Deep Learning Applied to White Light and Narrow Band Imaging Videolaryngoscopy: Toward Real-Time Laryngeal Cancer Detection.
Deep Learning Applied to White Light and Narrow Band Imaging Videolaryngoscopy: Toward Real-Time Laryngeal Cancer Detection.
复制标题
DOI：
10.1002/lary.29960
复制
发表时间：
2022-09
期刊：
影响因子：
2.6
通讯作者：
Peretti, Giorgio
中科院分区：
文献类型：
--
作者：
Azam, Muhammad Adeel;Sampieri, Claudio;Ioppi, Alessandro;Africano, Stefano;Vallin, Alberto;Mocellin, Davide;Fragale, Marco;Guastini, Luca;Moccia, Sara;Piazza, Cesare;Mattos, Leonardo S.;Peretti, Giorgio
关键词：
评估基于You - Only - Look - Once （YOLO）深度学习卷积神经网络（CNN）的人工智能在白光（WL）和窄带成像（NBI）视频喉镜下实时检测喉鳞癌（LSCC）的新应用。回顾性实验研究。回顾性地收集了经鼻内镜和术中硬内镜下LSCC的录像。提取LSCC视频帧用于各种YOLO模型的训练、验证和测试。使用了不同的技术来增强图像分析：对比度有限的自适应直方图均衡化，数据增强技术和测试时间增强（TTA）。使用表现最佳的模型来评估6次视频喉镜检查中LSCC的自动检测。回顾性纳入了219例患者。共提取了624个LSCC视频帧。将图像随机分配到训练集（82.6%）、验证集（8.2%）和测试集（9.2%）后，对YOLO模型进行训练。在各种模型中，集成算法（YOLOv5s与YOLOv5m-TTA）获得了最佳的LSCC检测结果，其性能指标与其他最先进的检测模型报告的结果相当：精度0.66（阳性预测值），召回率0.62（灵敏度），平均精度0.63在0.5交集超过联合。对6台视频喉镜的测试表明，每帧视频的平均计算时间为0.026秒。提供了三个演示视频。本研究确定了一种适用于WL和NBI视频喉镜下LSCC检测的CNN模型。检测性能非常有希望。LSCC检测的有限复杂性和快速计算时间使该模型非常适合实时处理。[3]喉镜，32 (2):798 - 796,2022
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). Experimental study with retrospective data. 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. 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. 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. 3 Laryngoscope, 132:1798–1806, 2022
登录
查看更多内容
影响因子：
4.7
作者：
Paderno A;Piazza C;Del Bon F;Lancini D;Tanagli S;Deganello A;Peretti G;De Momi E;Patrini I;Ruperti M;Mattos LS;Moccia S
通讯作者：
Moccia S
影响因子：
3.7
作者：
Schrynemackers M;Küffner R;Geurts P
通讯作者：
Geurts P
影响因子：
3
作者：
Tama BA;Kim DH;Kim G;Kim SW;Lee S
通讯作者：
Lee S
影响因子：
3.9
作者：
Esmaeili, Nazila;Illanes, Alfredo;Friebe, Michael
通讯作者：
Friebe, Michael
DOI：
10.1002/hed.26313
发表时间：
2020-06-16
影响因子：
2.9
作者：
Inaba, Atsushi;Hori, Keisuke;Yano, Tomonori
通讯作者：
Yano, Tomonori