A5015906097- Radiomics and Machine Learning in Medical Imaging
- Artificial Intelligence in Healthcare and Education
- Liver Disease Diagnosis and Treatment
- Liver Disease and Transplantation
- AI in cancer detection
- Organ Transplantation Techniques and Outcomes
- Renal Transplantation Outcomes and Treatments
- Pregnancy and Medication Impact
- Cell Image Analysis Techniques
- Organ Donation and Transplantation
- Artificial Intelligence in Healthcare
- Machine Learning in Healthcare
- Pancreatic and Hepatic Oncology Research
- Digital Imaging for Blood Diseases
- Neurological Complications and Syndromes
- COVID-19 diagnosis using AI
- Cancer Immunotherapy and Biomarkers
- Lung Cancer Treatments and Mutations
- Hepatocellular Carcinoma Treatment and Prognosis
- Cancer, Lipids, and Metabolism
- Pneumocystis jirovecii pneumonia detection and treatment
University Health Network
2020-2025
University of Toronto
2022-2025
Toronto General Hospital
2022-2025
ABSTRACT Background and Aim Liver transplant (LT) recipients may succumb to graft‐related pathologies, contributing graft fibrosis (GF). Current methods diagnose GF are limited, ranging from procedural‐related complications low accuracy. With recent advances in machine learning (ML), we aimed develop a noninvasive tool using demographic, clinical, laboratory, B‐mode ultrasound (US) features predict significant (METAVIR≥F2). Methods We used nested 10‐fold cross‐validation approach with...
Immunohistochemistry (IHC) assessment of tissue is a central component the modern pathology workflow, but quantification challenged by subjective estimates pathologists or manual steps in semi-automated digital tools. This study integrates various computer vision tools to develop fully automated workflow for quantifying Ki-67, standard IHC test used assess cell proliferation on whole slide images (WSIs).We create an nuclear segmentation strategy deploying Mask R-CNN classifier recognise and...
Modern molecular pathology workflows in neuro-oncology heavily rely on the integration of morphologic and immunohistochemical patterns for analysis, classification, prognostication. However, despite recent emergence digital platforms artificial intelligence-driven computational image analysis tools, automating histomorphologic information found across these multiple studies is challenged by large files sizes whole slide images (WSIs) shifts/rotations tissue sections introduced during...
Skanthan, Cavizshajan; Nguyen, Emily; Somaweera, Lakindu; Rabindranath, Madhumitha; Famure, Olusegun; Kim, Joseph Author Information
Abstract Background: Modern diagnostic pathology workflows involve the integration of histomorphologic, immunohistochemical (IHC), and molecular data to reach a final diagnosis. Recently, advances in deep learning have revolutionized by providing prospect for expert-level autonomous image analysis tools. Despite recent innovations learning, integrating histomorphologic information found on respective H&E- IHC-stained tissue sections still remains challenge. Here, we aim address this...