Deep learning‐assisted diagnosis of parotid gland tumors by using contrast‐enhanced CT imaging

• Published in: Oral diseases Vol. 29; no. 8; pp. 3325 - 3336
• Main Authors: Shen, Xue‐Meng, Mao, Liang, Yang, Zhi‐Yi, Chai, Zi‐Kang, Sun, Ting‐Guan, Xu, Yongchao, Sun, Zhi‐Jun
• Format: Journal Article
• Language: English
• Published: Denmark Wiley Subscription Services, Inc 01.11.2023
• Subjects: binary classification; Computed tomography; contrast‐enhanced computed tomography (CECT); convolutional neural network; Deep learning; Exocrine glands; Malignancy; Oral cancer; Parotid gland; parotid gland tumor; Statistical analysis; Tumors; deep learning; contrast-enhanced computed tomography (CECT); binary classification; parotid gland tumor; convolutional neural network
• ISSN: 1354-523X; 1601-0825; 1601-0825
• DOI: 10.1111/odi.14474

Objectives Imaging interpretation of the benignancy or malignancy of parotid gland tumors (PGTs) is a critical consideration prior to surgery in view of therapeutic and prognostic values of such discrimination. This study investigates the application of a deep learning‐based method for preoperative stratification of PGTs. Materials and Methods Using the 3D DenseNet‐121 architecture and a dataset consisting of 117 volumetric arterial‐phase contrast‐enhanced CT scans, we developed a binary classifier for PGT distinction and tested it. We compared the discriminative performance of the model on the test set to that of 12 junior and 12 senior head and neck clinicians. Besides, potential clinical utility of the model was evaluated by measuring changes in unassisted and model‐assisted performance of junior clinicians. Results The model finally reached the sensitivity, specificity, PPV, NPV, F1‐score of 0.955 (95% CI 0.751–0.998), 0.667 (95% CI 0.241–0.940), 0.913 (95% CI 0.705–0.985), 0.800 (95% CI 0.299–0.989) and 0.933, respectively, comparable to that of practicing clinicians. Furthermore, there were statistically significant increases in junior clinicians' specificity, PPV, NPV and F1‐score in differentiating benign from malignant PGTs when unassisted and model‐assisted performance of junior clinicians were compared. Conclusion Our results provide evidence that deep learning‐based method may offer assistance for PGT's binary distinction.