Validation and Evaluation of Algorithms

Slides:



Advertisements
Similar presentations
Towards Automating Patient- Specific Finite Element Model Development Kiran H. Shivanna 1,4, Brian D. Adams 2,1, Vincent A. Magnotta 3,1,4, Nicole M. Grosland.
Advertisements

Imaging Methods: Gait, Cognition and Mood Richard Camicioli MD University of Alberta Edmonton, Alberta
Six-week project Lauren Villemaire MBP 3970Z Department of Medical Biophysics University of Western Ontario.
NA-MIC National Alliance for Medical Image Computing Validation of Bone Models Using 3D Surface Scanning Nicole M. Grosland Vincent A.
Evaluation of Reconstruction Techniques
DTI group (Pitt) Instructor: Kevin Chan Kaitlyn Litcofsky & Toshiki Tazoe 7/12/2012.
Quality Control of Diffusion Weighted Images
© Fraunhofer MEVIS Toward Automated Validation of Sketch-based 3D Segmentation Editing Tools Frank Heckel 1, Momchil I. Ivanov 2, Jan H. Moltz 1, Horst.
PET/CT Working Group Update Jayashree Kalpathy-Cramer Sandy Napel.
Reproducibility of diffusion tractography E Heiervang 1,2, TEJ Behrens 1, CEM Mackay 3, MD Robson 3, H Johansen-Berg 1 1 Centre for Functional MRI of the.
The structural organization of the Brain Gray matter: nerve cell bodies (neurons), glial cells, capillaries, and short nerve cell extensions (axons and.
Comparison of Parametric and Nonparametric Thresholding Methods for Small Group Analyses Thomas Nichols & Satoru Hayasaka Department of Biostatistics U.
A COMPARISON OF APPROACHES FOR VERIFYING SOUTHWEST REGIONAL GAP VERTEBRATE-HABITAT DISTRIBUTION MODELS J. Judson Wynne, Charles A. Drost and Kathryn A.
Yujun Guo Kent State University August PRESENTATION A Binarization Approach for CT-MR Registration Using Normalized Mutual Information.
12-Apr CSCE790T Medical Image Processing University of South Carolina Department of Computer Science 3D Active Shape Models Integrating Robust Edge.
Signal and Noise in fMRI fMRI Graduate Course October 15, 2003.
Li Wang1, Feng Shi1, Gang Li1, Weili Lin1, John H
What can you see by MRI ? Stephen Paisey.
Computational Radiology Laboratory Harvard Medical School Children’s Hospital Department of Radiology Boston Massachusetts A Survey.
MNTP Trainee: Georgina Vinyes Junque, Chi Hun Kim Prof. James T. Becker Cyrus Raji, Leonid Teverovskiy, and Robert Tamburo.
M. Reddy, A. Livorine, R. Naini, H. Sucharew, A. Vagal
Global and Regional Brain Morphology in Subjects with Huntington’s Disease Prior to Diagnosis Peg C. Nopoulos 1,2,4, Hans J. Johnson 1, Vincent A. Magnotta.
Diffusion-Tensor Imaging Tractography: Correlation with Processing Speed in Aging Stephen Correia 1, Stephanie Y. Lee 2, Song Zhang 2, Stephen P. Salloway.
Quantifying of avascular necrosis of femoral head The clinical problem Determining the risk of femoral head collapse in a patient with AVNFH.
Comparative Diffusion Tensor Imaging (DTI) Study of Tool Use Pathways in Humans, Apes and Monkeys Ashwin G. Ramayya 1,2, Matthew F. Glasser 1, David A.
J OURNAL C LUB : Cardoso et al., University College London, UK “STEPS: Similarity and Truth Estimation for Propagated Segmentations and its application.
All Hands Meeting 2005 The Family of Reliability Coefficients Gregory G. Brown VASDHS/UCSD.
NA-MIC National Alliance for Medical Image Computing Validation of DTI Analysis Guido Gerig, Clement Vachet, Isabelle Corouge, Casey.
NA-MIC National Alliance for Medical Image Computing NAMIC UNC Site Update Site PI: Martin Styner Site NAMIC folks: Clement Vachet, Gwendoline.
References: [1]S.M. Smith et al. (2004) Advances in functional and structural MR image analysis and implementation in FSL. Neuroimage 23: [2]S.M.
NA-MIC National Alliance for Medical Image Computing Competitive Evaluation & Validation of Segmentation Methods Martin Styner, UNC NA-MIC.
A fMRI approach to probe CNS interaction Wei Chen, MD, MS. Modality : Animal MRI Mentor : Professor Seong-Gi Kim Kim’s Lab Faculty : Seong-Gi Kim, Tae.
National Alliance for Medical Image Computing Core What We Need from Cores 1 & 2 NA-MIC National Alliance for Medical Image Computing.
Cluster validation Integration ICES Bioinformatics.
Exploring Connectivity of the Brain’s White Matter with Dynamic Queries Presented by: Eugene (Austin) Stoudenmire 14 Feb 2007 Anthony Sherbondy, David.
Conclusions Simulated fMRI phantoms with real motion and realistic susceptibility artifacts have been generated and tested using SPM2. Image distortion.
Spatial Smoothing and Multiple Comparisons Correction for Dummies Alexa Morcom, Matthew Brett Acknowledgements.
Correction of bias field artifact in T1w MR images of the thigh and calf muscles Correction de contraste d’images IRM Projet A.
NA-MIC National Alliance for Medical Image Computing fMRI in NAMIC Facilitator: Polina Golland Presenters: Jim Fallon and Andy Saykin.
The PET/CT Working Group: CT Segmentation Challenge Informatics Issues Multi-site algorithm comparison Task: CT-based lung nodule segmentation.
NA-MIC National Alliance for Medical Image Computing NAMIC UNC Site Update Site PI: Martin Styner UNC Site NAMIC folks: C Vachet, G Roger,
Dynamic Connectivity: Pitfalls and Promises
Accuracy, Reliability, and Validity of Freesurfer Measurements David H. Salat
Maguire Physiological Psychology The Core Studies.
QIBA DCE-MRI Analysis Algorithm Validation Specification and Testing Daniel Barboriak M.D. Duke University Medical Center
New Features Added to Our DTI Package XU, Dongrong Ph.D. Columbia University New York State Psychiatric Institute Support: 1R03EB A1 June 18, 2009.
C. P. Loizou1, C. Papacharalambous1, G. Samaras1, E. Kyriakou2, T
Conclusion/Discussion
Reliability of Negative BOLD in Ipsilateral Motor Cortex
1 2 3 INDIAN INSTITUTE OF TECHNOLOGY ROORKEE PROJECT REPORT 2016
Voxel-based Morphometric Analysis
20 Years of FreeSurfer PETsurfer: MRI-PET Integration using FreeSurfer Nov 17, 2017 Douglas N. Greve, Ph.D. Martinos Center for Biomedical Imaging Massachusetts.
Human Brain Mapping Conference 2003 # 653
Johnny Suh M.D., Dr. Jacobson M.D., Dr. Pond M.D.
A Review in Quality Measures for Halftoned Images
Voxel-based Morphometric Analysis
Signal and Noise in fMRI
Graph Theoretic Analysis of Resting State Functional MR Imaging
Toward Automating Patient-Specific Finite Element Model Development
Voxel-based Morphometric Analysis
3T-versus-7T DTI with 36 diffusion-encoding directions at b = 3000 s/mm2 and 2.0 × 2.0 × 2.0 mm isotropic voxel resolution. 3T-versus-7T DTI with 36 diffusion-encoding.
SYSTEMATIC REVIEW OF COMPUTATIONAL MODELS FOR BRAIN PARCELLATION
Voxel-based Morphometric Analysis
Intermediate methods in observational epidemiology 2008
MultiModality Registration using Hilbert-Schmidt Estimators
Will Penny Wellcome Trust Centre for Neuroimaging,
Mapped Hexahedral Meshing: Evaluate the use of multi-resolution itk::fem registration for mapped meshing Team Plan/Expected Challenges/Publication Ritesh.
Automating stroke lesion segmentation in brain images using a multi-model multi-path convolutional neural network Yunzhe.
Christa Müller-Axt, Alfred Anwander, Katharina von Kriegstein 
Three-dimensional US Fractional Moving Blood Volume: Validation of Renal Perfusion Quantification In a porcine model, renal kidney perfusion measured with.
Presentation transcript:

Validation and Evaluation of Algorithms Vincent A. Magnotta The University of Iowa June 30, 2008

Software Development In many areas of medical imaging, the generation of an algorithm is the “easy” aspect of the project Now that I have an algorithm what is the next step? Validate the algorithm Evaluate reliability Evaluate biological relevance These are very different and give the developer information that is useful to enhance an algorithm

Validation Degree of accuracy of a measuring device Validation of medical image analysis is a major challenge What are our standards Actual structure of interest Another technique Manual raters Comparison with the literature

Validation Based on Actual Specimens Laser scanned surface Traced surface Surface Distance Map

Doppler US and Phase Contrast MR From Ho et al. Am. J. Roentgenol. 178 (3): 551, 2002

Manual Raters Often we are left with manual raters in medical imaging to serve as a standard Need to evaluate rater reliability May be subject to rater drift and bias Algorithms such as STAPLE have been developed to estimate the probability of a voxel being in a region-of-interest Several metrics to evaluate reliability Percent difference Intraclass correlation Border distance Overlap metrics: Dice, Jaccard, Spatial Overlap Sensitivity and Specificity

Metrics Intraclass Correlation Coefficient R2=(σsubject)2/ [(σsubject)2+ (σmethod)2+ (σerror)2] Volume(A∩B) Jaccard Metric = ------------------- Volume(AUB) 2*Volume(A∩B) Dice Metric = -------------------------------- [Volume(A)+Volume(B)] Volume(A∩B) Spatial Overlap = ------------------ Volume(A)

Intraclass Correlation Data Set 1 Data Set 2

Performance of Overlap Metrics Jaccard Metric Dice Metric

Reliability Ability to reproduce measurements within a subject across trials Most algorithms will give the same results when run on the same image data Typically evaluated on a scan/rescan basis Provides an estimate of the noise introduced by the algorithm Helps to determine the sample size required to measure a known effect size

Scan/Resan of DTI Fiber Tract FA Scan/Resan of DTI Fiber Tract Dist (mm)

Evaluation Use of digital phantoms Easily define cases of interest Can readily adjust SNR Usually a simplification of biological structure Lacks physiological noise Often do not model the PSF and partial volume artifacts Does the method replicate findings in the literature or known via observation

Age Related FA Changes

Conclusions Validation and evaluation of tools can be the most difficult part of a neuroimaging project There exist several methods for evaluating algorithms that have there strengths and weaknesses Validation determines how close we are to the actual process of interest Reliability determines in part our ability to measure changes In general, neuroimaging provides an index of brain volumes and function; not absolute measurements

Acknowledgements Department of Psychiatry Department of Radiology Hans Johnson Department of Radiology Stephanie Powell Peng Cheng MIMX Lab Nicole Grosland Nicole DeVries Ester Gassman