cell segmentation, enabling generalized solutions across types and imaging modalities. This been driven ease of scaling up image acquisition, annotation computation. However 3D which requires dense slices still poses significant challenges. Labelling every in slice prohibitive. Moreover it...
Abstract Deep convolutional neural networks have emerged as a powerful technique to identify hidden patterns in complex cell imaging data. However, these machine learning techniques are often criticized uninterpretable “black-boxes” - lacking the ability provide meaningful explanations for properties that drive machine’s prediction. Here, we demonstrate latent features extracted from label-free live images by an adversarial auto-encoding deep network capture subtle details of appearance...
Twenty-six genotypes of lowbush blueberry ( Vaccinium angustifolium Aiton) representing four geographical zones (Maine, United States; New Brunswick, northern Nova Scotia, and western Canada) were selected to obtain DNA fingerprints estimate genetic similarity by randomly amplified polymorphic analysis. The either native accessions or selections from crosses involving as parents grandparents. Thirty 10-base RAPD primers initially screened; 11 proved be polymorphic, resulting in 73 consistent...
Field plantings of improved Vaccinium angustifolium Aiton clones have had limited success due to reduced rhizome formation in plants propagated by stem cuttings. This study was designed evaluate the field performance lowbush blueberry when alternative methods. A plot established 1985 from that were either cuttings, micropropagation, or grown open-pollinated seeds. The three genotypes selected for this known vary yield fruit and proclivity produce rhizomes. When K206 produced many rhizomes...