CROMBÉ, Amandine; KIND, Michèle; FADLI, David; LE LOARER, François; ITALIANO, Antoine; BUY, Xavier; SAUT, Olivier

doi:10.1038/s41598-020-72535-0

Metadatos

Licencia de uso del documento

CROMBÉ, Amandine
Institut Bergonié [Bordeaux]
Modélisation Mathématique pour l'Oncologie [MONC]
Université de Bordeaux [UB]

KIND, Michèle
Institut Bergonié [Bordeaux]

FADLI, David
Institut Bergonié [Bordeaux]

Idioma

Article de revue

Este ítem está publicado en

Scientific Reports. 2020-12, vol. 10, n° 1

Nature Publishing Group

Resumen en inglés

Intensity harmonization techniques (IHT) are mandatory to homogenize multicentric MRIs before any quantitative analysis because signal intensities (SI) do not have standardized units. Radiomics combine quantification of tumors' radiological phenotype with machine-learning to improve predictive models, such as metastasticrelapse-free survival (MFS) for sarcoma patients. We post-processed the initial T2weighted-imaging of 70 sarcoma patients by using 5 IHTs and extracting 45 radiomics features (RFs), namely: classical standardization (IHTstd), standardization per adipose tissue SIs (IHTfat), histogram-matching with a patient histogram< Leer menos

Metadatos

Compartir este ítem

Licencia de uso del documento

Intensity Harmonization Techniques Influence Radiomics Features and Radiomics-based Predictions in Sarcoma Patients

Idioma

Este ítem está publicado en

Resumen en inglés

URI

DOI

Orígen

Centros de investigación