Data from: Survival prediction of non-small cell lung cancer patients using radiomics analyses of cone-beam CT images

TitleData from: Survival prediction of non-small cell lung cancer patients using radiomics analyses of cone-beam CT images
Publication TypeDataset
Year of Publication2017
Authorsvan Timmeren, J, Leijenaar, RTH, van Elmpt, W, Reymen, B, Oberije, C, Monshouwer, R, Bussink, J, Brink, C, Hansen, O, Lambin, P
Publication Languageeng
Keywordscomputed tomography, cone-beam CT, non-small cell lung cancer, Radiomics, survival prediction
Abstract

Background and Purpose: In this study we investigated the interchangeability of planning CT and cone-beam CT (CBCT) extracted radiomic features. Furthermore, this study validates a previously described CT based prognostic radiomic signature for non-small cell lung cancer (NSCLC) patients using CBCT based features.

Material and Methods: One internal dataset of 132 and two external datasets of 62 and 94 stage I-IV NSCLC patients were included in this study. Interchangeability was assessed by performing a linear regression on CT and CBCT extracted features. A two-step correction was applied prior to model validation of a previously published radiomic signature.

Results: 13.3% (149 out of 1119) of the radiomic features, including all features of the previously published radiomic signature, showed an R2 above 0.85 between intermodal imaging techniques. For the radiomic signature, Kaplan-Meier curves were significantly different between groups with high and low prognostic value for both modalities. Harrell’s concordance index was 0.69 for CT and 0.66 for CBCT models for dataset 1.

Conclusions: The results show that a subset of radiomic features extracted from CT and CBCT images are interchangeable using simple linear regression. Moreover, a previously developed radiomics signature has prognostic value for overall survival in three CBCT cohorts, showing the potential of CBCT radiomics to be used as prognostic imaging biomarker.

 

Kaplan-Meier curves for pCT and CBCT. Kaplan-Meier curves are based on model predictions of the radiomic signature.

DOI10.17195/candat.2017.02.1
File: 
AttachmentSize
Van-Timmeren_2017_cases-001-020.zipdisplayed 2698 times750.99 MB
Van-Timmeren_2017_cases-021-040.zipdisplayed 1606 times726.98 MB
Van-Timmeren_2017_cases-041-060.zipdisplayed 1912 times777.6 MB
Van-Timmeren_2017_cases-061-080.zipdisplayed 1560 times795.72 MB
Van-Timmeren_2017_cases-081-102.zipdisplayed 1913 times827.01 MB