Conventional and radiomic features to predict pathology in the preoperative assessment of anterior mediastinal masses. (April 2023)

• Record Type: Journal Article
• Authors: Mayoral, Maria; Pagano, Andrew M.; Araujo-Filho, Jose Arimateia Batista; Zheng, Junting; Perez-Johnston, Rocio; Tan, Kay See; Gibbs, Peter; Fernandes Shepherd, Annemarie; Rimner, Andreas; Simone II, Charles B.; Riely, Gregory; Huang, James; Ginsberg, Michelle S.
• Is Part Of: Lung cancer. Volume 178(2023)
• Page Start: 206
• Page End: 212
• Publication Date: 2023-04
• Subjects: Thymic epithelial tumors -- Computed tomography -- Radiomics -- Artificial intelligence -- Machine learning; Lungs -- Cancer -- Periodicals; Lung Neoplasms -- Abstracts; Lung Neoplasms -- Periodicals; Poumons -- Cancer -- Périodiques; Lungs -- Cancer; Periodicals; Electronic journals; Electronic journals; 616.99424
• DOI: 10.1016/j.lungcan.2023.02.014
• Languages: English
• ISSNs: 0169-5002

Abstract

Highlights: Machine learning analysis of CT features could predict pathology of mediastinal masses. The diagnostic performance to differentiate benign from malignant lesions was moderate. The diagnostic performance to differentiate thymomas from thymic carcinomas was good. The best performance was achieved when conventional and radiomic features were used. This approach would benefit therapy planning and allow personalized medicine. Abstract: Objectives: The aim of this study was to differentiate benign from malignant tumors in the anterior mediastinum based on computed tomography (CT) imaging characteristics, which could be useful in preoperative planning. Additionally, our secondary aim was to differentiate thymoma from thymic carcinoma, which could guide the use of neoadjuvant therapy. Materials and methods: Patients referred for thymectomy were retrospectively selected from our database. Twenty-five conventional characteristics were evaluated by visual analysis, and 101 radiomic features were extracted from each CT. In the step of model training, we applied support vector machines to train classification models. Model performance was assessed using the area under the receiver operating curves (AUC). Results: Our final study sample comprised 239 patients, 59 (24.7 %) with benign mediastinal lesions and 180 (75.3 %) with malignant thymic tumors. Among the malignant masses, there were 140 (58.6 %) thymomas, 23 (9.6 %) thymic carcinomas, and 17 (7.1 %) non-thymic lesions. For the benign versus malignant differentiation, the model that integrated both conventional and radiomic features achieved the highest diagnostic performance (AUC = 0.715), in comparison to the conventional (AUC = 0.605) and radiomic-only (AUC = 0.678) models. Similarly, regarding thymoma versus thymic carcinoma differentiation, the model that integrated both conventional and radiomic features also achieved the highest diagnostic performance (AUC = 0.810), in comparison to the conventional (AUC = 0.558) and radiomic-only (AUC = 0.774) models. Conclusion: CT-based conventional and radiomic features with machine learning analysis could be useful for predicting pathologic diagnoses of anterior mediastinal masses. The diagnostic performance was moderate for differentiating benign from malignant lesions and good for differentiating thymomas from thymic carcinomas. The best diagnostic performance was achieved when both conventional and radiomic features were integrated in the machine learning algorithms.