Sub-millimeter precision 3D measurement through a standard endoscope with time of flight

计算机科学 计算机视觉 人工智能 工作流程 内窥镜 单眼 机器人 移动设备 外科 医学 数据库 操作系统
作者
R. A. Stolyarov,Vasiliy E. Buharin,Michael Val,Charlie Beurskens,Manuel DeMaio,Suraj Srinivasan,Tom Calef,Peter Kim
标识
DOI:10.1117/12.2605993
摘要

Endoscopic surgery has been widely adopted across specialties because it reduces patient trauma, risk, and recovery time as compared to open procedures. The foremost challenge of endoscopic surgery is the inability to see in three dimensions, a disadvantage that significantly increases procedure time and uncertainty by inhibiting depth perception as well as localization and measurement capability. State-of-the-art approaches in endoscopic 3D measurement are largely based on a combination of structured light and stereo vision, but are limited in their robustness and applicability to clinical workflow. Both approaches require a large baseline and are not supported by most handheld off-the-shelf endoscopes; stereo methods specifically are sensitive to scenes lacking features or containing disturbances such as smoke and specular reflections, which are common in surgery. To address these issues, we propose an alternative method for 3D measurement based on time-of-flight (TOF), a depth sensing modality which is inherently monocular and known to be insensitive to featureless scenes and many types of disturbances. Specifically, we develop a TOF imaging module adapter compatible with off-theshelf endoscopes and demonstrate single-shot, sub-millimeter 3D measurement accuracy on animal tissue. These results are significant because they suggest widespread compatibility with existing operating room equipment and workflow and applicability to a wide variety of clinically relevant surgical tasks including measurement of tumors, hernias, and anastomoses, intra-operative registration of the surgical scene to high-quality static 3D imaging data, and control of surgical robots.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1111完成签到,获得积分10
1秒前
大模型的应助被h_h采纳,获得10
1秒前
在下小李发布了新的文献求助10
1秒前
张伟发布了新的文献求助10
1秒前
sikh的应助被Aileen采纳,获得10
1秒前
晚晚完成签到,获得积分10
2秒前
2秒前
所所的应助被亚李采纳,获得10
2秒前
2秒前
鸢尾绘画发布了新的文献求助10
2秒前
成就书雪完成签到,获得积分0
3秒前
pure123完成签到,获得积分10
3秒前
3秒前
Enigma_GEB的应助被11采纳,获得20
3秒前
唐博文发布了新的文献求助10
3秒前
4秒前
4秒前
张磊完成签到,获得积分10
4秒前
希望天下0贩的0的应助被雾语采纳,获得10
4秒前
你好发布了新的文献求助10
4秒前
Hello的应助被落寞千愁采纳,获得50
5秒前
氓月发布了新的文献求助10
5秒前
5秒前
6秒前
SHAN完成签到 ,获得积分10
6秒前
Serendipity发布了新的文献求助10
7秒前
自觉的清涟完成签到,获得积分10
7秒前
科研通AI6.2的应助被楚天采纳,获得10
7秒前
哈基雷完成签到 ,获得积分10
7秒前
xiaoguai完成签到 ,获得积分0
8秒前
8秒前
李祥龙完成签到,获得积分10
8秒前
8秒前
qs的小迷妹完成签到,获得积分20
8秒前
9秒前
molihuakai的应助被张伟采纳,获得10
9秒前
qiqi完成签到,获得积分10
9秒前
molihuakai的应助被张伟采纳,获得10
9秒前
Jasper的应助被生动项链采纳,获得10
9秒前
古月发布了新的文献求助10
9秒前
高分求助中
(应助此贴封号)通过应助OA文献获取积分 10000
Rosenblum, Global Change Biology 800
Computational Chemical Reaction Engineering: Modeling, Simulation, and Design with MATLAB 600
Organizational Behavior 510
Management and the Arts 510
Deformation and Fracture of the Lumbar Vertebral End Plate 500
CLSI C56QG Examples of Hemolyzed, Icteric, and Lipemic/Turbid Samples Quick Guide 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 计算机科学 工程类 纳米技术 内科学 物理 有机化学 化学工程 生物化学 复合材料 光电子学 细胞生物学 心理学 量子力学 催化作用 物理化学 电极
热门帖子
关注 科研通微信公众号,转发送积分 7803162
求助须知:如何正确求助?哪些是违规求助? 9337349
关于积分的说明 20485246
捐赠科研通 7395061
什么是DOI,文献DOI怎么找? 3327026
关于科研通互助平台的介绍 2474160
邀请新用户注册赠送积分活动 2345232