Radiomics improves efficiency for differentiating subclinical pheochromocytoma from lipid-poor adenoma: a predictive, preventive and personalized medical approach in adrenal incidentalomas
This study aims to define a radiomic signature for pre-operative differentiation between subclinical pheochromocytoma (sPHEO) and lipid-poor adrenal adenoma (LPA) in adrenal incidentaloma. The goal was to apply a predictive, preventive, and personalized medical approach to the management of adrenal tumors.
Patients and methods
This retrospective study consisted of 265 consecutive patients (training cohort, 212 (LPA, 145; sPHEO, 67); validation cohort, 53 (LPA, 36; sPHEO, 17)). Computed tomography (CT) imaging features were evaluated, including long diameter (LD), short diameter (SD), pre-enhanced CT value (CTpre), enhanced CT value (CTpost), shape, homogeneity, necrosis or cystic degeneration (N/C). Radiomic features were extracted and then were used to construct a radiomic signature (Rad-score) and radiomic nomogram. The area under the receiver operating characteristic curve (AUC) was used to evaluate their performance.
Sixteen of three hundred forty candidate features were used to build a radiomic signature. The signature was significantly different between the sPHEO and LPA groups (AUC: training, 0.907; validation, 0.902). The radiomic nomogram based on enhanced CT features (M1) consisted of Rad-score, LD, SD, CTpre, shape, homogeneity and N/C (AUC: training, 0.957; validation, 0.967). The pre-enhanced CT features based radiomic nomogram (M2) included Rad-score, LD, SD, CTpre, shape, and homogeneity (AUC: training, 0.955; validation, 0.958).
Our radiomic nomograms based on pre-enhanced and enhanced CT images distinguished sPHEO from LPA. In addition, the promising result using pre-enhanced CT images for predictive diagnostics is important because patients could avoid the additional radiation and risk associated with enhanced CT.
KeywordsAdrenal gland neoplasms Pheochromocytoma Adrenal adenoma Predictive preventive personalized medicine Computed tomography Radiomics
Area under the receiver operating characteristic curve
Pre-enhanced CT value
Enhanced CT value
Intraclass correlation coefficient
Least absolute shrinkage and selection operator
Lipid-poor adrenal adenoma
Magnetic resonance imaging
Necrosis or cystic degeneration
Positron emission tomography
Receiver operating characteristic
We thank Taihao Jin (Ph.D), from the Department of Diagnostic Radiology (City of Hope National Medical Center) for helpful discussion and assistance in preparing the manuscript. Editing assistance was provided by Nancy Linford, PhD.
This study is partially supported in part by China Postdoctoral Science Foundation funded project (2018M632997) and The Postdoctoral Science Foundation of Central South University (No. 185705).
Compliance with ethical standards
The authors declare that they have no competing interests.
Consent for publication
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. For this type of study, formal consent is not required.
- 3.Golubnitschaja O, Costigliola V. General report and recommendations in predictive, preventive and personalised medicine 2012: white paper of the European Association for Predictive, Preventive and Personalised Medicine. EPMA J. 2012;3:14. https://doi.org/10.1186/1878-5085-3-14.CrossRefPubMedPubMedCentralGoogle Scholar
- 4.Umanodan T, Fukukura Y, Kumagae Y, Shindo T, Nakajo M, Takumi K, et al. ADC histogram analysis for adrenal tumor histogram analysis of apparent diffusion coefficient in differentiating adrenal adenoma from pheochromocytoma. J Magn Reson Imaging. 2017;45:1195–203. https://doi.org/10.1002/jmri.25452.CrossRefGoogle Scholar
- 13.Dennie C, Thornhill R, Sethi-Virmani V, Souza CA, Bayanati H, Gupta A, et al. Role of quantitative computed tomography texture analysis in the differentiation of primary lung cancer and granulomatous nodules. Quant Imaging Med Surg. 2016;6:6–15. https://doi.org/10.3978/j.issn.2223-4292.2016.02.01.CrossRefPubMedPubMedCentralGoogle Scholar
- 14.Feng Z, Rong P, Cao P, Zhou Q, Zhu W, Yan Z, et al. Machine learning-based quantitative texture analysis of CT images of small renal masses: differentiation of angiomyolipoma without visible fat from renal cell carcinoma. Eur Radiol. 2017;28:1625–33. https://doi.org/10.1007/s00330-017-5118-z.CrossRefPubMedGoogle Scholar
- 26.Bogowicz M, Riesterer O, Ikenberg K, Stieb S, Moch H, Studer G, et al. Computed tomography radiomics predicts HPV status and local tumor control after definitive radiochemotherapy in head and neck squamous cell carcinoma. Int J Radiat Oncol Biol Phys. 2017;99:921–8. https://doi.org/10.1016/j.ijrobp.2017.06.002.CrossRefPubMedGoogle Scholar
- 32.Feng Z, Rong P, Cao P, Zhou Q, Zhu W, Yan Z, et al. Machine learning-based quantitative texture analysis of CT images of small renal masses: differentiation of angiomyolipoma without visible fat from renal cell carcinoma. Eur Radiol. 2018;28:1625–33. https://doi.org/10.1007/s00330-017-5118-z.CrossRefGoogle Scholar