深度学习应用于白光和窄带成像视频喉镜:实现喉癌实时检测
本研究回顾性收集219例喉鳞状细胞癌(LSCC)患者的视频喉镜帧,训练多种YOLO深度学习模型,集成算法(YOLOv5s联合YOLOv5m-TTA)取得精确率0.66、召回率0.62、平均精度均值0.63,单帧计算时间0.026秒,有望用于实时检测。
要点
- 集成YOLO模型在白光和窄带成像视频喉镜中检测LSCC,精确率0.66、召回率0.62。
- 平均精度均值(IoU=0.5)为0.63,单帧计算时间0.026秒。
- 模型复杂度低、计算速度快,适合实时处理。
核心结论
- 研究识别出适合在白光和窄带成像视频喉镜中检测LSCC的卷积神经网络模型,检测性能很有前景,且计算速度快,适合实时处理。
研究设计与样本
- 实验性研究,使用回顾性数据;回顾性收集219例LSCC患者的诊室经鼻视频内镜和术中硬性内镜录像。
主要发现
- 共提取624个LSCC视频帧,随机分为训练集82.6%、验证集8.2%、测试集9.2%。
- 集成算法(YOLOv5s联合YOLOv5m-TTA)检测效果最佳:精确率0.66、召回率0.62、平均精度均值(IoU=0.5)0.63。
- 在6例视频喉镜上测试,平均每帧计算时间0.026秒。
临床怎么用
- 原文未据此给出推荐。
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
OBJECTIVES: To assess a new application of artificial intelligence for real-time detection of laryngeal squamous cell carcinoma (LSCC) in both white light (WL) and narrow-band imaging (NBI) videolaryngoscopies based on the You-Only-Look-Once (YOLO) deep learning convolutional neural network (CNN). STUDY DESIGN: Experimental study with retrospective data. METHODS: Recorded videos of LSCC were retrospectively collected from in-office transnasal videoendoscopies and intraoperative rigid endoscopies. LSCC videoframes were extracted for training, validation, and testing of various YOLO models. Different techniques were used to enhance the image analysis: contrast limited adaptive histogram equalization, data augmentation techniques, and test time augmentation (TTA). The best-performing model was used to assess the automatic detection of LSCC in six videolaryngoscopies. RESULTS: Two hundred and nineteen patients were retrospectively enrolled. A total of 624 LSCC videoframes were extracted. The YOLO models were trained after random distribution of images into a training set (82.6%), validation set (8.2%), and testing set (9.2%). Among the various models, the ensemble algorithm (YOLOv5s with YOLOv5m-TTA) achieved the best LSCC detection results, with performance metrics in par with the results reported by other state-of-the-art detection models: 0.66 Precision (positive predicted value), 0.62 Recall (sensitivity), and 0.63 mean Average Precision at 0.5 intersection over union. Tests on the six videolaryngoscopies demonstrated an average computation time per videoframe of 0.026 seconds. Three demonstration videos are provided. CONCLUSION: This study identified a suitable CNN model for LSCC detection in WL and NBI videolaryngoscopies. Detection performances are highly promising. The limited complexity and quick computational times for LSCC detection make this model ideal for real-time processing. LEVEL OF EVIDENCE: 3 Laryngoscope, 132:1798-1806, 2022.
引用
- Azam MA, Sampieri C, Ioppi A, et al. Deep Learning Applied to White Light and Narrow Band Imaging Videolaryngoscopy: Toward Real-Time Laryngeal Cancer Detection. Laryngoscope. 2021. PMID: 34821396. doi:10.1002/lary.29960
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。