Distinguishing metastases from benign adrenal masses: what can CT texture analysis do?

Abstract

Background Computed tomography texture analysis (CTTA) has gained an increasing role in oncology and has successfully demonstrated to reflect biological associations with glucose metabolism, hypoxia, angiogenesis, and even genetic variation. Purpose To determine whether quantitative CTTA can be used to differentiate metastases from benign adrenal masses on single energy CT images. Material and Methods A total of 225 patients with 265 histologically confirmed adrenal masses (101 metastases, 98 pheochromocytomas, and 66 lipid-poor adenomas) were included in this retrospective study. CTTA was performed and six texture parameters (including mean, SD of pixel distribution histogram, mean of positive pixels, entropy, kurtosis, skewness) across six spatial scaling factor (SSF) were recorded on both unenhanced and contrast-enhanced CT images. Receiver operating characteristic (ROC) analysis was performed and the area under the ROC curve (AUC) was calculated using the significant texture parameters for the objective. Diagnostic performance was evaluated using the cut-off values of texture parameters by ROC analysis. The optimal discriminative texture parameters were used to produce support vector machine (SVM) classifiers. Diagnostic accuracy and 10-fold cross-validation was performed. Results Compared to benign adrenal masses, metastases had significantly lower mean gray-level intensity, SD, entropy, mean of positive pixels and kurtosis on unenhanced images (P < 0.0083). On contrast-enhanced CT images, except for skewness and kurtosis, the other four texture texture-quantifiers were lower in the metastatic compared to the other group (P < 0.0083). A model incorporating mean, SD, entropy and mean value of positive pixels produced an AUC of 0.85 ± 0.03 with an SVM accuracy of 77% to identify metastatic from benign adrenal masses. Conclusion Differentiation of metastatic and benign adrenal masses can be achieved accurately with CTTA on contrast-enhanced CT images.

Utility of T2-weighted MRI to Differentiate Adrenal Metastases from Lipid-Poor Adrenal Adenomas

“…In our study, T2-weighted SI was also significantly lower in lipid-poor adenomas compared with a large group of adrenal metastases from various primary malignancies using both subjective and quantitative assessment with a five-point Likert scale and through the measurement of a simple T2weighted SI ratio. The use of texture analysis in adrenal assessment has been predominantly applied in CT, with few studies evaluating texture features of adrenal masses on MR images (24,(45)(46)(47)(48)(49)(50). In our study, both qualitative and quantitative analyses of tumor heterogeneity revealed that metastases were significantly more heterogeneous compared with lipid-poor adenomas, which is comparable to a prior study which compared adrenal metastases from renal cell carcinoma and adenomas at T2-weighted MRI (21).…”

Metastases or benign adrenal lesions in patients with histopathological verification of lung cancer: Can CT texture analysis distinguish?

“…They found no significant difference between mean grey-level intensity (58.2 ± 21.0 HU for metastases vs 55.5 ± 21.5 HU, p = 0.582); however, Shi et al in 2019 found metastases to have a significantly lower mean grey-level intensity and in the present study we find a significantly higher mean grey-level intensity in malignant adrenal lesions (50.60 CI95 % 46.85-54.34) compared to benign adrenal lesions (42.86 CI95 % 39.74-45.98). Furthermore, Shi et al found significantly lower entropy and mean of positive pixels in the metastatic group compared to the benign lesions [15]. We found both entropy and mean to be higher in the metastatic group compared to the benign.…”

“…Concerning adrenal lesions, CTTA has shown some promise in differentiating malignant from benign lesions. However, external validity of the findings in relation to lung cancer is hampered by small samples, single-center design, or non-lung cancer population [14][15][16][17].…”

Adrenal Incidentaloma

“…In a feasibility study of 164 patients with indeterminate adrenal lesions at CT (98 pheochromocytoma; 66 lipid-poor adrenal adenomas), intralesion textural features (mean gray-level intensity and mean positive pixels) extracted from unenhanced images allowed differentiation between adenoma and pheochromocytoma with an accuracy of 81% ( 378 ). In a recent larger patient cohort (n = 225) the same Chinese group has reported an accuracy of 77% for distinguishing metastases from benign adrenal lesions using this CT textural feature analysis technique ( 379 ). Other groups have shown similar results in small retrospective series evaluating the accuracy of MRI and PET-CT textural features for distinguishing benign and malignant adrenal lesions ( 380 , 381 ).…”