Anatomic Surface Reconstruc1on from Sampled Point Cloud Data and Prior Models

Similar documents
Fast and Robust Normal Estimation for Point Clouds with Sharp Features

Pa8ern Recogni6on. and Machine Learning. Chapter 4: Linear Models for Classifica6on

DAMAGED ROAD TUNNEL LASER SCANNER SURVEY

A. OPENING POINT CLOUDS. (Notepad++ Text editor) (Cloud Compare Point cloud and mesh editor) (MeshLab Point cloud and mesh editor)

The Essential Role of CT Planning and TEE Guidance to Optimize Device Deployment

Application Report. Propeller Blade Inspection Station

Topographic Change Detection Using CloudCompare Version 1.0

Three Dimensional Ultrasound Imaging

High-accuracy ultrasound target localization for hand-eye calibration between optical tracking systems and three-dimensional ultrasound

Alessandro Laio, Maria d Errico and Alex Rodriguez SISSA (Trieste)

Computer Graphics AACHEN AACHEN AACHEN AACHEN. Public Perception of CG. Computer Graphics Research. Methodological Approaches

Moments. Objec-ves. He who asks is a fool for five minutes, but he who does not ask remains a fool forever. - Chinese proverb

Introduction to Computer Graphics

PCL - SURFACE RECONSTRUCTION

Introduction to Scientific Data Visualization

ACCURACY ASSESSMENT OF BUILDING POINT CLOUDS AUTOMATICALLY GENERATED FROM IPHONE IMAGES

V6 AIRS Spectral Calibra2on

Point cloud processing - scanning, analysing and validating

Digital Imaging and Communications in Medicine (DICOM) Supplement 132: Surface Segmentation Storage SOP Class

Robust NURBS Surface Fitting from Unorganized 3D Point Clouds for Infrastructure As-Built Modeling

How To Analyze Medical Image Data With A Feature Based Approach To Big Data Medical Image Analysis

Low-dose CT for Pulmonary Embolism

Ultrasound Simulators

Image Analysis for Volumetric Industrial Inspection and Interaction

Introduction to Electrophysiology. Wm. W. Barrington, MD, FACC University of Pittsburgh Medical Center

MODEL BASED RECONSTRUCTION OF THE BONY KNEE ANATOMY FROM 3D ULTRASOUND IMAGES

Deformable Registration for Image-Guided Radiation Therapy

Part-Based Recognition

How To Use Design Mentor

Recovering Primitives in 3D CAD meshes

The process components and related data characteristics addressed in this document are:

IMPLICIT SHAPE MODELS FOR OBJECT DETECTION IN 3D POINT CLOUDS

Creation of an Unlimited Database of Virtual Bone. Validation and Exploitation for Orthopedic Devices

How To Create A Surface From Points On A Computer With A Marching Cube

Computer Animation and Visualisation. Lecture 1. Introduction

Automatic Building Facade Detection in Mobile Laser Scanner point Clouds

Anatomic Modeling from Unstructured Samples Using Variational Implicit Surfaces

Multiphysics Software Applications in Reverse Engineering

Consolidated Visualization of Enormous 3D Scan Point Clouds with Scanopy

CS 5614: (Big) Data Management Systems. B. Aditya Prakash Lecture #18: Dimensionality Reduc7on

Construction of human knee bone joint model using FDM based 3D Printer from CT scan images.

Electrocardiography I Laboratory

Movement analysis with stereophotogrammetry: anatomical landmarks calibration

Lecture 9: Geometric map transformations. Cartographic Transformations

Normal & Abnormal Intracardiac. Lancashire & South Cumbria Cardiac Network

Oncentra Brachy Comprehensive treatment planning for brachytherapy. Time to focus on what counts

Summa cardiovascular institute. A Patient s Guide to AFib Treatment

Probabilistic Latent Semantic Analysis (plsa)

Diffeomorphic Diffusion Registration of Lung CT Images

Alexander Wood is a Senior So/ware Engineer at Analy5cal Graphics Inc (AGI). At AGI, he is a contributor to Cesium and Technical Lead on the STK

Protec'ng Communica'on Networks, Devices, and their Users: Technology and Psychology

Normal Intracardiac Pressures. Lancashire & South Cumbria Cardiac Network

TOLOMEO. ORFEO Toolbox. Jordi Inglada - CNES. TOoLs for Open Mul/- risk assessment using Earth Observa/on data TOLOMEO

PCL Tutorial: The Point Cloud Library By Example. Jeff Delmerico. Vision and Perceptual Machines Lab 106 Davis Hall UB North Campus.

SOFTWARE FOR 3D IMAGE VISUALISATION, ANALYSIS AND MODEL GENERATION

ANALYTICAL TECHNIQUES FOR DATA VISUALIZATION

Robot Perception Continued

Files Used in this Tutorial

Embedded Systems in Healthcare. Pierre America Healthcare Systems Architecture Philips Research, Eindhoven, the Netherlands November 12, 2008

A Novel Flex Circuit Area-Array Interconnect System for a Catheter-Based Ultrasound Transducer

ASSESSMENT OF VISUALIZATION SOFTWARE FOR SUPPORT OF CONSTRUCTION SITE INSPECTION TASKS USING DATA COLLECTED FROM REALITY CAPTURE TECHNOLOGIES

Single Depth Image Super Resolution and Denoising Using Coupled Dictionary Learning with Local Constraints and Shock Filtering

Normal Estimation for Point Clouds: A Comparison Study for a Voronoi Based Method

Ablation For Atrial Fibrillation. Bill Petrellis Electrophysiologist

Tizian TM Creativ RT. Abutment Designer. for the CAD-software version Instruction Manual

Mimics Innovation Suite. Software and Services for Engineering on Anatomy TM

BIOINF 585 Fall 2015 Machine Learning for Systems Biology & Clinical Informatics

Segmentation of building models from dense 3D point-clouds

Spatio-Temporally Coherent 3D Animation Reconstruction from Multi-view RGB-D Images using Landmark Sampling

A Three-Dimensional Correlation Method for Registration of Medical Images in Radiology

Volume visualization I Elvins

Machine Learning for Medical Image Analysis. A. Criminisi & the InnerEye MSRC

Contents. HD11 XE Quick Guide

SITE IMAGING MANUAL ACRIN 6698

Hunk & Elas=c MapReduce: Big Data Analy=cs on AWS

On Fast Surface Reconstruction Methods for Large and Noisy Point Clouds

Self-Calibrated Structured Light 3D Scanner Using Color Edge Pattern

A Study on SURF Algorithm and Real-Time Tracking Objects Using Optical Flow

ECBDL 14: Evolu/onary Computa/on for Big Data and Big Learning Workshop July 13 th, 2014 Big Data Compe//on

Image Segmentation and Registration

Shape Measurement of a Sewer Pipe. Using a Mobile Robot with Computer Vision

Using Optech LMS to Calibrate Survey Data Without Ground Control Points

Data Mining Cluster Analysis: Basic Concepts and Algorithms. Lecture Notes for Chapter 8. Introduction to Data Mining

Measurement Tools in Inventor

CMMI for High-Performance with TSP/PSP

VFI Technology to Change the Way You Work

COVERAGE GUIDANCE: ABLATION FOR ATRIAL FIBRILLATION

Automatic Calibration of an In-vehicle Gaze Tracking System Using Driver s Typical Gaze Behavior

Tracking and Recognition in Sports Videos

A Patient Guide to Atrial Fibrillation and Catheter Ablation

VECTORAL IMAGING THE NEW DIRECTION IN AUTOMATED OPTICAL INSPECTION

TISSUE MIMICKING GEL QUALITY LE PHANTOM SERIES DESIGN. performance the ultrasound labs ofand. icking material has the same attenuation mim-

Data Visualization for Atomistic/Molecular Simulations. Douglas E. Spearot University of Arkansas

Rb 82 Cardiac PET Scanning Protocols and Dosimetry. Deborah Tout Nuclear Medicine Department Central Manchester University Hospitals

siftservice.com - Turning a Computer Vision algorithm into a World Wide Web Service

Synthetic Sensing: Proximity / Distance Sensors

Transcription:

Anatomic Surface Reconstruc1on from Sampled Point Cloud Data and Prior Models Deyu Sun, Maryam E. Rettmann, David R. Holmes III, Cristian Linte, Bruce Cameron, Jiquan Liu, Douglas Packer, Richard A. Robb

Catheter- Based Cardiac Abla1on Used to treat le> atrial fibrilla1on Ectopic electrical foci o>en originate in pulmonary veins Typical treatment strategy electrical isola1on of pulmonary veins Anatomical guidance and targe1ng is key component of procedure

Standard Visualiza1ons Standard visualization tools include fluoroscopy, ultrasound, EAM Registration of preoperative surface models (Dickfeld et. al. Circulation 2003, Reddy et. al. JACC 2004, Sun et. al. SPIE MI 2005) Catheter in fluoroscopy image Electroanatomic map constructed from Biosense CARTO system Real- 1me intracardiac echocardiography (ICE)

Introduc1on Goals of study Intra- opera1ve surface reconstruc1on from tracked, ECG- gated ICE images and pre- op model built from CT scan Assump1ons ICE and pre- op model are acquired in the same ECG phase and have been registered to pa1ent Anatomy contour has been segmented from ICE images

Introduc1on Challenges Freehand ICE images are acquired in irregular posi1ons and cannot be reconstructed by conven1onal methods such as marching algorithms Point cloud generated from intra- opera1ve scanning are sparse, thus difficult to be reconstructed by conven1onal methods developed in computer graphics area for dense laser scanning data

Introduc1on Screened Poisson Surface Reconstruc1on A high resolu1on and quality surface reconstruc1on method, robust to noise In addi1on to point posi1on informa1on, also integra1ng normal direc1on, thus working for sparse point cloud M. Kazhdan, M. Bolitho, H. Hoppe, Poisson Surface Reconstruc1on, Eurographics Symposium on Geometry Processing, (2006), 61-70.

Introduc1on Challenge Consistent es1ma1on of normal vector for complex structure from sparse point cloud Pre- op model of le> atrium Normal es1ma1on by Hoppe et al. method

Proposed Normal Vector Es1ma1on Method K- NN based consistent es1ma1on of normal vector Using the average normal vectors of k nearest neighbor ver1ces in the pre- op model as an es1ma1on for each point of the point cloud

Workflow CT/MR scan Pre- op model Pre- op model registered to patient Inter- op images Point cloud Point cloud with estimated normals Reconstructed model

Simula1on Experiment Goal Es1mate reconstruc1on error (RMS error) due to different factors Single factor simula1on experiment Possible factors: point cloud density, ICE image noise, registra1on error, k value in k- NN normal vector es1ma1on Combined factors simula1on experiment Combine all factors together and evaluate reconstruc1on error

Single Factor Experiment Results

Single Factor Experiment Results

Single Factor Experiment Results

Single Factor Experiment Results

Combined Factors Experiment Results 35% subsampled point set from original model Add zero mean Gaussian noise to X,Y,Z respectively; σ=1.8mm Translate along X, Y, and Z axis respectively with random distances, mean=0, σ=2.0mm Rotate around X, Y, Z axis respectively with random angles, mean=0, σ=3.0 degree Repeate 20 times Estimate normal vectors with K=1,4,8,12 respectively Reconstruction & Measure error

Combined Factors Experiment Results 0 3.6 #10 Visualization of reconstruction error of 18th experiment on the surface of the prior model. Different colors indicate different reconstruction errors; the color map was scaled from 0 to 3.6mm reconstruction error; if the error is larger than 3.6mm, then it was set to the same color as 3.6mm. The reconstructed models were reconstruction results of 18th experiment. The reconstruction parameters for a-d are K=1 & RMS=0.88mm, K=4 & RMS=1.02mm, K=8 & RMS=1.05mm, K=12 & RMS=1.06mm, respectively.

Conclusion & Future Development Summary Proposed an approach to es1mate consistent normal vectors which helps adapt SPSR in modeling le> atrium from intra- op point cloud and prior models Es1mated reconstruc1on error caused by prac1cal factors by simula1on experiments Sebng factors to normal values, the surface reconstruc1on error is 0.88±0.03mm Future development Further valida1on by collec1ng data via ICE transducer from real le> atrium phantom and animals

Acknowledgement Thanks to my partners from Biomedical Imaging Resource lab Thank you for your afen1on