4DCT imaging to assess radiomics feature stability: An investigation for thoracic cancers

Autor: Ruben T. H. M. Larue, Janna E. van Timmeren, Maaike Berbee, Wouter van Elmpt, Lien Van De Voorde, Philippe Lambin, Meindert N. Sosef, Wendy M. J. Schreurs, Ralph T.H. Leijenaar
Přispěvatelé: RS: GROW - R3 - Innovative Cancer Diagnostics & Therapy, Promovendi ODB, Radiotherapie, MUMC+: MA Radiotherapie OC (9), Afdeling Onderwijs FHML
Rok vydání: 2017
Předmět:
Male
medicine.medical_specialty
Pathology
Lung Neoplasms
Esophageal Neoplasms
CELL LUNG-CANCER
TUMOR HETEROGENEITY
TEXTURAL FEATURES
Feature selection
Overfitting
4D-CT
TEST-RETEST
030218 nuclear medicine & medical imaging
Correlation
03 medical and health sciences
0302 clinical medicine
Carcinoma
Non-Small-Cell Lung
medicine
Humans
Feature stability
F-18-FDG PET
Radiology
Nuclear Medicine and imaging
Four-Dimensional Computed Tomography
JUNCTIONAL CANCER
Neoplasm Staging
Proportional Hazards Models
Retrospective Studies
Radiomics
business.industry
Proportional hazards model
Oesophageal cancer
Univariate
Cancer
Hematology
LEARNING HEALTH-CARE
Prognosis
medicine.disease
VARIABILITY
Concordance correlation coefficient
Oncology
Feature (computer vision)
030220 oncology & carcinogenesis
Respiratory Mechanics
PRIMARY ESOPHAGEAL CANCER
Female
Radiology
Lung cancer
business
DECISION-SUPPORT-SYSTEMS
Zdroj: Radiotherapy and Oncology, 125(1), 147-153. Elsevier Ireland Ltd
ISSN: 0167-8140
DOI: 10.1016/j.radonc.2017.07.023
Popis: Background and purpose: Quantitative tissue characteristics derived from medical images, also called radiomics, contain valuable prognostic information in several tumour-sites. The large number of features available increases the risk of overfitting. Typically test-retest CT-scans are used to reduce dimensionality and select robust features. However, these scans are not always available. We propose to use different phases of respiratory-correlated 4D CT-scans (4DCT) as alternative.Materials and methods: In test-retest CT-scans of 26 non-small cell lung cancer (NSCLC) patients and 4DCT-scans (8 breathing phases) of 20 NSCLC and 20 oesophageal cancer patients, 1045 radiomics features of the primary tumours were calculated. A concordance correlation coefficient (CCC) >0.85 was used to identify robust features. Correlation with prognostic value was tested using univariate cox regression in 120 oesophageal cancer patients.Results: Features based on unfiltered images demonstrated greater robustness than wavelet-filtered features. In total 63/74 (85%) unfiltered features and 268/299 (90%) wavelet features stable in the 4D-lung dataset were also stable in the test-retest dataset. In oesophageal cancer 397/1045 (38%) features were robust, of which 108 features were significantly associated with overall-survival.Conclusion: 4DCT-scans can be used as alternative to eliminate unstable radiomics features as first step in a feature selection procedure. Feature robustness is tumour-site specific and independent of prognostic value. (C) 2017 The Authors. Published by Elsevier Ireland Ltd.
Databáze: OpenAIRE
Externí odkaz: