Robust Automatic Co-segmentation of Multiple Medical Images T. Liu 1 - - PowerPoint PPT Presentation

▶
robust automatic co segmentation of multiple medical
SMART_READER_LITE
LIVE PREVIEW

Robust Automatic Co-segmentation of Multiple Medical Images T. Liu 1 - - PowerPoint PPT Presentation

Sep 05, 2023 180 likes •376 views

Robust Automatic Co-segmentation of Multiple Medical Images T. Liu 1 , D. Floros 2 , N, Pitsianis 21 , X. Sun 1 , L. Ren 3 , F. Yin 3 59 th AAPM Annual Meeting, Denver, CO July 30, 2017 1 Department of Computer Science, Duke University, USA 2

slide-1
SLIDE 1

Robust Automatic Co-segmentation

  • f Multiple Medical Images
  • T. Liu1, D. Floros2, N, Pitsianis21, X. Sun1, L. Ren3, F. Yin3

59th AAPM Annual Meeting, Denver, CO July 30, 2017

1Department of Computer Science, Duke University, USA 2Department of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Greece 3Department of Radiation Oncology, Duke University School of Medicine, USA

1 / 9

slide-2
SLIDE 2

Introduction: from segmentation to co-segmentation

+ Texture-based segmentation1:

– Intra-region texture homogeneity – Inter-region texture heterogeneity

Thoracic CT slice i Segmentation of slice i (colors == region labels)

CT and atlas data from the AAPM LCTSC dataset

1 [Belongie et al. ICCV, 1998]

[Cimpoi et al. ICCV, 2015] [Shi et al. IEEE Trans. PAML, 2000]

2 [Rother et al. CVPR, 2006]

[Rubio et al. CVPR, 2012]

3 [Wang et al. IEEE Trans. PAML, 2010], [Iglesias et al. Med Image Anal, 2015]

2 / 9

slide-3
SLIDE 3

Introduction: from segmentation to co-segmentation

+ Texture-based segmentation1:

– Intra-region texture homogeneity – Inter-region texture heterogeneity

+ Texture-based co-segmentation2:

– Simultaneous segmentation – Inter-image region correspondence

Thoracic CT slice i Thoracic CT slice j Co-segmentation of slice i Co-segmentation of slice j

CT and atlas data from the AAPM LCTSC dataset

1 [Belongie et al. ICCV, 1998]

[Cimpoi et al. ICCV, 2015] [Shi et al. IEEE Trans. PAML, 2000]

2 [Rother et al. CVPR, 2006]

[Rubio et al. CVPR, 2012]

3 [Wang et al. IEEE Trans. PAML, 2010], [Iglesias et al. Med Image Anal, 2015]

2 / 9

slide-4
SLIDE 4

Introduction: from segmentation to co-segmentation

+ Texture-based segmentation1:

– Intra-region texture homogeneity – Inter-region texture heterogeneity

+ Texture-based co-segmentation2:

– Simultaneous segmentation – Inter-image region correspondence

* Atlas guided segmentation3: special case of co-segmentation

Thoracic CT slice i Thoracic CT slice j Provided labels of slice i Generated labels of slice j

CT and atlas data from the AAPM LCTSC dataset

1 [Belongie et al. ICCV, 1998]

[Cimpoi et al. ICCV, 2015] [Shi et al. IEEE Trans. PAML, 2000]

2 [Rother et al. CVPR, 2006]

[Rubio et al. CVPR, 2012]

3 [Wang et al. IEEE Trans. PAML, 2010], [Iglesias et al. Med Image Anal, 2015]

2 / 9

slide-5
SLIDE 5

Purpose: Automatic co-segmentation

INPUT:

– CT slice i equipped with provided atlas (labels) – CT slice j without labels

OUTPUT:

– Automatically generated atlas (labels) of CT slice j

+ Provide texture homogeneity information for further image processing tasks (e.g. adaptive denoising1, registration) + Identify (label) organs of interest in query image guided by atlas

1Dimitris Floros’ talk on Wednesday, August 02: WE-G-201-6

3 / 9

slide-6
SLIDE 6

Method: co-segmentation by utilizing texture similarity and atlas

Patch: texture element (local signal structure and noise statistics)

pixela Pa pixelb Pb

Patch similarity weight: w(Pa, Pb) = exp

  • − Pa−Pb2

2

σ2

f

  • 4 / 9
slide-7
SLIDE 7

Method: co-segmentation by utilizing texture similarity and atlas

Patch: texture element (local signal structure and noise statistics) Joint weight matrix:

AT

ij

Aij Aii Ajj

intra-image inter-image

pixela Pa pixelb Pb

Patch similarity weight: w(Pa, Pb) = exp

  • − Pa−Pb2

2

σ2

f

  • 4 / 9
slide-8
SLIDE 8

Result part 1: co-segmentation by texture similarity alone

Thoracic CT slice i Thoracic CT slice j

Provide texture homogeneity information for further image processing tasks (e.g. adaptive denoising, registration) Co-segmentation via texture similarity and graph spectral embedding and clustering 1

1 [Shi et al. IEEE Trans. PAML, 2000]

5 / 9

slide-9
SLIDE 9

Results part 2: co-segmentation for label (atlas) transferring

Co-segmentation with texture only Co-segmentation with atlas labels guidance

Observation: Similar textures between heart and aorta Solution: incorporate label and spatial relationship into joint similarity matrix

6 / 9

slide-10
SLIDE 10

Method: co-segmentation for label (atlas) transferring

p – a subset of heart patches q – a subset of aorta patches

AT

ij

Aij Aii Ajj

App Apq Aqp Aqq

p ⊂ Ii q ⊂ Ij p ⊂ Ii q ⊂ Ij

Aqp Apq App Aqq

similarity submatrix: texture-only

w(Pa, Pb) = exp

  • − Pa−Pb2

2

σ2

f

  • 7 / 9
slide-11
SLIDE 11

Method: co-segmentation for label (atlas) transferring

p – a subset of heart patches q – a subset of aorta patches

AT

ij

Aij Aii Ajj

App Apq Aqp Aqq

p ⊂ Ii q ⊂ Ij p ⊂ Ii q ⊂ Ij

ˆ Aqp ˆ Apq ˆ App ˆ Aqq

similarity submatrix: with feature, atlas and spatial relationship

w(Pa, Pb) = exp

  • − Pa−Pb2

2

σ2

f

− xa−xb2

2

σ2

s

− 1−δ(la−lb)2

2

σ2

l

  • xa – spatial coordinates of Pa

la – atlas label of Pa (if available)

7 / 9

slide-12
SLIDE 12

Results part 2: co-segmentation for label (atlas) transferring

Thoracic CT slice i Co-segmentation of slice i Provided labels of slice i Thoracic CT slice j Co-segmentation of slice j

8 / 9

slide-13
SLIDE 13

Results part 2: co-segmentation for label (atlas) transferring

Thoracic CT slice i Co-segmentation of slice i Provided labels of slice i Thoracic CT slice j Co-segmentation of slice j

Transferred labels of slice j

8 / 9

slide-14
SLIDE 14

Summary

– Enable the texture-based co-segmentation for registration and denoising – Transfer labels from reference image (with atlas labels) to query images In Progress: – Transferring labels (atlas info) between different scans/patient – Transferring labels between different patients

9 / 9

slide-15
SLIDE 15

Thank you!

Tiancheng Liu – tcliu@cs.duke.edu

9 / 9

slide-16
SLIDE 16

References i

  • R. Castillo, E. Castillo, R. Guerra, V. E. Johnson, T. McPhail, A. K. Garg, and
  • T. Guerrero.

A framework for evaluation of deformable image registration spatial accuracy using large landmark point sets. Physics in medicine and biology, 54(7):1849, 2009.

  • X. Chen, J. K. Udupa, U. Bagci, Y. Zhuge, and J. Yao.

Medical image segmentation by combining graph cuts and oriented active appearance models. IEEE Transactions on Image Processing, 21(4):2035–2046, 2012.

  • R. C. Craddock, G. James, P. E. Holtzheimer, X. P. Hu, and H. S. Mayberg.

A whole brain fmri atlas generated via spatially constrained spectral clustering. Human Brain Mapping, 33(8):1914–1928, 2012.

slide-17
SLIDE 17

References ii

  • A. L. Dulmage and N. S. Mendelsohn.

Coverings of bipartite graphs. Canadian Journal of Mathematics, 10(4):516–534, 1958.

  • L. Grady and G. Funka-Lea.

Multi-label image segmentation for medical applications based on graph-theoretic electrical potentials. In Computer Vision and Mathematical Methods in Medical and Biomedical Image Analysis, pages 230–245. Springer, 2004.

  • V. Grau, A. Mewes, M. Alcaniz, R. Kikinis, and S. K. Warfield.

Improved watershed transform for medical image segmentation using prior information. IEEE transactions on medical imaging, 23(4):447–458, 2004.

slide-18
SLIDE 18

References iii

  • B. N. Li, C. K. Chui, S. Chang, and S. H. Ong.

Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation. Computers in biology and medicine, 41(1):1–10, 2011.

  • A. Y. Ng, M. I. Jordan, Y. Weiss, et al.

On spectral clustering: Analysis and an algorithm. In NIPS, volume 14, pages 849–856, 2001.

  • H. Ng, S. Ong, K. Foong, P. Goh, and W. Nowinski.

Medical image segmentation using k-means clustering and improved watershed algorithm. In Image Analysis and Interpretation, 2006 IEEE Southwest Symposium on, pages 61–65. IEEE, 2006.

slide-19
SLIDE 19

References iv

  • D. L. Pham, C. Xu, and J. L. Prince.

Current methods in medical image segmentation. Annual review of biomedical engineering, 2(1):315–337, 2000.

  • U. Von Luxburg.

A tutorial on spectral clustering. Statistics and computing, 17(4):395–416, 2007.