BEGIN:VCALENDAR VERSION:2.0 PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4// BEGIN:VEVENT UID:20250913T012053EDT-7581tczt55@132.216.98.100 DTSTAMP:20250913T052053Z DESCRIPTION:The Feindel Brain and Mind Seminar Series will advance the visi on of Dr. William Feindel (1918–2014)\, Former Director of the Neuro (1972 –1984)\, to constantly bridge the clinical and research realms. The talks will highlight the latest advances and discoveries in neuropsychology\, co gnitive neuroscience\, and neuroimaging.\n\nSpeakers will include scientis ts from across The Neuro\, as well as colleagues and collaborators locally and from around the world. The series is intended to provide a virtual fo rum for scientists and trainees to continue to foster interdisciplinary ex changes on the mechanisms\, diagnosis and treatment of brain and cognitive disorders.\n\n\nRegister for In-Person\n\nTo watch online\, click here\n \nHost: Julien Doyon\n\n\nFrom Hype to Hope: Making Medical AI Reproducibl e\n\nAbstract: Artificial intelligence promises to transform medical imagi ng\, but its impact will remain limited unless research can be made reprod ucible\, transparent\, and sustainable. In neuroimaging especially\, small datasets\, variable annotations\, and scanner differences often erode the robustness of AI models. These challenges underscore that lasting progres s in medical AI depends less on the next complex architecture\, and more o n how research practices are designed so that others can reliably reproduc e and build upon them.\n\nIn this lecture\, Julien Cohen-Adad shares lesso ns learned from developing AI tools for neuroimaging\, highlighting both s uccesses and failures. He emphasizes how open standards such as BIDS\, int eroperable ecosystems like MONAI\, and sound data stewardship with tools l ike git-annex and DataLad provide a foundation for reproducibility at scal e. Beyond algorithms\, he discusses how reproducibility can be embedded di rectly into workflows—through transparent data pipelines\, automated monit oring of models for drift\, and software that remains lightweight\, mainta inable\, and usable by the broader community.\n\nUltimately\, Cohen-Adad a rgues that reproducibility is not a constraint but a catalyst: it fosters collaboration across disciplines\, accelerates translation to the clinic\, and ensures that medical AI builds trust by delivering results that can b e verified\, adapted\, and extended. By re-centering efforts on reproducib le research and leveraging unique strengths in MR physics and clinical par tnerships\, he charts a path where AI meaningfully advances both neuroscie nce and patient care.\n\nJulien Cohen-Adad\n\nProfessor\, Polytechnique Mo ntreal\, Director of the Neuroimaging Functional Unit\, University of Mont real\n\n\n\nJulien Cohen-Adad is a full Professor at Polytechnique Montrea l\, Director of the Neuroimaging Functional Unit at the University of Mont real\, member of the Mila – Quebec AI Institute\, and Canada Research Chai r in Quantitative Magnetic Resonance Imaging. Julien Cohen-Adad has a back ground in MR physics\, medical image analysis\, A.I. and open-source softw are development. His research focuses on advancing MRI hardware and analys is methods to help characterizing pathologies in the central nervous syste m\, with a particular focus in the spinal cord. He has published over 200 articles (h-index of 72). Cohen-Adad also dedicates efforts in bringing th e community together by developing open source solutions (https://neuro.po lymtl.ca/software.html) and is a strong advocate of open science and repro ducible research.\n DTSTART:20251110T180000Z DTEND:20251110T190000Z LOCATION:De Grandpré Communications Centre\, The Neuro SUMMARY:Feindel Brain and Mind Seminar Series: From Hype to Hope: Making Me dical AI Reproducible URL:/research/channels/event/feindel-brain-and-mind-se minar-series-hype-hope-making-medical-ai-reproducible-367561 END:VEVENT END:VCALENDAR