Evaluation of a fusion model combining deep learning models based on enhanced CT images with radiological and clinical features in distinguishing lipid-poor adrenal adenoma from metastatic lesions

• Published in: BMC medical imaging Vol. 25; no. 1; pp. 219 - 9
• Main Authors: Wang, Shao-Cai, Yin, Sheng-Nan, Wang, Zi-You, Ding, Ning, Ji, Yi-Ding, Jin, Long
• Format: Journal Article
• Language: English
• Published: London BioMed Central 01.07.2025; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Abdomen; Adenoma; Adenoma - diagnostic imaging; Adrenal gland; Adrenal Gland Neoplasms - diagnostic imaging; Adrenal Gland Neoplasms - pathology; Adrenal Gland Neoplasms - secondary; Adult; Aged; Artificial intelligence; Artificial neural networks; Automatic segmentation; Biopsy; Computed tomography; Contrast Media; CT imaging; Deep Learning; Diagnosis, Differential; Female; Humans; Imaging; Learning algorithms; Lesions; Lipids; Machine learning; Male; Medical imaging; Medicine; Medicine & Public Health; Metastases; Metastasis; Middle Aged; Neoplasm Metastasis; Neural networks; Neural Networks, Computer; Pathology; Patients; Performance evaluation; Radiographic Image Interpretation, Computer-Assisted - methods; Radiology; Retrospective Studies; Statistical analysis; Tomography, X-Ray Computed - methods; Tumors; Taiwan; Deep learning; Automatic segmentation; Adrenal gland; Adenoma; Metastasis; Machine learning
• ISSN: 1471-2342; 1471-2342
• DOI: 10.1186/s12880-025-01798-8

Objective To evaluate the diagnostic performance of a machine learning model combining deep learning models based on enhanced CT images with radiological and clinical features in differentiating lipid-poor adrenal adenomas from metastatic tumors, and to explain the model’s prediction results through SHAP(Shapley Additive Explanations) analysis. Methods A retrospective analysis was conducted on abdominal contrast-enhanced CT images and clinical data from 416 pathologically confirmed adrenal tumor patients at our hospital from July 2019 to December 2024. Patients were randomly divided into training and testing sets in a 7:3 ratio. Six convolutional neural network (CNN)-based deep learning models were employed, and the model with the highest diagnostic performance was selected based on the area under curve(AUC) of the ROC. Subsequently, multiple machine learning models incorporating clinical and radiological features were developed and evaluated using various indicators and AUC.The best-performing machine learning model was further analyzed using SHAP plots to enhance interpretability and quantify feature contributions. Results All six deep learning models demonstrated excellent diagnostic performance, with AUC values exceeding 0.8, among which ResNet50 achieved the highest AUC. Among the 10 machine learning models incorporating clinical and imaging features, the extreme gradient boosting(XGBoost) model exhibited the best accuracy(ACC), sensitivity, and AUC, indicating superior diagnostic performance.SHAP analysis revealed contributions from ResNet50, RPW, age, and other key features in model predictions. Conclusion Machine learning models based on contrast-enhanced CT combined with clinical and imaging features exhibit outstanding diagnostic performance in differentiating lipid-poor adrenal adenomas from metastases.