eprintid: 10115261 rev_number: 22 eprint_status: archive userid: 608 dir: disk0/10/11/52/61 datestamp: 2020-11-19 11:49:48 lastmod: 2022-01-04 17:51:53 status_changed: 2020-11-19 11:49:48 type: article metadata_visibility: show creators_name: Gong, T creators_name: Tong, Q creators_name: Li, Z creators_name: He, H creators_name: Zhang, H creators_name: Zhong, J title: Deep learning‐based method for reducing residual motion effects in diffusion parameter estimation ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 keywords: diffusion kurtosis imaging, diffusion tensor imaging, head motion, neural network note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: PURPOSE: Conventional motion-correction techniques for diffusion MRI can introduce motion-level-dependent bias in derived metrics. To address this challenge, a deep learning-based technique was developed to minimize such residual motion effects. METHODS: The data-rejection approach was adopted in which motion-corrupted data are discarded before model-fitting. A deep learning-based parameter estimation algorithm, using a hierarchical convolutional neural network (H-CNN), was combined with motion assessment and corrupted volume rejection. The method was designed to overcome the limitations of existing methods of this kind that produce parameter estimations whose quality depends strongly on a proportion of the data discarded. Evaluation experiments were conducted for the estimation of diffusion kurtosis and diffusion-tensor-derived measures at both the individual and group levels. The performance was compared with the robust approach of iteratively reweighted linear least squares (IRLLS) after motion correction with and without outlier replacement. RESULTS: Compared with IRLLS, the H-CNN-based technique is minimally sensitive to motion effects. It was tested at severe motion levels when 70% to 90% of the data are rejected and when random motion is present. The technique had a stable performance independent of the numbers and schemes of data rejection. A further test on a data set from children with attention-deficit hyperactivity disorder shows the technique can potentially ameliorate spurious group-level difference caused by head motion. CONCLUSION: This method shows great potential for reducing residual motion effects in motion-corrupted diffusion-weighted-imaging data, bringing benefits that include reduced bias in derived metrics in individual scans and reduced motion-level-dependent bias in population studies employing diffusion MRI. date: 2021-04 date_type: published official_url: https://doi.org/10.1002/mrm.28544 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1823958 doi: 10.1002/mrm.28544 lyricists_name: Gong, Ting lyricists_name: Zhang, Hui lyricists_id: TGONG58 lyricists_id: HZHAN50 actors_name: Gong, Ting actors_id: TGONG58 actors_role: owner full_text_status: public publication: Magnetic Resonance in Medicine volume: 85 number: 4 pagerange: 2278-2293 event_location: United States citation: Gong, T; Tong, Q; Li, Z; He, H; Zhang, H; Zhong, J; (2021) Deep learning‐based method for reducing residual motion effects in diffusion parameter estimation. Magnetic Resonance in Medicine , 85 (4) pp. 2278-2293. 10.1002/mrm.28544 <https://doi.org/10.1002/mrm.28544>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10115261/3/Gong_Main-MRM-20-21048-clean.pdf