DeepIGeoS : A Deep Interactive Geodesic Framework for Medical Image Segmentation
- Submitting institution
-
King's College London
- Unit of assessment
- 12 - Engineering
- Output identifier
- 97871518
- Type
- D - Journal article
- DOI
-
10.1109/TPAMI.2018.2840695
- Title of journal
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Article number
- -
- First page
- 1559
- Volume
- 41
- Issue
- 7
- ISSN
- 0162-8828
- Open access status
- Compliant
- Month of publication
- May
- Year of publication
- 2018
- URL
-
-
- 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
- No
- Number of additional authors
-
10
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work is the first to combine deep learning with interactive medical image segmentation. This allows for the first time to combine the power of modern AI methods with the clinical need for human operators to control and adjust any results based on patient- and clinician-specific needs. Its publication in a prestigious journal whose scope extends much beyond the field of medical image computing attests the broad applicability of the method. A patent application (WO2018229490A1) has been filed to protect the underpinning invention. The method has raised commercial interest from a major medical device manufacturer (Medtronic contact: leslie.holton@medtronic.com).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -