Feng Na, Zhao Shanshan, Wang Kai, Chen Peizhe, Wang Yunpeng, Gao Yuan, Wang Zhengping, Lu Yidan, Chen Chen, Yao Jincao, Lei Zhikai, Xu Dong
Department of Ultrasound, Zhejiang Cancer Hospital, Hangzhou 310022, China.
Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou 310000, China.
Eur J Radiol Open. 2024 Oct 31;13:100609. doi: 10.1016/j.ejro.2024.100609. eCollection 2024 Dec.
To develop a ultrasound images based dual-channel deep learning model to achieve accurate early diagnosis of thyroid nodules less than 1 cm.
A dual-channel deep learning model called thyroid nodule transformer network (TNT-Net) was proposed. The model has two input channels for transverse and longitudinal ultrasound images of thyroid nodules, respectively. A total of 9649 nodules from 8455 patients across five hospitals were retrospectively collected. The data were divided into a training set (8453 nodules, 7369 patients), an internal test set (565 nodules, 512 patients), and an external test set (631 nodules, 574 patients).
TNT-Net achieved an area under the curve (AUC) of 0.953 (95 % confidence interval (CI): 0.934, 0.969) on the internal test set and 0.941 (95 % CI: 0.921, 0.957) on the external test set, significantly outperforming traditional deep convolutional neural network models and single-channel swin transformer model, whose AUCs ranged from 0.800 (95 % CI: 0.759, 0.837) to 0.856 (95 % CI: 0.819, 0.881). Furthermore, feature heatmap visualization showed that TNT-Net could extract richer and more energetic malignant nodule patterns.
The proposed TNT-Net model significantly improved the recognition capability for thyroid nodules with size less than 1 cm. This model has the potential to reduce overdiagnosis and overtreatment of such nodules, providing essential support for precise management of thyroid nodules while complementing fine-needle aspiration biopsy.
开发一种基于超声图像的双通道深度学习模型，以实现对小于1厘米的甲状腺结节的准确早期诊断。
提出了一种名为甲状腺结节变压器网络（TNT-Net）的双通道深度学习模型。该模型分别有两个用于甲状腺结节横向和纵向超声图像的输入通道。回顾性收集了来自五家医院的8455例患者的9649个结节。数据分为训练集（8453个结节，7369例患者）、内部测试集（565个结节，512例患者）和外部测试集（631个结节，574例患者）。
TNT-Net在内部测试集上的曲线下面积（AUC）为0.953（95%置信区间（CI）：0.934，0.969），在外部测试集上为0.941（95%CI：0.921，0.957），显著优于传统深度卷积神经网络模型和单通道swin变压器模型，其AUC范围为0.800（95%CI：0.759，0.837）至0.856（95%CI：0.819，0.881）。此外，特征热图可视化显示TNT-Net可以提取更丰富、更有活力的恶性结节模式。
所提出的TNT-Net模型显著提高了对小于1厘米的甲状腺结节的识别能力。该模型有可能减少此类结节的过度诊断和过度治疗，为甲状腺结节的精确管理提供重要支持，同时补充细针穿刺活检。
