Diagnostic Accuracy of CT Texture Analysis in Adrenal Masses: A Systematic Review

Abstract

Adrenal incidentalomas (AIs) are incidentally discovered adrenal neoplasms. Overt endocrine secretion (glucocorticoids, mineralocorticoids, and catecholamines) and malignancy (primary or metastatic disease) are assessed at baseline evaluation. Size, lipid content, and washout characterise benign AIs (respectively, <4 cm, <10 Hounsfield unit, and rapid release); nonetheless, 30% of adrenal lesions are not correctly indicated. Recently, image-based texture analysis from computed tomography (CT) may be useful to assess the behaviour of indeterminate adrenal lesions. We performed a systematic review to provide the state-of-the-art of texture analysis in patients with AI. We considered 9 papers (from 70 selected), with a median of 125 patients (range 20–356). Histological confirmation was the most used criteria to differentiate benign from the malignant adrenal mass. Unenhanced or contrast-enhanced data were available in all papers; TexRAD and PyRadiomics were the most used software. Four papers analysed the whole volume, and five considered a region of interest. Different texture features were reported, considering first- and second-order statistics. The pooled median area under the ROC curve in all studies was 0.85, depicting a high diagnostic accuracy, up to 93% in differentiating adrenal adenoma from adrenocortical carcinomas. Despite heterogeneous methodology, texture analysis is a promising diagnostic tool in the first assessment of patients with adrenal lesions.

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

“…Recently, several papers have been published regarding to the application of radiomics in patients with adrenal lesions. Results coming from these studies, performed especially to discriminate benign from malignant lesions, appear to be very promising (23). Keeping in mind that approximately 50% of AIs produce more cortisol and about diagnostic pitfalls occurring in adrenal masses characterization, we speculate on the properties of radiomics to discriminate cortisolsecreting from not-secreting AIs.…”

“…Up to now, most of radiomics studies have been performed in oncologic field with surprising results (7). Furthermore, as supported by the review from Crimì et al (23), encouraging data come from texture analysis in adrenal lesions. This study moves the field of application of radiomics in the context of functional adrenal disease trying to overcome some of the pitfalls described above, proposing it as a useful tool for clinical investigation.…”

“…The analysis of each ROI included features derived from first-order histogram (HIS), co-occurrence matrix (COM), run-length matrix (RLM), absolute gradient (GRA), autoregressive model (ARM), and discrete Haar wavelet transform (WAV), for a maximum of 291 features, as shown specifically in the Supplementary Materials, to which are added 23…”

Computerized tomography texture analysis of pheochromocytoma: relationship with hormonal and histopathological data

“…Furthermore, another limit is that this study does not address the main radiologic diagnostic challenge regarding the adrenal glands, which is discriminating malignant from benign lesions. This is a potential use of texture analysis, which already demonstrated an accuracy up to 93% in this task [ 20 ]. However, this study aimed to give even more purpose to the data extracted in the setting of the studies regarding the discrimination of adrenal incidentalomas.…”

Adrenal Lesions: A Review of Imaging

“…In addition, the latest evidence shows that texture analysis features based on CT and MRI images allow for differentiating malignant from benign adrenal lesions with good accuracy. If a suspected malignant or functioning form is found, a multidisciplinary team should plan an appropriate follow-up [ 15 ]. Moreover, recent studies reported that the inactivating variants in the ARMC5 (Amadilo repeats containing 5; OMIM 615,549) gene located on chromosome 16p11.2 are the most common genetic cause of PBMAH (primary bilateral macronodular adrenal hyperplasia), which is a rare type of Cushing syndrome characterized by the bilateral enlargement of the adrenal glands, large adrenal nodules (>10 mm), and increased cortisol production.…”