Analysis of heterogeneity in T2-weighted MR images can differentiate pseudoprogression from progression in glioblastoma
- Submitting institution
-
King's College London
- Unit of assessment
- 12 - Engineering
- Output identifier
- 101391709
- Type
- D - Journal article
- DOI
-
10.1371/journal.pone.0176528
- Title of journal
- PloS one
- Article number
- -
- First page
- e0176528
- Volume
- 12
- Issue
- 5
- ISSN
- 1932-6203
- Open access status
- Compliant
- Month of publication
- May
- Year of publication
- 2017
- 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
-
12
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Analysis of disease heterogeneity in T2-weighted magnetic resonance brain images, routinely acquired in the clinic, has the potential to detect earlier tumour treatment response, allowing an early change in treatment strategy. This work presents a novel imaging biomarker based on unsupervised and supervised machine learning methodology (Minkowski Functionals biomarker). This work is becoming more widely adopted in clinical/pre-clinical brain cancer studies (e.g. https://www.nature.com/articles/s41598-020-76686-y, https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0217785, https://onlinelibrary.wiley.com/doi/full/10.1002/jmri.26171) and has informed the development of published AI brain tumour consortium (representing UK https://academic.oup.com/neuro-oncology/article/22/6/886/5802285?login=true) as well as artificial intelligence guidelines at the Royal College of Radiologists (AI committee member and author https://www.rcr.ac.uk/posts/rcr-position-statement-artificial-intelligence).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -