Estimation of large motion in lung CT by integrating regularized keypoint correspondences into dense deformable registration
- Submitting institution
-
University of Sussex
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 504012_89515
- Type
- D - Journal article
- DOI
-
10.1109/TMI.2017.2691259
- Title of journal
- IEEE Transactions on Medical Imaging
- Article number
- -
- First page
- 1746
- Volume
- 36
- Issue
- 8
- ISSN
- 0278-0062
- Open access status
- Deposit exception
- Month of publication
- April
- Year of publication
- 2017
- URL
-
https://doi.org/10.1109/TMI.2017.2691259
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
6
- Research group(s)
-
-
- Citation count
- 25
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- "This paper was significant in introducing a computationally efficient framework to incorporate regularised keypoint correspondences into dense intensity-based non-linear image registration. This work demonstrated a substantial improvement in the accuracy of aligning pulmonary CT images between inspiration and expiration. This was quantified on public benchmark datasets: matching the inter-observer variability for sparse landmarks, while maintaining biologically plausible deformations as defined by the Jacobian determinant. The work has field-weighted citation impact 2.51 (Scopus) and has been referred to by other leading groups in medical image analysis such as Fraunhofer MEVIS [1] and Kyoto [2].
[1] https://doi.org/10.1007/978-3-030-32226-7_29
[2] https://doi.org/10.1007/s11548-019-02013-0"
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -