Dataset Information

Development and Validation of a Clinical-Image Model for Quantitatively Distinguishing Uncertain Lipid-Poor Adrenal Adenomas From Nonadenomas

ABSTRACT:

Background

There remains a demand for a practical method of identifying lipid-poor adrenal lesions.

Purpose

To explore the predictive value of computed tomography (CT) features combined with demographic characteristics for lipid-poor adrenal adenomas and nonadenomas.

Materials and Methods

We retrospectively recruited patients with lipid-poor adrenal lesions between January 2015 and August 2021 from two independent institutions as follows: Institution 1 for the training set and the internal validation set and Institution 2 for the external validation set. Two radiologists reviewed CT images for the three sets. We performed a least absolute shrinkage and selection operator (LASSO) algorithm to select variables; subsequently, multivariate analysis was used to develop a generalized linear model. The probability threshold of the model was set to 0.5 in the external validation set. We calculated the sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) for the model and radiologists. The model was validated and tested in the internal validation and external validation sets; moreover, the accuracy between the model and both radiologists were compared using the McNemar test in the external validation set.

Results

In total, 253 patients (median age, 55 years [interquartile range, 47–64 years]; 135 men) with 121 lipid-poor adrenal adenomas and 132 nonadenomas were included in Institution 1, whereas another 55 patients were included in Institution 2. The multivariable analysis showed that age, male, lesion size, necrosis, unenhanced attenuation, and portal venous phase attenuation were independently associated with adrenal adenomas. The clinical-image model showed AUCs of 0.96 (95% confidence interval [CI]: 0.91, 0.98), 0.93 (95% CI: 0.84, 0.97), and 0.86 (95% CI: 0.74, 0.94) in the training set, internal validation set, and external validation set, respectively. In the external validation set, the model showed a significantly and non-significantly higher accuracy than reader 1 (84% vs. 65%, P = 0.031) and reader 2 (84% vs. 69%, P = 0.057), respectively.

Conclusions

Our clinical-image model displayed good utility in differentiating lipid-poor adrenal adenomas. Further, it showed better diagnostic ability than experienced radiologists in the external validation set.

SUBMITTER: Pan W

PROVIDER: S-EPMC9326106 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposeTo evaluate T2-weighted MRI features to differentiate adrenal metastases from lipid-poor adenomas.Materials and methodsWith institutional review board approval, this study retrospectively compared 40 consecutive patients (mean age, 66 years ± 10 [standard deviation]) with metastases to 23 patients (mean age, 60 years ± 15) with lipid-poor adenomas at 1.5- and 3-T MRI between June 2016 and March 2019. A blinded radiologist measured T2-weighted signal intensity (SI) ratio (SInodule/SIpsoas muscle), T2-weighted histogram features, and chemical shift SI index. Two blinded radiologists (radiologist 1 and radiologist 2) assessed T2-weighted SI and T2-weighted heterogeneity using five-point Likert scales.ResultsSubjectively, T2-weighted SI (P < .001 for radiologist 1 and radiologist 2) and T2-weighted heterogeneity (P < .001, for radiologist 1 and radiologist 2) were higher in metastases compared with adenomas when assessed by both radiologists. Agreement between the radiologists was substantial for T2-weighted SI (Cohen κ = 0.67) and T2-weighted heterogeneity (κ = 0.62). Metastases had higher T2-weighted SI ratio than adenomas (3.6 ± 1.7 [95% confidence interval {CI}: 0.2, 8.2] vs 2.2 ± 1.0 [95% CI: 0.6, 4.3], P < .001) and higher T2-weighted entropy (6.6 ± 0.6 [95% CI: 4.9, 7.5] vs 5.0 ± 0.8 [95% CI: 3.5, 6.6], P < .001). At multivariate analysis, T2-weighted entropy was the best differentiating feature (P < .001). Chemical shift SI index did not differ between metastases and adenomas (P = .748). Area under the receiver operating characteristic curve (AUC) for T2-weighted SI ratio and T2-weighted entropy were 0.76 (95% CI: 0.64, 0.88) and 0.94 (95% CI: 0.88, 0.99). The logistic regression model combining T2-weighted SI ratio with T2-weighted entropy yielded AUC of 0.95 (95% CI: 0.91, 0.99) and did not differ compared with T2-weighted entropy alone (P = .268). There was no difference in logistic regression model accuracy comparing the data by either field strength, 1.5- or 3-T MRI (P > .05).ConclusionLogistic regression models combining T2-weighted SI and T2-weighted heterogeneity can differentiate metastases from lipid-poor adenomas. Validation of these preliminary results is required.Keywords: Adrenal, MR-Imaging, UrinarySupplemental material is available for this article.© RSNA, 2020.

Project description:ObjectivesIn this study, we developed a radiomic signature for the classification of benign lipid-poor adenomas, which may potentially help clinicians limit the number of unnecessary investigations in clinical practice. Indeterminate adrenal lesions of benign and malignant nature may exhibit different values of key radiomics features.MethodsPatients who had available histopathology reports and a non-contrast-enhanced CT scan were included in the study. Radiomics feature extraction was done after the adrenal lesions were contoured. The primary feature selection and prediction performance scores were calculated using the least absolute shrinkage and selection operator (LASSO). To eliminate redundancy, the best-performing features were further examined using the Pearson correlation coefficient, and new predictive models were created.ResultsThis investigation covered 50 lesions in 48 patients. After LASSO-based radiomics feature selection, the test dataset's 30 iterations of logistic regression models produced an average performance of 0.72. The model with the best performance, made up of 13 radiomics features, had an AUC of 0.99 in the training phase and 1.00 in the test phase. The number of features was lowered to 5 after performing Pearson's correlation to prevent overfitting. The final radiomic signature trained a number of machine learning classifiers, with an average AUC of 0.93.ConclusionsIncluding more radiomics features in the identification of adenomas may improve the accuracy of NECT and reduce the need for additional imaging procedures and clinical workup, according to this and other recent radiomics studies that have clear points of contact with current clinical practice.Clinical relevance statementThe study developed a radiomic signature using unenhanced CT scans for classifying lipid-poor adenomas, potentially reducing unnecessary investigations that scored a final accuracy of 93%.Key points• Radiomics has potential for differentiating lipid-poor adenomas and avoiding unnecessary further investigations. • Quadratic mean, strength, maximum 3D diameter, volume density, and area density are promising predictors for adenomas. • Radiomics models reach high performance with average AUC of 0.95 in the training phase and 0.72 in the test phase.