1 / 28

Towards Robust Medical Image Segmentation

Towards Robust Medical Image Segmentation. Shaoting Zhang CBIM Center Computer Science Department Rutgers University. Introduction Background. Segmentation (finding 2D/3D region-of-interest) is a fundamental problem and bottleneck in many areas.

Download Presentation

Towards Robust Medical Image Segmentation

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Towards Robust Medical Image Segmentation Shaoting Zhang CBIM Center Computer Science Department Rutgers University

  2. IntroductionBackground • Segmentation (finding 2D/3D region-of-interest) is a fundamental problem and bottleneck in many areas. • We focus on learning-based deformable models with shape priors (2D contour or 3D mesh). Chest X-ray Rat brain structures in MR Microscopy Lung CAD Liver in whole-body CT (PET-CT)

  3. IntroductionBackground • End-to-end, automatic, accurate, efficient. • Robustness • Handle weak or misleading appearance cues. • Handle diseased cases (e.g., with tumor/cancer). • Leverage shape priors to improve the robustness (Active Shape Model, T. Cootes, CVIU’95; 3D ASM for cardiac segmentation, Y. Zheng, TMI’08) Liver shape variations [Springer images] Segmentation system

  4. IntroductionResearch Void • Limitations of existing shape prior methods: • Assume Gaussian errors → Sensitive to outliers • Assume unimodal distribution of shapes → Cannot handle large shape variations, e.g., multimodal • Only keep major variation → Lose local shape detail

  5. IntroductionResearch Void Need to solve all three challenges simultaneously in practice • Handling gross errors or outliers. • RANSAC + ASM [M. Rogers, ECCV’02] • Robust Point Matching [J. Nahed, MICCAI’06] • Handling multimodal distribution of shapes. • Mixture of Gaussians [T. F. Cootes, IVC’97] • Manifold learning for shape prior [Etyngier, ICCV’07] • Patient-specific shape [Y. Zhu, TMI’10] • Preserving local shape details. • Sparse PCA [K. Sjostrand, TMI’07] • Hierarchical ASM [D. Shen, TMI’03]

  6. MethodsSegmentation framework Critical anatomical landmarks. Image Data and Manually Labeled Ground Truths Offline Learning Landmark Detectors Shape Priors via Sparse Shape Representation Boundary Detectors Runtime Segmentation Model Initialize Iterative Deformation and Shape Refinement Final Results New Image

  7. MethodsSegmentation framework • Initialization: Landmark detectors + shape prior • Automatic, fast (AdaBoosting/PBT/random forest + 3D Haar). • Deformation: Boundary detectors + shape prior • Extend the landmark detectors to locate the sub-surfaces. Heart Lung Critical anatomical landmarks. Rib Abdomen Colon 7

  8. MethodsShape prior using sparse shape representation • Our shape prior 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. ... ≈

  9. MethodsShape prior using sparse shape representation • Formulation: • Sparse linear combination: Number of nonzero elements ... ... ≈ ≈ Global transformation operator Global transformation parameter Input y Weight x Dense x Sparse x Aligned shape data matrix D

  10. MethodsShape prior using sparse shape representation • Non-Gaussian errors:

  11. MethodsShape prior using sparse shape representation • Why it works? • Robust: Explicitly modeling “e” with L0 norm constraint. Thus it can detect gross (sparse) errors, i.e., non-Gaussian • General: No assumption of any parametric distribution model (e.g., a unimodal distribution assumption in ASM). Thus it can model large shape variations. • 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.

  12. MethodsOptimization • Convex relaxation [Candes, Tao, T-IT’06]: • Tuning parameters (λ1 and λ2)are not difficult to choose, compared to k1 and k2. • λ1║x║1, λ1 controls thesparsity of x. • λ2║e║1, λ2 controls thesparsity of e. • One group of parameters work well for all images. • Efficient convex optimization: fast proximal gradient methods (e.g., FISTA)

  13. MethodsScalability Dictionary size = 64 #Coefficients = 1000 #Input samples = 1000 1. To efficiently handle many training samples - dictionary learning: ... ... ... ≈ 2. To efficiently handle thousands of vertices - mesh partitioning:

  14. Applications – Part I 2D lung localization in X-ray (Lung computer-aided diagnosis system, Siemens) • Handling gross errors Detection PA ASM RASM NN TPS Sparse1 Sparse2 Procrustes analysis Active Shape Model Robust ASM Nearest Neighbors Thin-plate-spline Without modeling “e” Proposed method

  15. Applications – Part I2D lung localization in X-ray • Multimodal shape distribution Detection PA ASM/RASM NN TPS Sparse1 Sparse2

  16. Applications – Part I2D lung localization in X-ray • Recover local detail information Detection PA ASM/RASM NN TPS Sparse1 Sparse2

  17. Applications – Part I2D lung localization in X-ray • Sparse shape components • ASM modes: ≈ + + 0.5760 0.2156 0.0982

  18. Applications – Part I2D lung localization in X-ray • Mean values and standard deviations. ~1,000 cases. σ µ Left lung Right lung 1)PA, 2)ASM, 3)RASM, 4)NN, 5)TPS, 6)Sparse1, 7)Sparse2

  19. Applications – Part II3D liver segmentation in low-dose CT • Use case: Improved interpretation of PET-CT, with Siemens • PET: Measure functional process (metabolic activity), oncology • CT: Provide anatomical information, co-registered with PET • Issues: High variations of activities across different organs • Solution: Segment organs in CT for organ-specific interpret. • Challenge: Low dose results in low contrast & fuzzy boundary

  20. Applications – Part II3D liver segmentation in low-dose CT Same landmarks + different shape priors Procrustes analysis Sparse shape Ground truth Initialization Deformation Same deformation module

  21. Applications – Part II3D liver segmentation in low-dose CT Procrustes analysis Sparse shape

  22. Applications – Part II3D liver segmentation in low-dose CT Procrustes analysis Sparse shape

  23. Applications – Part II3D liver segmentation in low-dose CT Procrustes analysis Sparse shape

  24. Applications – Part II3D liver segmentation in low-dose CT Procrustes analysis Sparse shape

  25. Applications – Part II3D liver segmentation in low-dose CT • Shape refinement during segmentation ASM-type [Zhan’09] Sparse shape Ground truth

  26. Applications – Part II3D liver segmentation in low-dose CT • Quantitative results: surface distances. ~80 cases Mean value and standard deviation (voxel)

  27. Applications – Part IIISegmentation of Multiple Brain Structures in MRI Human brain, 34 structures Alzheimer's disease (with GE Global Research) Rat brain structures Drug addiction and alcoholism (with Brookhaven National Lab)

  28. Summary of Robust Segmentation • Robustly handle abnormal cases, such as diseased cases (liver tumor). Critical to healthcare applications such as computational diagnosis systems. • Patent with Siemens. Used in several clinical applications. Key contribution for our awarded NSF-MRI grant (’12-’16). • Relevant publications: • First author papers • MICCAI 2012, 2011 (MICCAI Young Scientist Award Finalist) • CVPR 2011 • Two journal papers in Medical Image Analysis • Second author paper • Medical Physics 2013 (with my co-mentored student, G. Wang) • ISBI 2013, oral (with my co-mentored student, Z. Yan)

More Related