Join the Machine Learning in Medical Imaging Consortium (MaLMIC) for an opportunity to network on machine learning
Monthly Virtual Forum Series on Zoom
Friday, January 21, 2022
3:30 to 5:30 p.m. EST
Derek Cool, an interventional radiologist, discussed the clinical need for machine learning in image-guided intervention. Purang Abolmaesumi and Derek Gillies then presented their research work in the area. The talks were followed by discussion focused on lessons learned, opportunities to collaborate and sharing of resources.
Monthly Virtual Forum Series on Zoom
Friday, January 21, 2022
3:30 to 5:30 p.m. EST
Derek Cool, an interventional radiologist, discussed the clinical need for machine learning in image-guided intervention. Purang Abolmaesumi and Derek Gillies then presented their research work in the area. The talks were followed by discussion focused on lessons learned, opportunities to collaborate and sharing of resources.
How might artificial intelligence enhance ultrasound-guided procedures in interventional radiology?
Derek W. Cool, MD, PhD FRCPC
Interventional Radiologist and Assistant Professor, Western University
Talk summary: Derek discussed the potential application of artificial intelligence to enhance and expand image-guided procedures within the field of interventional radiology. The current challenges faced in ultrasound-guided interventions in the abdomen, including percutaneous ablation of solid organ malignancies, was the primary focus. The potential value of AI to intra-procedure multi-modality image fusion, tumour and instrument segmentation, and needle navigation was reviewed
Designing for impact: AI-enabled point-of-care imaging
Purang Abolmaesumi, PhD
Professor, University of British Columbia
Talk summary: In this talk, Purang summarized the journey his research team has taken to mobilize AI technology in order to augment decision support for point-of-care ultrasound imaging in BC. He also presented several case studies as future direction for research in AI in this domain.
Evaluating the generalizability of deep learning for 2D ultrasound applicator segmentation during image-guided interventions
Derek J. Gillies, PhD
Radiation Oncology Physics Resident, London Regional Cancer Program
Talk summary: Image-guided interventional procedures require the accurate placement of applicators to planned targets for achieving desired diagnoses and treatments of cancer. Two-dimensional ultrasound can be clinically valuable due to the real-time temporal resolution, but visualization of these applicators can be difficult and vary across interventional applications. This presentation discussed our deep learning-based approach to identify these applicators during ultrasound-guided procedures.