基于自注意力机制的喉镜图像分类技术用于喉癌检测
研究收集1462例患者的5768张喉镜图像,构建基于Swin-Transformer的智能喉癌检测系统(ILCDS),并在内部和外部测试集上评估,与六种卷积神经网络(CNN)模型及三名专业喉科医生比较。ILCDS在内部集准确率92.78%、AUC 0.9732,外部集准确率85.79%、AUC 0.9550,均优于六种CNN;准确率92.00%超过专业喉科医生。结论认为ILCDS对喉癌检测具有高准确性和稳定性,可减轻喉科医生负担。
要点
- ILCDS内部测试集准确率92.78%、AUC 0.9732,优于六种CNN模型。
- 外部测试集准确率85.79%、AUC 0.9550,性能略有下降但仍最优。
- ILCDS准确率92.00%,超过三名专业喉科医生。
核心结论
- ILCDS对喉癌检测具有高准确性和稳定性,可减轻喉科医生负担。
研究设计与样本
- 研究收集1462例患者的5768张喉镜图像,构建基于Swin-Transformer的智能喉癌检测系统(ILCDS),经训练和验证后在内部与外部测试集评估,并与既往卷积神经网络(CNN)模型及三名专业喉科医生比较。
主要发现
- ILCDS优于六种CNN,内部测试集最高准确率92.78%,AUC 0.9732。
- 外部测试集性能略有下降,ILCDS仍保持最优,准确率85.79%,AUC 0.9550。
- ILCDS准确率92.00%,超过专业喉科医生。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: The early diagnosis of laryngeal cancer (LCA) is crucial for prognosis, driving our search for an accurate, precise, and sensitive deep learning model to assist in LCA detection. METHODS: We collected 5768 laryngoscopic images from 1462 patients and created the intelligent laryngeal cancer detection system (ILCDS) based on Swin-Transformer. Following training and validation, we assessed the ILCDS performance on the internal and external test sets and compared it with previous convolutional neural network (CNN) models and three professional laryngologists. RESULTS: The ILCDS outperformed the six CNNs, with the highest accuracy of 92.78% and an area under the curve (AUC) of 0.9732. Despite a slight drop in performance on external sets, the ILCDS maintained the best superiority, with 85.79% accuracy and an AUC of 0.9550. Surpassing professional laryngologists, the ILCDS achieved 92.00% accuracy. CONCLUSIONS: The ILCDS offers high accuracy and stability for LCA detection, reducing the burden on laryngologists.
引用
- Kang YF, Yang L, Hu YF, et al. Self-Attention Mechanisms-Based Laryngoscopy Image Classification Technique for Laryngeal Cancer Detection. Head Neck. 2024. PMID: 39526389. doi:10.1002/hed.27999
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。