eprintid: 10074390 rev_number: 33 eprint_status: archive userid: 608 dir: disk0/10/07/43/90 datestamp: 2019-10-03 11:23:45 lastmod: 2021-09-19 22:56:51 status_changed: 2019-10-03 11:23:45 type: proceedings_section metadata_visibility: show creators_name: Hill, I creators_name: Palombo, M creators_name: Santin, MD creators_name: Branzoli, F creators_name: Philippe, A-C creators_name: Wassermann, D creators_name: Aigrot, M-S creators_name: Stankoff, B creators_name: Zhang, H creators_name: Lehericy, S creators_name: Petiet, A creators_name: Alexander, D creators_name: Ciccarelli, O creators_name: Drobnjak, I title: Deep neural network based framework for in-vivo axonal permeability estimation ispublished: pub divisions: UCL divisions: B02 divisions: C07 divisions: D07 divisions: F87 divisions: B04 divisions: C05 divisions: F43 divisions: F48 note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: 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 (Kärger model). Motivated by recent developments in machine learning, 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, i.e. raw diffusion signals or signal-derived features yield the same results. date: 2018-06-16 date_type: published publisher: ISMRM (International Society for Magnetic Resonance in Medicine) official_url: https://www.ismrm.org/18m/ oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1658745 lyricists_name: Alexander, Daniel lyricists_name: Ciccarelli, Olga lyricists_name: Drobnjak, Ivana lyricists_name: Hill, Ioana lyricists_name: Palombo, Marco lyricists_name: Zhang, Hui lyricists_id: DALEX06 lyricists_id: OCICC52 lyricists_id: IDROB84 lyricists_id: IDOPR43 lyricists_id: MPALO05 lyricists_id: HZHAN50 actors_name: Palombo, Marco actors_id: MPALO05 actors_role: owner full_text_status: public series: ISMRM (International Society for Magnetic Resonance in Medicine) volume: 2018 place_of_pub: Concord, CA, USA event_title: Joint Annual Meeting ISMRM-ESMRMB 2018, 16-21 June 2018, Paris, France institution: ISMRM 26th Annual Meeting & Exhibition book_title: Proceedings of the Joint Annual Meeting ISMRM-ESMRMB 2018 editors_name: Miller, KL editors_name: Port, JD citation: Hill, I; Palombo, M; Santin, MD; Branzoli, F; Philippe, A-C; Wassermann, D; Aigrot, M-S; ... Drobnjak, I; + view all <#> Hill, I; Palombo, M; Santin, MD; Branzoli, F; Philippe, A-C; Wassermann, D; Aigrot, M-S; Stankoff, B; Zhang, H; Lehericy, S; Petiet, A; Alexander, D; Ciccarelli, O; Drobnjak, I; - view fewer <#> (2018) Deep neural network based framework for in-vivo axonal permeability estimation. In: Miller, KL and Port, JD, (eds.) Proceedings of the Joint Annual Meeting ISMRM-ESMRMB 2018. ISMRM (International Society for Magnetic Resonance in Medicine): Concord, CA, USA. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10074390/1/ISMRM_abstract_IoanaHill.pdf