AUTHOR=Maggio Roberta , Messina Filippo , D’Arrigo Benedetta , Maccagno Giacomo , Lardo Pina , Palmisano Claudia , Poggi Maurizio , Monti Salvatore , Matarazzo Iolanda , Laghi Andrea , Pugliese Giuseppe , Stigliano Antonio 

TITLE=Machine Learning-Based Texture Analysis in the Characterization of Cortisol Secreting vs. Non-Secreting Adrenocortical Incidentalomas in CT Scan

JOURNAL=Frontiers in Endocrinology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2022.873189

DOI=10.3389/fendo.2022.873189

ISSN=1664-2392

ABSTRACT=New radioimaging techniques, exploiting the quantitative variables of imaging, permit to identify an hypothetical pathological tissue. We have applied this potential in a series of 72 adrenal incidentalomas followed at our center, subdivided in functioning and non functioning using laboratory findings.
Each incidentaloma was studied in the preliminary non-contrast phase with a specific software (Mazda), surrounding a region of interest within each lesion. 314 features were extrapolated. Mean and standard deviations of features were obtained and the difference in means between the two groups was statistically analyzed. ROC curves were used to identify an optimal cut off for each variable and a prediction model was constructed via multivariate logistic regression with backward and stepwise selection.
A 11-variables prediction model was constructed and a ROC curve was used to differentiate patients with high probability of functioning incidentalomas. Using a specific threshold value we obtained a sensitivity of 93.75% and a specificity of 100% in diagnosing functioning incidentaloma.
Based on these results, computed tomography (CT) texture analysis appears a promising tool in the diagnostic definition of adrenal incidentalomas.