Colonoscopy 3D Video Dataset with Paired Depth from 2D-3D Registration

基本事实 人工智能 计算机科学 计算机视觉 帧(网络) 标杆管理 旋转(数学) 图像配准 结肠镜检查 光流 虚拟大肠镜 翻译(生物学) 图像(数学) 医学 电信 生物化学 化学 结直肠癌 营销 癌症 信使核糖核酸 内科学 业务 基因
作者
Taylor L. Bobrow,Mayank Golhar,Rohan C. Vijayan,Venkata S. Akshintala,Juán Ramón Carbo García,Nicholas J. Durr
出处
期刊:Cornell University - arXiv 被引量:2
标识
DOI:10.48550/arxiv.2206.08903
摘要

Screening colonoscopy is an important clinical application for several 3D computer vision techniques, including depth estimation, surface reconstruction, and missing region detection. However, the development, evaluation, and comparison of these techniques in real colonoscopy videos remain largely qualitative due to the difficulty of acquiring ground truth data. In this work, we present a Colonoscopy 3D Video Dataset (C3VD) acquired with a high definition clinical colonoscope and high-fidelity colon models for benchmarking computer vision methods in colonoscopy. We introduce a novel multimodal 2D-3D registration technique to register optical video sequences with ground truth rendered views of a known 3D model. The different modalities are registered by transforming optical images to depth maps with a Generative Adversarial Network and aligning edge features with an evolutionary optimizer. This registration method achieves an average translation error of 0.321 millimeters and an average rotation error of 0.159 degrees in simulation experiments where error-free ground truth is available. The method also leverages video information, improving registration accuracy by 55.6% for translation and 60.4% for rotation compared to single frame registration. 22 short video sequences were registered to generate 10,015 total frames with paired ground truth depth, surface normals, optical flow, occlusion, six degree-of-freedom pose, coverage maps, and 3D models. The dataset also includes screening videos acquired by a gastroenterologist with paired ground truth pose and 3D surface models. The dataset and registration source code are available at durr.jhu.edu/C3VD.
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
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
1秒前
Zayro完成签到,获得积分10
2秒前
3秒前
自信雅琴发布了新的文献求助10
3秒前
anna发布了新的文献求助10
6秒前
CodeCraft应助Lu采纳,获得10
7秒前
7秒前
7秒前
Bressanone发布了新的文献求助10
8秒前
妙蛙完成签到,获得积分10
9秒前
10秒前
111111111发布了新的文献求助10
11秒前
妙蛙发布了新的文献求助10
13秒前
14秒前
爱笑紫菜发布了新的文献求助30
16秒前
16秒前
17秒前
李爱国应助111111111采纳,获得10
17秒前
tay发布了新的文献求助10
18秒前
科研通AI5应助ffff采纳,获得10
19秒前
过氧化氢发布了新的文献求助30
21秒前
感动黄豆发布了新的文献求助10
22秒前
钱宇成发布了新的文献求助10
22秒前
YJ888发布了新的文献求助10
22秒前
vincen91完成签到,获得积分10
26秒前
Leach完成签到 ,获得积分10
27秒前
长乐完成签到,获得积分10
28秒前
FashionBoy应助院士人启动采纳,获得10
32秒前
33秒前
33秒前
AptRank完成签到,获得积分10
34秒前
量子星尘发布了新的文献求助10
34秒前
焦糖布丁的滋味完成签到,获得积分10
34秒前
35秒前
隐形的觅波完成签到 ,获得积分10
36秒前
儒雅南风完成签到 ,获得积分10
37秒前
小马甲应助科研通管家采纳,获得10
38秒前
打打应助科研通管家采纳,获得10
38秒前
科研通AI5应助科研通管家采纳,获得10
38秒前
Orange应助科研通管家采纳,获得10
38秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989115
求助须知:如何正确求助?哪些是违规求助? 3531367
关于积分的说明 11253688
捐赠科研通 3269986
什么是DOI,文献DOI怎么找? 1804868
邀请新用户注册赠送积分活动 882078
科研通“疑难数据库(出版商)”最低求助积分说明 809105