CT Texture Analysis and Machine Learning Improve Post-ablation Prognostication in Patients with Adrenal Metastases: A Proof of Concept
To assess the performance of pre-ablation computed tomography texture features of adrenal metastases to predict post-treatment local progression and survival in patients who underwent ablation using machine learning as a prediction tool.
Materials and Methods
This is a pilot retrospective study of patients with adrenal metastases undergoing ablation. Clinical variables were collected. Thirty-two texture features were extracted from manually segmented adrenal tumors. A univariate cox proportional hazard model was used for prediction of local progression and survival. A linear support vector machine (SVM) learning technique was applied to the texture features and clinical variables, with leave-one-out cross-validation. Receiver operating characteristic analysis and the area under the curve (AUC) were used to assess performance between using clinical variables only versus clinical variables and texture features.
Twenty-one patients (61% male, age 64.1 ± 10.3 years) were included. Mean time to local progression was 29.8 months. Five texture features exhibited association with progression (p < 0.05). The SVM model based on clinical variables alone resulted in an AUC of 0.52, whereas the SVM model that included texture features resulted in an AUC 0.93 (p = 0.01). Mean overall survival was 35 months. Fourteen texture features were associated with survival in the univariate model (p < 0.05). While the trained SVM model based on clinical variables resulted in an AUC of 0.68, the SVM model that included texture features resulted in an AUC of 0.93 (p = 0.024).
Pre-ablation texture analysis and machine learning improve local tumor progression and survival prediction in patients with adrenal metastases who undergo ablation.
KeywordsRadiomics Machine learning Prognostication Texture analysis Ablation Adrenal metastasis
This study was not supported by any funding.
Compliance with Ethical Standards
Conflict of interest
The authors declare that they have no conflict of interest.
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.
- 1.Abrams HL, Spiro R, Goldstein N. Metastases in carcinoma; analysis of 1000 autopsied cases. Cancer. 1950;3(1):74–85.Google Scholar
- 2.Lam KY, Lo CY. Metastatic tumours of the adrenal glands: a 30-year experience in a teaching hospital. Clin Endocrinol. 2002;56(1):95–101.Google Scholar
- 3.Fintelmann FJ, Tuncali K, Puchner S, Gervais DA, Thabet A, Shyn PB, et al. Catecholamine surge during image-guided ablation of adrenal gland metastases: predictors, consequences, and recommendations for management. J Vasc Interv Radiol. 2016;27(3):395–402. https://doi.org/10.1016/j.jvir.2015.11.034.Google Scholar
- 10.Yamakado K, Anai H, Takaki H, Sakaguchi H, Tanaka T, Kichikawa K, et al. Adrenal metastasis from hepatocellular carcinoma: radiofrequency ablation combined with adrenal arterial chemoembolization in six patients. AJR Am J Roentgenol. 2009;192(6):W300–5. https://doi.org/10.2214/ajr.08.1752.Google Scholar
- 12.Carrafiello G, Lagana D, Recaldini C, Giorgianni A, Ianniello A, Lumia D, et al. Imaging-guided percutaneous radiofrequency ablation of adrenal metastases: preliminary results at a single institution with a single device. Cardiovasc Interv Radiol. 2008;31(4):762–7. https://doi.org/10.1007/s00270-008-9337-1.Google Scholar
- 26.Haralick RM, Shanmugam K. Textural features for image classification. IEEE Trans Syst Man Cybern. 1973;6:610–21.Google Scholar
- 27.Hau CC. Handbook of pattern recognition and computer vision. Singapore: World Scientific; 2015.Google Scholar
- 28.Laws KI. Textured image segmentation: University of Southern California Los Angeles Image Processing INST; 1980.Google Scholar
- 29.DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;44(3):837–45.Google Scholar