A5019088364- Explainable Artificial Intelligence (XAI)
- MicroRNA in disease regulation
- Machine Learning in Bioinformatics
- Bioinformatics and Genomic Networks
- Adversarial Robustness in Machine Learning
- Molecular Biology Techniques and Applications
- Pediatric Urology and Nephrology Studies
- Gene expression and cancer classification
- Cancer-related molecular mechanisms research
- Advanced Neural Network Applications
- Traumatic Brain Injury Research
- Machine Learning in Healthcare
- Renal and Vascular Pathologies
- Autopsy Techniques and Outcomes
- Cell Image Analysis Techniques
- Brain Tumor Detection and Classification
- AI in cancer detection
- Autism Spectrum Disorder Research
- Radiomics and Machine Learning in Medical Imaging
- Posttraumatic Stress Disorder Research
- Fetal and Pediatric Neurological Disorders
- Renal and related cancers
- Bone Metabolism and Diseases
Children's Hospital of Eastern Ontario
2023-2024
Queen's University
2019-2023
Ottawa Hospital
2023
Ottawa Hospital Research Institute
2023
University of Ottawa
2023
Discriminative classifiers have become a foundational tool in deep learning for medical imaging, excelling at separable features of complex data distributions. However, these models often need careful design, augmentation, and training techniques to ensure safe reliable deployment. Recently, diffusion synonymous with generative modeling 2D. These showcase robustness across range tasks including natural image classification, where classification is performed by comparing reconstruction errors...
Abstract Deep learning algorithms have demonstrated remarkable potential in clinical diagnostics, particularly the field of medical imaging. In this study, we investigated application deep models early detection fetal kidney anomalies. To provide an enhanced interpretation those models’ predictions, proposed adapted two-class representation and developed a multi-class model approach for problems with more than two labels variable hierarchical grouping labels. Additionally, employed...
Deep neural networks have been widely adopted in numerous domains due to their high performance and accessibility developers application-specific end-users. Fundamental image-based applications is the development of Convolutional Neural Networks (CNNs), which possess ability automatically extract features from data. However, comprehending these complex models learned representations, typically comprise millions parameters layers, remains a challenge for both This arises absence interpretable...
Post-traumatic stress disorder (PTSD) can be a debilitating condition and early intervention instrumental in preventing patients' suffering. Identifying patients at risk for PTSD is challenging because of the limitations available data set, variations symptoms different patients, misdiagnosis due to being shared with other conditions. In this preliminary study, we explore small set structured primary care extracted from electronic medical records (EMR) Manitoba, Canada. This has subset...
Abstract Background Early diagnosis and access to resources, support therapy are critical for improving long-term outcomes children with autism spectrum disorder (ASD). ASD is typically detected using a case-finding approach based on symptoms family history, resulting in many delayed or missed diagnoses. While population-based screening would be ideal early identification, available tools have limited accuracy. This study aims determine whether machine learning models applied health...
The need for clear, trustworthy explanations of deep learning model predictions is essential high-criticality fields, such as medicine and biometric identification. Class Activation Maps (CAMs) are an increasingly popular category visual explanation methods Convolutional Neural Networks (CNNs). However, the performance individual CAMs depends largely on experimental parameters selected image, target class, model. Here, we propose MetaCAM, ensemble-based method combining multiple existing CAM...
RNA-based sample discrimination and classification can be used to provide biological insights and/or distinguish between clinical groups. However, finding informative differences groups challenging due the multidimensional noisy nature of sequencing data. Here, we apply a machine learning approach for hierarchical samples with high-dimensional miRNA expression Our protocol comprises data preprocessing, unsupervised learning, feature selection, machine-learning-based classification, alongside...
<title>Abstract</title> Deep learning algorithms have demonstrated remarkable potential in clinical diagnostics, particularly the field of medical imaging. In this study, we investigated application deep models early detection fetal kidney anomalies. To provide an enhanced interpretation those models’ predictions, proposed adapted two-class representation and developed a multi-class model approach for problems with more than two labels variable hierarchical grouping labels. Additionally,...
Deep neural networks have been widely adopted in numerous domains due to their high performance and accessibility developers application-specific end-users. Fundamental image-based applications is the development of Convolutional Neural Networks (CNNs), which possess ability automatically extract features from data. However, comprehending these complex models learned representations, typically comprise millions parameters layers, remains a challenge for both This arises absence interpretable...
Abstract Background Accurate cancer classification is essential for correct treatment selection and better prognostication. microRNAs (miRNAs) are small RNA molecules that negatively regulate gene expression, their dyresgulation a common disease mechanism in many cancers. Through clearer understanding of miRNA dysregulation cancer, improved mechanistic knowledge treatments can be sought. Results We present topology-preserving deep learning framework to study cancer. Our comprises expression...