Conventional and radiomic features to predict pathology in the preoperative assessment of anterior mediastinal masses Journal Article
| Authors: | Mayoral, M.; Pagano, A. M.; Araujo-Filho, J. A. B.; Zheng, J.; Perez-Johnston, R.; Tan, K. S.; Gibbs, P.; Shepherd, A. F.; Rimner, A.; Simone, C. B. 2nd; Riely, G.; Huang, J.; Ginsberg, M. S. |
| Article Title: | Conventional and radiomic features to predict pathology in the preoperative assessment of anterior mediastinal masses |
| 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. © 2023 Elsevier B.V. |
| Keywords: | adult; controlled study; middle aged; major clinical study; clinical feature; patient selection; treatment planning; preoperative care; neoadjuvant therapy; diagnostic procedure; computer assisted tomography; tumor differentiation; retrospective study; prediction; artificial intelligence; clinical evaluation; thymoma; thymectomy; patient referral; computed tomography; thymic epithelial tumors; image segmentation; mediastinum mass; thymus carcinoma; machine learning; support vector machine; benign neoplasm; human; male; female; article; disease assessment; radiomics; malignant neoplasm |
| Journal Title: | Lung Cancer |
| Volume: | 178 |
| ISSN: | 0169-5002 |
| Publisher: | Elsevier Ireland Ltd. |
| Date Published: | 2023-04-01 |
| Start Page: | 206 |
| End Page: | 212 |
| Language: | English |
| DOI: | 10.1016/j.lungcan.2023.02.014 |
| PUBMED: | 36871345 |
| PROVIDER: | scopus |
| PMCID: | PMC10544811 |
| DOI/URL: | |
| Notes: | Article -- MSK Cancer Center Support Grant (P30 CA008748) acknowledged in PubMed and PDF -- Source: Scopus |
Altmetric
Citation Impact
MSK Authors
Related MSK Work