arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1907.08136cs.CVcs.RO
收藏

使用深度学习进行定位的肺部自动驾驶

Autonomous Driving in the Lung using Deep Learning for Localization

Stanford University(斯坦福大学);Auris Health, Inc.(Auris Health公司)

Jake Sganga, David Eng, Chauncey Graetzel, David B. Camarillo

摘要:

肺癌是全球癌症相关死亡的主要原因,早期诊断对改善患者预后至关重要。为了诊断癌症,训练有素的肺病学家必须将柔性支气管镜深入肺的分支结构进行活检。在26-33%的病例中,活检未能对靶组织进行采样,这主要是因为与术前CT图配准不良。为了改善术中配准,我们开发了两种深度学习方法,以基于支气管镜视频实时在术前CT图中定位支气管镜,称为AirwayNet和BifurcationNet。该网络完全在来自患者特定CT的模拟图像上进行训练。当在模拟肺中对记录的支气管镜检查视频进行评估时,AirwayNet优于其他深度学习定位算法,其精确度-召回率曲线下面积为0.97。使用AirwayNet,我们仅基于视频反馈在幻肺中演示了自动驾驶。在95%的试验中,机器人在左肺和右肺中达到了四个目标。在八个人类尸体肺的记录视频中,AirwayNet实现了精确度-召回率曲线下的区域,范围从0.82到0.997。

英文摘要:

Lung cancer is the leading cause of cancer-related death worldwide, and early diagnosis is critical to improving patient outcomes. To diagnose cancer, a highly trained pulmonologist must navigate a flexible bronchoscope deep into the branched structure of the lung for biopsy. The biopsy fails to sample the target tissue in 26-33% of cases largely because of poor registration with the preoperative CT map. To improve intraoperative registration, we develop two deep learning approaches to localize the bronchoscope in the preoperative CT map based on the bronchoscopic video in real-time, called AirwayNet and BifurcationNet. The networks are trained entirely on simulated images derived from the patient-specific CT. When evaluated on recorded bronchoscopy videos in a phantom lung, AirwayNet outperforms other deep learning localization algorithms with an area under the precision-recall curve of 0.97. Using AirwayNet, we demonstrate autonomous driving in the phantom lung based on video feedback alone. The robot reaches four targets in the left and right lungs in 95% of the trials. On recorded videos in eight human cadaver lungs, AirwayNet achieves areas under the precision-recall curve ranging from 0.82 to 0.997.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑