en
Scientific article
Open access
English

Overall survival prognostic modelling of non-small cell lung cancer patients using positron emission tomography/computed tomography harmonised radiomics features: the quest for the optimal machine learning algorithm

Published inClinical oncology, vol. 34, no. 2, p. 114-127
Publication date2022-02
First online date2021-12-03
Abstract

Despite the promising results achieved by radiomics prognostic models for various clinical applications, multiple challenges still need to be addressed. The two main limitations of radiomics prognostic models include information limitation owing to single imaging modalities and the selection of optimum machine learning and feature selection methods for the considered modality and clinical outcome. In this work, we applied several feature selection and machine learning methods to single-modality positron emission tomography (PET) and computed tomography (CT) and multimodality PET/CT fusion to identify the best combinations for different radiomics modalities towards overall survival prediction in non-small cell lung cancer patients.

eng
Keywords
  • Fusion
  • Machine learning
  • Non-small cell lung cancer
  • PET/CT
  • Radiomics
Citation (ISO format)
AMINI, Mehdi et al. Overall survival prognostic modelling of non-small cell lung cancer patients using positron emission tomography/computed tomography harmonised radiomics features: the quest for the optimal machine learning algorithm. In: Clinical oncology, 2022, vol. 34, n° 2, p. 114–127. doi: 10.1016/j.clon.2021.11.014
Main files (1)
Article (Published version)
Secondary files (1)
Identifiers
ISSN of the journal0936-6555
146views
62downloads

Technical informations

Creation12/04/2021 9:42:00 AM
First validation12/04/2021 9:42:00 AM
Update time03/16/2023 2:39:14 AM
Status update03/16/2023 2:39:13 AM
Last indexation05/06/2024 9:55:04 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack