Predicting local tumour progression after ablation for colorectal liver metastases: CT-based radiomics of the ablation zone. Issue 141 (August 2021)

• Record Type: Journal Article
• Authors: Staal, F.C.R.; Taghavi, M.; van der Reijd, D.J.; Gomez, F.M.; Imani, F.; Klompenhouwer, E.G.; Meek, D.; Roberti, S.; de Boer, M.; Lambregts, D.M.J.; Beets-Tan, R.G.H.; Maas, M.
• Is Part Of: European journal of radiology. Issue 141(2021)
• Publication Date: 2021-08
• Subjects: AIC Akaike's information criterion -- AZ ablation zone -- CI confidence interval -- (ce)CT (contrast-enhanced) computed tomography -- CRC colorectal cancer -- CRLM colorectal liver metastases -- CEA carcinoembryonic antigen -- HR hazard ratio -- LoG laplacian of Gaussian -- LOOCV leave-one-out-cross-validation -- LTP local tumour progression -- MWA microwave ablation -- OS overall survival -- PAR periablational rim -- PVP portal venous phase -- RFA radiofrequency ablation -- VOI volume of interest; Colorectal neoplasms -- Radiofrequency ablation -- Neoplasm metastasis -- Liver -- Ablation techniques -- Neoplasm recurrence -- Local -- Tomography -- X-ray computed; Medical radiology -- Periodicals; Radiology -- Periodicals; Radiologie médicale -- Périodiques; Medical radiology; Periodicals; 616.075705
• DOI: 10.1016/j.ejrad.2021.109773
• Languages: English
• ISSNs: 0720-048X

Abstract

Abstract: Purpose: To assess whether CT-based radiomics of the ablation zone (AZ) can predict local tumour progression (LTP) after thermal ablation for colorectal liver metastases (CRLM). Materials and methods: Eighty-two patients with 127 CRLM were included. Radiomics features (with different filters) were extracted from the AZ and a 10 mm periablational rim (PAR)on portal-venous-phase CT up to 8 weeks after ablation. Multivariable stepwise Cox regression analyses were used to predict LTP based on clinical and radiomics features. Performance (concordance [c]-statistics) of the different models was compared and performance in an 'independent' dataset was approximated with bootstrapped leave-one-out-cross-validation (LOOCV). Results: Thirty-three lesions (26 %) developed LTP. Median follow-up was 21 months (range 6−115). The combined model, a combination of clinical and radiomics features, included chemotherapy (HR 0.50, p = 0.024), cT-stage (HR 10.13, p = 0.016), lesion size (HR 1.11, p = <0.001), AZ_Skewness (HR 1.58, p = 0.016), AZ_Uniformity (HR 0.45, p = 0.002), PAR_Mean (HR 0.52, p = 0.008), PAR_Skewness (HR 1.67, p = 0.019) and PAR_Uniformity (HR 3.35, p < 0.001) as relevant predictors for LTP. The predictive performance of the combined model (after LOOCV) yielded a c-statistic of 0.78 (95 %CI 0.65−0.87), compared to the clinical or radiomics models only (c-statistic 0.74 (95 %CI 0.58−0.84) and 0.65 (95 %CI 0.52−0.83), respectively). Conclusion: Combining radiomics features with clinical features yielded a better performing prediction of LTP than radiomics only. CT-based radiomics of the AZ and PAR may have potential to aid in the prediction of LTP during follow-up in patients with CRLM.