{"links":{"self":"http://dataportal.arc.gov.au/NCGP/API/grants/FT250100684"},"data":{"type":"grant-details","id":"FT250100684","attributes":{"code":"FT250100684","administering-organisation":"The University of Queensland","announcement-administering-organisation":"The University of Queensland","scheme-name":"ARC Future Fellowships","grant-status":"Active","funding-commencement-year":2025,"years-funded":4,"project-start-date":"2026-01-01","anticipated-end-date":"2029-12-31","grant-summary":"Next generation magnetic resonance imaging through vision. Images acquired via magnetic resonance imaging (MRI) currently do not make any allowances for the way that humans read and understand regions of interest like segmenting important objects from the background. This project aims to unify artificial intelligence (AI) models for segmentation with MRI measurements and reconstruction directly in the frequency domain, helping us explain how such models work and create a new method of MRI image acquisition more akin to human vision that only acquires the areas an operator needs. The outcomes of the project have the potential to explain AI models, speed-up MRI scans and lower costs, thereby improving access to MRI services in the future and further advancing urgently needed AI research in Australia.","funding-current":1086824.00,"funding-at-announcement":1063528,"investigators-current":[{"title":"Dr","firstName":"Shekhar","familyName":"Chandra","roleName":"Future Fellowship","roleCode":"FT","isFellowship":true,"orcidIdentifier":"0000-0001-6544-900X "}],"investigators-at-announcement":[{"title":"Dr","firstName":"Shekhar","familyName":"Chandra","roleName":"Future Fellowship","roleCode":"FT","isFellowship":true,"orcidIdentifier":"0000-0001-6544-900X "}],"organisations-current":[{"organisationName":"The University of Queensland","roleName":"Administering Organisation","state":"QLD"}],"organisations-at-announcement":[{"organisationName":"The University of Queensland","roleName":"Administering Organisation","state":"QLD"}],"field-of-research":[{"isPrimary":false,"code":"400304","name":"Biomedical Imaging","type":"FOR20"},{"isPrimary":true,"code":"4603","name":"Computer Vision and Multimedia Computation","type":"FOR20"},{"isPrimary":false,"code":"460304","name":"Computer Vision","type":"FOR20"},{"isPrimary":false,"code":"460306","name":"Image Processing","type":"FOR20"}],"socio-economic-objective":[{"code":"220403","name":"Artificial Intelligence","type":"SEO20"},{"code":"241003","name":"Scientific Instruments","type":"SEO20"},{"code":"280115","name":"Expanding Knowledge In the Information and Computing Sciences","type":"SEO20"}],"international-collaboration":["France"],"lief-register":[],"achievement-summary":null,"national-interest-test-statement":"Magnetic resonance imaging (MRI) is essential in healthcare for non-invasively seeing inside the human body, but its cost is so prohibitive that it is seldom used unless there is no other option. Artificial intelligence (AI) models have been used to help improve MRI to lower some of the cost, but their black box nature makes it difficult to understand and verify that they won’t do us harm. This project aims to research theoretical advancements to better integrate AI models tightly into how MRIs are formed directly where they are acquired to improve MRI scanning speed. This integration will also reveal what information AI models use in these tasks and enable us to better understand how they work. A reduction in scan time will make MRI cheaper and therefore allow the technology to be more readily utilised in the future, including further studies into aging and other chronic conditions. The resulting breakthroughs in AI could also enable new, more efficient models with explainable properties urgently needed to strengthen Australia’s local digital economy."}}}