Risk prediction model establishment with tri-phasic CT image features for differential diagnosis of adrenal pheochromocytomas and lipid-poor adenomas: Grouping method

Abstract

Objectives: The purpose of this study was to establish a risk prediction model for differential diagnosis of pheochromocytomas (PCCs) from lipid-poor adenomas (LPAs) using a grouping method based on tri-phasic CT image features.

Methods: In this retrospective study, we enrolled patients that were assigned to a training set (136 PCCs and 183 LPAs) from two medical centers, along with an external independent validation set (30 PCCs and 54 LPAs) from another center. According to the attenuation values in unenhanced CT (CTu), the lesions were divided into three groups: group 1, 10 HU < CTu ≤ 25 HU; group 2, 25 HU < CTu ≤ 40 HU; and group 3, CTu > 40 HU. Quantitative and qualitative CT imaging features were calculated and evaluated. Univariate, ROC, and binary logistic regression analyses were applied to compare these features.

Results: Cystic degeneration, CTu, and the peak value of enhancement in the arterial and venous phase (DEpeak) were independent risk factors for differential diagnosis of adrenal PCCs from LPAs. In all subjects (groups 1, 2, and 3), the model formula for the differentiation of PCCs was as follows: Y = -7.709 + 3.617*(cystic degeneration) + 0.175*(CTu ≥ 35.55 HU) + 0.068*(DEpeak ≥ 51.35 HU). ROC curves were drawn with an AUC of 0.95 (95% CI: 0.927-0.973) in the training set and 0.91 (95% CI: 0.860-0.929) in the external validation set.

Conclusion: A reliable and practical prediction model for differential diagnosis of adrenal PCCs and LPAs was established using a grouping method.

Keywords: adenomas; adrenal; computed tomography; pheochromocytomas; risk prediction model.

Figure 1

Flowchart shows exclusion criteria for the study. PCCs, pheochromocytomas. LRAs, lipid-rich adenomas. LPAs, lipid-poor adenomas. Group 1: 10 HU < CTu ≤ 25 HU. Group 2: 25 HU < CTu ≤ 40 HU. Group 3: CTu > 40 HU.

Figure 2

(A) Graph shows ROC of CTu for differentiating PCCs from LPAs in group 1. (B) Graph shows ROCs of CTu, CTv, DEpeak, LD, and SD in group 2. (C) Graph shows ROCs of LD and SD in group 3. (D) Graph shows ROCs of CTu, CTa, CTv, DEpeak, RPW, LD, and SD in all subjects (groups 1, 2, and 3).

Figure 3

(A) ROC analysis of the model in group 2 on the training set. The AUC was 0.94 (95% CI: 0.902–0.984), with accuracy, sensitivity, specificity of 88.7, 90.4, and 87.0%, respectively. (B) ROC analysis of the model in group 2 on the external validation set. The AUC was 0.91 (95% CI, 0.823–0.927) with accuracy, sensitivity, and specificity of 82.2, 69.0, and 90.0%, respectively.

Figure 4

(A) ROC analysis of the model in all subjects (groups 1, 2, and 3) on the training set. The value of the AUC was 0.95 (95% CI: 0.927–0.973). The accuracy, sensitivity, and specificity of the model were 87.1, 91.2, and 82.0%, respectively. (B) ROC analysis of the model in all subjects (groups 1, 2, and 3) on the external validation set. The AUC was 0.91 (95% CI, 0.860–0.929), with accuracy, sensitivity, and specificity of 80.9, 64.5, and 90.6%, respectively.

Figure 5

 A left adrenal LPA in a 63-year-old man. (A) Axial unenhanced phase. (B) Axial arterial phase. (C) Axial venous phase. The values of CTu, CTa, CTv, and DEpeak were 25.23, 70.61, 75.02, and 49.79 HU, respectively. LD and SD of the mass were 25 and 20 mm. No cystic degeneration was seen within the tumor.

Figure 6

 A left adrenal PCC in a 57-year-old man. (A) Axial unenhanced phase. (B) Axial arterial phase. (C) Axial venous phase. The values of CTu, CTa, CTv, and DEpeak were 37.54, 105.17, 128.79, and 91.25 HU, respectively. LD and SD of the mass were 40 and 38 mm. Cystic degeneration was seen within the Lesion (red star).