MISNeR: Medical Implicit Shape Neural Representation for Image Volume Visualisation

计算机科学 代表(政治) 可视化 图像(数学) 人工智能 计算机图形学(图像) 信息可视化 体积热力学 计算机视觉 物理 量子力学 政治 政治学 法学
作者
Guofan Jin,Yong Sik Jung,Lu Bi,Jeesun Kim
出处
期刊:Computer Graphics Forum [Wiley]
卷期号:43 (7)
标识
DOI:10.1111/cgf.15222
摘要

Abstract Three‐dimensional visualisation of mesh reconstruction of the medical images is commonly used for various clinical applications including pre / post‐surgical planning. Such meshes are conventionally generated by extracting the surface from volumetric segmentation masks. Therefore, they have inherent limitations of staircase artefacts due to their anisotropic voxel dimensions. The time‐consuming process for manual refinement to remove artefacts and/or the isolated regions further adds to these limitations. Methods for directly generating meshes from volumetric data by template deformation are often limited to simple topological structures, and methods that use implicit functions for continuous surfaces, do not achieve the level of mesh reconstruction accuracy when compared to segmentation‐based methods. In this study, we address these limitations by combining the implicit function representation with a multi‐level deep learning architecture. We introduce a novel multi‐level local feature sampling component which leverages the spatial features for the implicit function regression to enhance the segmentation result. We further introduce a shape boundary estimator that accelerates the explicit mesh reconstruction by minimising the number of the signed distance queries during model inference. The result is a multi‐level deep learning network that directly regresses the implicit function from medical image volumes to a continuous surface model, which can be used for mesh reconstruction from arbitrary high volume resolution to minimise staircase artefacts. We evaluated our method using pelvic computed tomography (CT) dataset from two public sources with varying z‐axis resolutions. We show that our method minimised the staircase artefacts while achieving comparable results in surface accuracy when compared to the state‐of‐the‐art segmentation algorithms. Furthermore, our method was 9 times faster in volume reconstruction than comparable implicit shape representation networks.
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
爽o发布了新的文献求助10
1秒前
莉莉安发布了新的文献求助10
1秒前
1秒前
m0405完成签到,获得积分10
2秒前
科研通AI5应助hangzhen采纳,获得10
3秒前
小林不熬夜完成签到 ,获得积分10
3秒前
NexusExplorer应助Zpiao采纳,获得10
4秒前
LINHAI发布了新的文献求助10
4秒前
沉心望星海完成签到,获得积分10
6秒前
7秒前
丘比特应助怕孤单的凝天采纳,获得10
7秒前
皮卡皮卡丘完成签到,获得积分10
8秒前
8秒前
细心的火龙果完成签到,获得积分10
9秒前
zyh完成签到,获得积分10
10秒前
科研通AI5应助吃肯德基采纳,获得10
13秒前
送外卖了发布了新的文献求助10
14秒前
15秒前
YH应助8888采纳,获得30
15秒前
17秒前
天真的邴完成签到 ,获得积分10
18秒前
zuozuo发布了新的文献求助10
18秒前
19秒前
21秒前
凉冰完成签到,获得积分20
22秒前
科研通AI5应助Sephirex采纳,获得30
22秒前
22秒前
江峰发布了新的文献求助10
23秒前
23秒前
23秒前
23秒前
蜗牛完成签到,获得积分10
23秒前
沉默新梅完成签到,获得积分20
26秒前
星星点灯发布了新的文献求助10
26秒前
天天快乐应助比白618采纳,获得10
27秒前
大个应助凉冰采纳,获得10
27秒前
27秒前
QJ完成签到,获得积分10
27秒前
所所应助Labixix采纳,获得10
28秒前
drr发布了新的文献求助10
28秒前
高分求助中
【此为提示信息,请勿应助】请按要求发布求助,避免被关 20000
Continuum Thermodynamics and Material Modelling 2000
ISCN 2024 – An International System for Human Cytogenomic Nomenclature (2024) 1000
CRC Handbook of Chemistry and Physics 104th edition 1000
Izeltabart tapatansine - AdisInsight 600
Maneuvering of a Damaged Navy Combatant 500
An International System for Human Cytogenomic Nomenclature (2024) 500
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 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3769651
求助须知:如何正确求助?哪些是违规求助? 3314720
关于积分的说明 10173463
捐赠科研通 3030075
什么是DOI,文献DOI怎么找? 1662585
邀请新用户注册赠送积分活动 795040
科研通“疑难数据库(出版商)”最低求助积分说明 756519