Radiomics utilization to differentiate nonfunctional adenoma in essential hypertension and functional adenoma in primary aldosteronism

Abstract

We performed the present study to investigate the role of computed tomography (CT) radiomics in differentiating nonfunctional adenoma and aldosterone-producing adenoma (APA) and outcome prediction in patients with clinically suspected primary aldosteronism (PA). This study included 60 patients diagnosed with essential hypertension (EH) with nonfunctional adenoma on CT and 91 patients with unilateral surgically proven APA. Each whole nodule on unenhanced and venous phase CT images was segmented manually and randomly split into training and test sets at a ratio of 8:2. Radiomic models for nodule discrimination and outcome prediction of APA after adrenalectomy were established separately using the training set by least absolute shrinkage and selection operator (LASSO) logistic regression, and the performance was evaluated on test sets. The model can differentiate adrenal nodules in EH and PA with a sensitivity, specificity, and accuracy of 83.3%, 78.9% and 80.6% (AUC = 0.91 [0.72, 0.97]) in unenhanced CT and 81.2%, 100% and 87.5% (AUC = 0.98 [0.77, 1.00]) in venous phase CT, respectively. In the outcome after adrenalectomy, the models showed a favorable ability to predict biochemical success (Unenhanced/venous CT: AUC = 0.67 [0.52, 0.79]/0.62 [0.46, 0.76]) and clinical success (Unenhanced/venous CT: AUC = 0.59 [0.47, 0.70]/0.64 [0.51, 0.74]). The results showed that CT-based radiomic models hold promise to discriminate APA and nonfunctional adenoma when an adrenal incidentaloma was detected on CT images of hypertensive patients in clinical practice, while the role of radiomic analysis in outcome prediction after adrenalectomy needs further investigation.

Application of a Radiomics Machine Learning Model for Differentiating Aldosterone-Producing Adenoma from Non-Functioning Adrenal Adenoma

“…Among the baseline clinical variables, age, Time, SBP, DBP, potassium level, and Radscore significantly differed between the APA and NAA groups. The differences in age and potassium level were consistent with the findings reported by Chen and Bioletto et al, wherein the patients in the APA group were younger and had lower potassium concentrations [16,23]. However, in the current study, patients with normal baseline blood pressure were included because of the possibility of subclinical PA.…”

“…Radiomics has the ability to predict adrenocortical carcinomas, metastatic carcinomas, pheochromocytomas, and APAs by quantitatively extracting the features of adrenal lesions before surgery [12][13][14][15]. One study reported that contrastenhanced CT (CECT)-based radiomics can be used to identify non-functioning adrenal adenomas (NAAs) in patients with EH and APAs in patients with PA [16]. However, the study only included patients with EH with NAA because some subclinical PA patients have APA tumors, but the clinical manifestations are normal; that is, there are no or only mild symptoms of hypertension and hypokalemia [17].…”

CT-based radiomics nomogram for differentiation of adrenal hyperplasia from lipid-poor adenoma: an exploratory study

“…For example, texture analysis was used for differentiating malignant from benign adrenal tumors [ 21 ]. Furthermore, Chen et al [ 28 ] and He et al [ 29 ] used radiomics signature and nomogram to confirm the risk of functional adenoma. Moreover, radiomics can be an effective medical approach for predicting subclinical pheochromocytoma from lipid-poor adenoma [ 22 ].…”

CT-based Radiomics Nomogram for Differentiation of Adrenal Hyperplasia from Lipid-poor Adenoma: An exploratory study

“…For example, texture analysis was used for differentiating malignant from benign adrenal tumors [21]. Furthermore, Chen et al [27] and He et al [28] used radiomics signature and nomogram to con rm the risk of functional adenoma. Moreover, radiomics can be an effective medical approach for predicting subclinical pheochromocytoma from lipid-poor adenoma [22].…”