Multi-sequence MRI radiomics of colorectal liver metastases: Which features are reproducible across readers?

[Display omitted] • Reproducibility is a pressing concern in radiomics research. • Manual segmentations by radiologists impact radiomics features. • Most MRI radiomics features have excellent agreement in colorectal liver metastases. • CE-T1W, DWI and T2W were more robust for segmentation variations compared to ADC. To assess the inter-reader reproducibility of radiomics features on multiple MRI sequences after segmentations of colorectal liver metastases (CRLM). 30 CRLM (in 23 patients) were manually delineated by three readers on MRI before the start of chemotherapy on the contrast enhanced T1-weighted images (CE-T1W) in the portal venous phase, T2-weighted images (T2W) and b800 diffusion weighted images (DWI). DWI delineations were copied to the ADC-maps. 107 radiomics features were extracted per sequence. The intraclass correlation coefficient (ICC) was calculated per feature. Features were considered reproducible if ICC > 0.9. 90% of CE-T1W features were reproducible with a median ICC of 0.98 (range 0.76–1.00). 81% of DWI features were robust with median ICC = 0.97 (range 0.38–1.00). The T2W features had a median ICC of 0.96 (range 0.55–0.99) and were reproducible in 80%. ADC showed the lowest number of reproducible features with 58% and median ICC = 0.91 (range 0.38–0.99) When considering the lower bound of the ICC 95% confidence intervals, 58%, 66%, 54% and 29% reached 0.9 for the CE-T1W, DWI, T2W and ADC features, respectively. The feature class with the best reproducibility differed per sequence. The majority of MRI radiomics features from CE-T1W, T2W, DWI and ADC in colorectal liver metastases were robust for segmentation variability between readers. The CE-T1W yielded slightly better reproducibility results compared to DWI and T2W. The ADC features seem more susceptible to reader differences compared to the other three sequences. [ABSTRACT FROM AUTHOR]