AI-enhanced utilization of computed tomography scans in emergency radiology - BC-1023

Genre de projet: Recherche
Discipline(s) souhaitée(s): Génie -biomédical, Génie, Génie - informatique / électrique, Informatique, Sciences mathématiques
Entreprise: Vancouver Imaging
Durée du projet: Plus d’un an
Date souhaitée de début: Dès que possible
Langue exigée: Anglais
Emplacement(s): Vancouver, BC, Canada
Nombre de postes: 1
Niveau de scolarité désiré: DoctoratRecherche postdoctorale
Ouvert aux candidatures de personnes inscrites à un établissement à l’extérieur du Canada: No

Au sujet de l’entreprise: 

Vancouver Imaging is the largest sub-specialty academic diagnostic and interventional radiology group in British Columbia. All our radiologists are fellowship-trained sub-specialists, including expertise in Abdomen, Body Intervention, Chest, Cardiac CT Angiography, Diagnostic Neuroradiology, Emergency & Trauma, Musculoskeletal, Interventional Neuroradiology, and Stroke Intervention. We are trusted leaders in the delivery of world-class healthcare, along with research and academia. Vancouver Imaging’s mission is to pursue excellence and innovation in the delivery of medical imaging programs and services to patients and clinicians within urban, rural and underserviced communities, in accordance with the principles for insured services as set out in the British Columbia Provincial Legislation and the Canada Health Act.
We remain committed to driving innovation in research that improves patient care. Our goal is to leverage cutting-edge technologies that expand access to radiology services, enhance diagnostic efficiency, and ensure equitable care for all patients across the province. By staying at the forefront of medical imaging advancements, we strive to make a meaningful impact on healthcare outcomes and quality of life for individuals and communities.

Veuillez décrire le projet.: 

The prompt and accurate diagnosis of diseases is crucial for achieving favorable patient outcomes in Emergency Departments (EDs). Radiology plays a vital role in the diagnostic process within emergency settings. However, the increasing overcrowding of EDs and the shortage of healthcare professionals have resulted in prolonged wait times, compromising the quality of care provided.
In recent years, there has been a concerted effort across North America to develop innovative solutions aimed at enhancing diagnostic Radiology workflow through decision support, diagnostic, and prognostic pathways. Vancouver General Hospital (VGH), the largest Level 1 trauma center in BC, provides care to over 900,000 patients annually. As a leader in Trauma Radiology, our team is dedicated to creating a disease-specific database of computed tomography (CT) scans. This database will be utilized for the development of artificial intelligence (AI) algorithms designed to augment decision support and diagnostic capabilities.
The project is structured into four distinct phases:
Phase 1: Secure Data Transfer Protocol
Establish a secure workflow for the transfer of de-identified DICOM CT scans from the hospital database to a digital repository.
Phase 2: AI Model Validation
Develop infrastructure for testing and validating existing AI models on the database.
Phase 3: Novel AI Model Development
Create innovative AI models aimed at enhancing diagnostic workflow efficiency.
Phase 4: Prognostication Model Development
Develop AI models focused on enhancing prognostic capabilities

Expertise ou compétences exigées: 

The successful candidate will work on Phase 1 and 2 of the project, focusing on building capacity for testing and deploying AI models on our database. Key responsibilities include:
• Designing and implementing AI/ML models for disease diagnosis
• Developing and testing data pipelines for efficient data processing and model evaluation
• Collaborating with team to establish model requirement, data preparation, labelling, and coordinating labelling efforts
• Experience in project management, ability to track progress, and present status on deliverables to various stakeholder
• Ability to break down complex scientific ideas into easy-to-understand language, making them accessible to everyone reagrdless of their scientific background
• Publishing research papers and presenting findings at conferences
• Grant development

Ideal candidates:
• Background in Computer Science, Engineering, Data Science, or a related field with a focus on AI/ML
• Strong programming skills in languages such as SQL, Python, PyTorch, AWS
• Familarity with medical terminology
• Experience with AI/ML frameworks and libraries (e.g., Keras, OpenCV)
• Familiarity with data preprocessing, feature engineering, and model evaluation
• Excellent communication and collaboration skills