Download presentation

Presentation is loading. Please wait.

Published byDamien Embry Modified over 4 years ago

1
Efficient Sparse Shape Composition with its Applications in Biomedical Image Analysis: An Overview Shaoting Zhang, Yiqiang Zhan, Yan Zhou, and Dimitris N. Metaxas

2
Outline Introduction Our methods Experiments Future work 2

3
Introduction Motivations Segmentation (i.e., finding 2D/3D ROI) is a fundamental problem in medical image analysis. We use deformable models and shape prior. Shape representation is based on landmarks. Chest X-ray Lung CAD Liver in low-dose whole-body CT Rat brain structure in MR Microscopy 3

4
Introduction Motivations Shape prior is important: – Automatic, accuracy, efficiency, robustness. – Handle weak or misleading appearance cues from image information. – Discover or preserve complex shape details. Segmentation system 4

5
Introduction Challenges – shape prior modeling Good shape prior method needs to: – Handle gross errors of the input data. – Model complex shape variations. – Preserve local shape details. 5

6
Introduction Relevant work – shape prior methods Handling gross errors. – RANSAC + ASM [M. Rogers, ECCV02] – Robust Point Matching [J. Nahed, MICCAI06] Complex shape variation (multimodal distribution). – Mixture of Gaussians [T. F. Cootes, IVC97] – Patient-specific shape [Y. Zhu, MICCAI09] Recovering local details. – Sparse PCA [K. Sjostrand, TMI07] – Hierarchical ASM [D. Shen, TMI03] 6

7
Our Approach Shape prior using sparse shape composition Our method is based on two observations: – An input shape can be approximately represented by a sparse linear combination of training shapes. – The given shape information may contain gross errors, but such errors are often sparse.... 7

8
Our Approach Shape prior using sparse shape composition Formulation: – Sparse linear combination: –...... Dense x Sparse x Aligned data matrix D Weight x Input y Global transformation parameter Number of nonzero elements 8 Global transformation operator

9
Our Approach Shape prior using sparse shape composition Non-Gaussian errors: – 9

10
Our Approach Shape prior using sparse shape composition Why it works? – Robust: Explicitly modeling e with L0 norm constraint. Thus it can detect gross (sparse) errors. – General: No assumption of a parametric distribution model (e.g., a unimodal distribution assumption in ASM). Thus it can model complex shape statistics. – Lossless: It uses all training shapes. Thus it is able to recover detail information even if the detail is not statistically significant in training data. Zhang, Metaxas, et.al.: MedIA11 10

11
Experiments 2D lung localization in X-ray Setting : –Manually select landmarks for training purpose. –200 training and 167 testing. –To locate the lung, detect landmarks, then predict a shape to fit them. –Sensitivity (P), Specificity (Q), Dice Similarity Coefficient. 11

12
Experiments 2D lung localization in X-ray Handling gross errors Detection PA ASM RASM NN TPS Sparse1 Sparse2 Procrustes analysis Active Shape Model Robust ASMNearest Neighbors Thin-plate-spline Without modeling e 12 Proposed method

13
Experiments 2D lung localization in X-ray Multimodal distribution Detection PA ASM/RASM NN TPS Sparse1 Sparse2 13

14
Experiments 2D lung localization in X-ray Recover local detail information Detection PA ASM/RASM NN TPS Sparse1 Sparse2 14

15
Experiments 2D lung localization in X-ray Sparse shape components ASM modes: 15 0.5760 ++ 0.21560.0982

16
Experiments 2D lung localization in X-ray Mean values (µ) and standard deviations (σ). Left lung Right lung 1)PA, 2)ASM, 3)RASM, 4)NN, 5)TPS, 6)Sparse1, 7)Sparse2 µ σ 16

17
Future Work Dictionary Learning 17...... Dictionary size = 128#Coefficients = 800#Input samples = 800

18
18 D Initialize D Sparse Coding Use MP or BP Dictionary Update Column-by-Column by SVD computation Use K-SVD to learn a compact dictionary Aharon, Elad, & Bruckstein (04) YTYT * The slides are from http://www.cs.technion.ac.il/~elad/talks/ Future Work Dictionary Learning

19
Future Work Online Update Dictionary 19......

20
Future Work Mesh Partitioning for Local Shape Priors 20 Segmentation system Lung Heart Rib Colon Abdomen

21
Thanks! Questions and comments 21

Similar presentations

OK

Insert Date HereSlide 1 Using Derivative and Integral Information in the Statistical Analysis of Computer Models Gemma Stephenson March 2007.

Insert Date HereSlide 1 Using Derivative and Integral Information in the Statistical Analysis of Computer Models Gemma Stephenson March 2007.

© 2018 SlidePlayer.com Inc.

All rights reserved.

To make this website work, we log user data and share it with processors. To use this website, you must agree to our Privacy Policy, including cookie policy.

Ads by Google