Wang Yaoqin, Xie Wenting, Huang Shixin, Feng Ming, Ke Xiaohui, Zhong Zhaoming, Tang Lina
Department of Ultrasound, Fujian Medical University Cancer Hospital, Fujian Cancer Hospital, Fuzhou, 350014 Fujian Province, China.
College of Electronic and Information Engineering, Tongji University, Shanghai 201804, China.
J Oncol. 2022 May 12;2022:8192999. doi: 10.1155/2022/8192999. eCollection 2022.
Evidence suggests that about 80% of all salivary gland tumors involve the parotid glands, with approximately 20% of parotid gland tumors (PGTs) being malignant. Discriminating benign and malignant parotid gland lesions preoperatively is vital for selecting the appropriate treatment strategy. This study explored the diagnostic performance of deep learning system for discriminating benign and malignant PGTs in ultrasonography images and compared it with radiologists. A total of 251 consecutive patients with surgical resection and proven parotid gland malignant or benign tumors who underwent preoperative ultrasound examinations were enrolled in this study between January 2014 and November 2020. Next, we compared the diagnostic accuracy of deep learning methods (ViT-B\16, EfficientNetB3, DenseNet121, and ResNet50) and radiologists in parotid gland tumor. In addition, the area under the curve (AUC), specificity, sensitivity, positive predictive value, and negative predictive value were calculated.
Among the 251 patients, 176/251 were the training set, whereas 75/251 were the validation set. Results showed that 74/251 patients had malignant tumor. Deep learning models achieved good performance in differentiating benign from malignant tumors, with the diagnostic accuracy and AUCs of ViT-B\16, EfficientNetB3, DenseNet121, and ResNet50 model being 81% and 0.81, 80% and 0.82, 77% and 0.81, and 79% and 0.80, respectively. On the other hand, the diagnostic accuracy and AUCs of radiologists were 77%-81% and 0.68-0.75, respectively. It was evident that the diagnostic accuracy of deep learning methods was higher than that of inexperienced radiologists, but there was no significant difference between deep learning methods and experienced radiologists.
This study shows that the deep learning system can be used for diagnosing parotid tumors. The findings also suggest that the deep learning system may improve the diagnosis performance of inexperienced radiologists.
有证据表明，约80%的涎腺肿瘤累及腮腺，其中约20%的腮腺肿瘤（PGT）为恶性。术前鉴别腮腺良性和恶性病变对于选择合适的治疗策略至关重要。本研究探讨了深度学习系统在超声图像中鉴别腮腺良恶性肿瘤的诊断性能，并与放射科医生进行了比较。2014年1月至2020年11月期间，本研究共纳入了251例接受术前超声检查且经手术切除证实为腮腺恶性或良性肿瘤的连续患者。接下来，我们比较了深度学习方法（ViT-B\16、EfficientNetB3、DenseNet121和ResNet50）和放射科医生在腮腺肿瘤诊断中的准确性。此外，还计算了曲线下面积（AUC）、特异性、敏感性、阳性预测值和阴性预测值。
251例患者中，176/251为训练集，75/251为验证集。结果显示，74/251例患者患有恶性肿瘤。深度学习模型在鉴别良性和恶性肿瘤方面表现良好，ViT-B\16、EfficientNetB3、DenseNet121和ResNet50模型的诊断准确率和AUC分别为81%和0.81、80%和0.82、77%和0.81、79%和0.80。另一方面，放射科医生的诊断准确率和AUC分别为77%-81%和0.68-0.75。显然，深度学习方法的诊断准确率高于经验不足的放射科医生，但深度学习方法与经验丰富的放射科医生之间没有显著差异。
本研究表明，深度学习系统可用于诊断腮腺肿瘤。研究结果还表明，深度学习系统可能会提高经验不足的放射科医生的诊断性能。
