Reproducible radiomics through automated machine learning validated on twelve clinical applications.
Martijn P. A. StarmansSebastian R. van der VoortThomas PhilMilea J. M. TimbergenMelissa VosGuillaume A. PadmosWouter KesselsDavid HanffDirk J. GrünhagenCornelis VerhoefStefan SleijferMartin J. van den BentMarion SmitsRoy S. DwarkasingChristopher J. ElsFederico FiduziGeert J. L. H. van LeendersAnela BlazevicJohannes HoflandTessa BrabanderRenza A. H. van GilsGaston J. H. FranssenRichard A. FeeldersWouter W. de HerderFlorian E. BuismanFrançois E. J. A. WillemssenBas Groot KoerkampLindsay AngusAstrid A. M. van der VeldtAna RajicicArlette E. OdinkMitchell DeenJose M. Castillo TJifke F. VeenlandIvo SchootsMichel RenckensMichail DoukasRob A. de ManJan N. M. IJzermansRazvan L. MicleaPeter B. VermeulenEsther E. BronMaarten G. ThomeerJacob J. VisserWiro J. NiessenStefan KleinPublished in: CoRR (2021)
Keyphrases
- clinical applications
- machine learning
- automated segmentation
- intraoperative
- medical images
- imaging modalities
- magnetic resonance
- anatomical structures
- feature selection
- medical image analysis
- machine learning methods
- data mining
- decision trees
- treatment planning
- computer assisted
- mr images
- machine learning algorithms
- active learning
- magnetic resonance imaging
- data analysis
- pattern recognition
- high quality
- computer vision
- neural network