?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Deep+neural+network+based+framework+for+in-vivo+axonal+permeability+estimation&rft.creator=Hill%2C+I&rft.creator=Palombo%2C+M&rft.creator=Santin%2C+MD&rft.creator=Branzoli%2C+F&rft.creator=Philippe%2C+A-C&rft.creator=Wassermann%2C+D&rft.creator=Aigrot%2C+M-S&rft.creator=Stankoff%2C+B&rft.creator=Zhang%2C+H&rft.creator=Lehericy%2C+S&rft.creator=Petiet%2C+A&rft.creator=Alexander%2C+D&rft.creator=Ciccarelli%2C+O&rft.creator=Drobnjak%2C+I&rft.description=This+study+introduces+a+novel+framework+for+estimating+permeability+from+diffusion-weighted+MRI+data+using+deep+learning.+Recent+work+introduced+a+random+forest+(RF)+regressor+model+that+outperforms+approximate+mathematical+models+(K%C3%A4rger+model).+Motivated+by+recent+developments+in+machine+learning%2C+we+propose+a+deep+neural+network+(NN)+approach+to+estimate+the+permeability+associated+with+the+water+residence+time.+We+show+in+simulations+and+in+in-vivo+mouse+brain+data+that+the+NN+outperforms+the+RF+method.+We+further+show+that+the+performance+of+either+ML+method+is+unaffected+by+the+choice+of+training+data%2C+i.e.+raw+diffusion+signals+or+signal-derived+features+yield+the+same+results.&rft.publisher=ISMRM+(International+Society+for+Magnetic+Resonance+in+Medicine)&rft.contributor=Miller%2C+KL&rft.contributor=Port%2C+JD&rft.date=2018-06-16&rft.type=Proceedings+paper&rft.publisher=ISMRM+26th+Annual+Meeting+%26+Exhibition&rft.language=eng&rft.source=+++++In%3A+Miller%2C+KL+and+Port%2C+JD%2C+(eds.)+Proceedings+of+the+Joint+Annual+Meeting+ISMRM-ESMRMB+2018.++++ISMRM+(International+Society+for+Magnetic+Resonance+in+Medicine)%3A+Concord%2C+CA%2C+USA.+(2018)+++++&rft.format=text&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10074390%2F1%2FISMRM_abstract_IoanaHill.pdf&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10074390%2F&rft.rights=open