Yang Le, Zhang Sien, Li Jinsong, Feng Chongjin, Zhu Lijun, Li Jingyuan, Lin Lisong, Lv Xiaozhi, Su Kai, Lao Xiaomei, Chen Jufeng, Cao Wei, Li Siyi, Tang Hongyi, Chen Xueying, Liang Lizhong, Shang Wei, Cao Zhongyi, Qiu Fangsong, Li Jun, Luo Wenhao, Gao Siyong, Wang Shuqin, Zeng Bin, Duan Wan, Ji Tong, Liao Guiqing, Liang Yujie
Department of Oral and Maxillofacial Surgery, Guanghua School of Stomatology, Hospital of Stomatology, Sun Yat-sen University, Guangzhou, Guangdong, China; Guangdong Province Key Laboratory of Stomatology, Guangzhou, Guangdong, China.
Department of Oral and Maxillofacial Surgery, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China; Oral & Maxillofacial-Head & Neck Digital Precision Reconstruction Technology Research Center of Guangdong Province, Guangzhou, China.
Oral Oncol. 2025 Feb;161:107165. doi: 10.1016/j.oraloncology.2024.107165. Epub 2025 Jan 2.
Cervical lymph node metastasis (LNM) is a well-established poor prognosticator of oral squamous cell carcinoma (OSCC), in which occult metastasis is a subtype that makes prediction challenging. Here, we developed and validated a deep learning (DL) model using magnetic resonance imaging (MRI) for the identification of LNM in OSCC patients.
This retrospective diagnostic study developed a three-stage DL model by 45,664 preoperative MRI images from 723 patients in 10 Chinese hospitals between January 2015 and October 2020. It was comprehensively processed from training (8:2), multicenter external validation to reader study. The performance of the DL model was accessed and compared with general and specialized radiologists.
LNM was found in 36.51% of all patients, and the occult metastasis rate was 16.45%. The three-stage DL model together with a random forest classifier achieved the performance in identification of LNM with areas under curve (AUC) of 0.97 (0.93-0.99) in training cohort and AUC of 0.81 (0.74-0.86) in external validation cohorts. The models can reduce the occult metastasis rate up to 89.50% and add more benefit in guiding neck dissection in cN0 patients. DL models tied or exceeded average performance relative to both general and specialized radiologists.
Our three-stage DL model based on MRI with three-dimensional sequences was beneficial in detecting LNM and reducing the occult metastasis rate of OSCC patients.
颈部淋巴结转移（LNM）是口腔鳞状细胞癌（OSCC）公认的预后不良指标，其中隐匿性转移是一种难以预测的亚型。在此，我们开发并验证了一种基于磁共振成像（MRI）的深度学习（DL）模型，用于识别OSCC患者的LNM。
这项回顾性诊断研究利用2015年1月至2020年10月期间中国10家医院723例患者的45664张术前MRI图像开发了一个三阶段DL模型。该模型经过了从训练（8:2）、多中心外部验证到阅片者研究的全面处理。评估了DL模型的性能，并与普通放射科医生和专科放射科医生进行了比较。
在所有患者中，36.51%发现有LNM，隐匿性转移率为16.45%。三阶段DL模型与随机森林分类器相结合，在训练队列中识别LNM的曲线下面积（AUC）为0.97（0.93 - 0.99），在外部验证队列中AUC为0.81（0.74 - 0.86）。该模型可将隐匿性转移率降低至89.50%，并在指导cN0患者的颈部清扫方面带来更多益处。DL模型在性能上与普通放射科医生和专科放射科医生相当或超过他们。
我们基于具有三维序列的MRI的三阶段DL模型有助于检测OSCC患者的LNM并降低隐匿性转移率。
