MICCAI 2015 Tutorial - Holiday Inn Hotel (Forum 3) - Munich City Center, October 5th

                                                                          
                                                                                                                                                             http://www.miccai2015.org


Organizers

Adrien Depeursinge, PhD, Professor of Computer Science, Institute of Information Systems, HES-SO Valais, 
Research Associate, School of Engineering, EPFL

J Ross Mitchell, PhD, Professor of Radiology, Mayo Clinic College of Medicine,
Chair, Division of Medical Imaging Informatics, Mayo Clinic Arizona

Invited speakers

Michael Unser, PhD, Professor and Director of the Biomedical Imaging Group, 
School of Engineering, EPFL

Leland Hu, MDAssistant Professor of Radiology, Mayo Clinic College of Medicine,
Neuro-radiologist, Mayo Clinic Arizona

Alvin C. Silva, MD, Associate Professor of Radiology, Mayo Clinic College of Medicine, 
Abdominal radiologist, and, Director, Clinical Outcomes and Response Evaluation Lab, Mayo Clinic Arizona


Outline

Texture-based imaging biomarkers complement focal, invasive biopsy based biomarkers by providing information on tissue structure over broad regions, non-invasively, and repeatedly across multiple time points. Texture has been used to predict patient survival, tissue function, disease subtypes and genomics (imagenomics and radiogenomics). Nevertheless, several challenges remain, such as: the lack of an appropriate framework for multi-scale, multi-spectral analysis in 2D and 3D; localization uncertainty of texture operators; validation; and, translation to routine clinical applications.

This tutorial will provide an overview of recent developments and clinical applications in the field of texture analysis in biomedical images. The target audience is general MICCAI attendees with basic knowledge in image processing. The tutorial will be be presented in two parts:
  • Part A will begin with the mathematical foundations of multidimensional texture operators. Then, it will review common algorithms and discuss their limitations. It will conclude by describing research opportunities to address the major challenges outlined above. 
  • Part B, after the coffee break, will focus on clinical applications of texture analysis. Several clinician-scientists will present their research in this area, discuss trends, and outline opportunities for the MICCAI community to contribute to this rapidly emerging field.

This tutorial will encourage the creation of an expert group within the medical image computing community. The organizers will share all teaching material with attendees after the event. This will include links to existing publicly available source code and databases.


Program

13:30    Introduction, J Ross Mitchell, Adrien Depeursinge

Part A – Mathematical foundations of multidimensional texture operators

13:35    Fundamentals of texture processing for biomedical image analysis, Adrien Depeursinge (PDF slides)

14:20    Wavelet-based operators for texture characterization, Michael Unser (PDF slides)


Part B – Clinical applications of texture analysis

15:05    Overview of applications, J Ross Mitchell (PDF slides)

15:40    Coffee break (15min)

15:55    Advanced MRI and texture analysis in gliomas: Clinical perspective, Leland Hu (PDF slides)

16:40    Texture analysis in a core lab / for gastrointestinal pathologies, Alvin Silva


17:25    Closing remarks, J Ross Mitchell, Adrien Depeursinge


Software

Here are some publicly available software for 2D and 3D texture analysis. This list is not exhaustive.

MaZdaFull framework with graphical user interface and image preprocessing under Windows [Szczypinski2009].C++ and Delphi
(compiled for Windows only)
Maximum response 8 (MR8)Implementations of the Leung-Malik (LM), Schmid (S) and Maximum Response (MR) filterbanks [Varma2005].Matlab
Local binary patterns (LBP)Implementation of the LBP operator [Ojala2002].Matlab
Steerable waveletsImplementation of isotropic and steerable wavelets in 2D and 3D [Chenouard2012, Unser2013].
Specific functions for texture analysis based on Riesz wavelets (including feature learning [Depeursinge2014b]) can downloaded here.
Matlab and Java
Gray-level co-occurrence matrix (GLCM)Built-in Matlab functions for computing GLCMs and derive statistics [Haralick1979].Matlab
Potts modelPotts model for unsupervised image segmentation [Storath2014]. Matlab and Java

Databases

Here are some publicly available texture databases. This list is not exhaustive.

Interstitial lung disease (ILD) databaseA multimedia collection of cases with interstitial lung diseases (ILDs). High-resolution computed tomography (HRCT) images with lung volume segmented and regions of interest delineating several classes of lung tissue textures in 2D are available.
Computed Tomography Emphysema DatabaseHRCT images from patients affected with chronic obstructive pulmonary disease (COPD). Three texture classes corresponding to emphysema subtypes are represented in manually segmented 2D square patches.
Outex Texture DatabaseNon-medical set of 2D natural textures with controlled validation schemes (carpets and rugs). The Outex_TC_00010, Outex_TC_00012 and Contrib_TC_00000 test suites have properties that are similar to medical images (i.e., rotation-invariance but no scale-invariance).
RFAI databaseNon-medical set of synthetic solid 3D textures.
Digital Database for Screening Mammography (DDSM)Mammograms digitized by various scanners (3000x4500 pixels with 16-bit pixel depth, pixel size is not known!). An available texture classification task is the differentiation of normal versus microclassification clusters.
Synthetic whole slide images (WSI)Software for synthesizing WSI histopathology images with known underlying texture components [Apou2015].

References

[Aerts2014] Aerts, H. J. W. L.; Velazquez, E. R.; Leijenaar, R. T. H.; Parmar, C.; Grossmann, P.; Carvalho, S.; Bussink, J.; Monshouwer, R.; Haibe-Kains, B.; Rietveld, D.; Hoebers, F.; Rietbergen, M. M.; Leemans, C. R.; Dekker, A.; Quackenbush, J.; Gillies, R. J. & Lambin, P.
Decoding Tumour Phenotype by Noninvasive Imaging Using a Quantitative Radiomics Approach
Nature Communications, Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved, 2014, 5
[Apou2015]Apou, G.; Feuerhake, F.; Forestier, G.; Naegel, B. & Wemmert, Cé.
Synthesizing Whole Slide Images
9th International Symposium on Image and Signal Processing and Analysis (ISPA), 2015
[Cheng2015]Cheng, C. H.; Pradhan, P. M. & Mitchell, J. R.
Texture Analysis of Images Using a Two-Dimensional Fast Time-Frequency Transform
Journal of Medical Imaging, 2015, 2, 024504
[Chenouard2012]Chenouard, N. & Unser, M.
3D Steerable Wavelets in Practice
IEEE Transactions on Image Processing, 2012, 21, 4522-4533
[Depeursinge2014a]Depeursinge, A.; Foncubierta-Rodrguez, A.; Van De Ville, D. & Müller, H.
Three-Dimensional Solid Texture Analysis and Retrieval in Biomedical Imaging: Review and Opportunities
Medical Image Analysis, 2014, 18, 176-196
[Depeursinge2014b]Depeursinge, A.; Foncubierta-Rodrguez, A.; Van De Ville, D. & Müller, H.
Rotation-Covariant Texture Learning Using Steerable Riesz Wavelets
IEEE Transactions on Image Processing, 2014, 23, 898-908
[Depeursinge2015b]Depeursinge, A.; Chin, A. C.; Leung, A. N.; Terrone, D.; Bristow, M.; Rosen, G. & Rubin, D. L.
Automated Classification of Usual Interstitial Pneumonia Using Regional Volumetric Texture Analysis in High-Resolution CT
Investigative Radiology, 2015, 50, 261-267
[Galloway1975]Galloway, M. M.
Texture Analysis Using Gray Level Run Lengths
Computer Graphics and Image Processing, 1975, 4, 172-179
[Gerlinger2012] Gerlinger, M.; Rowan, A. J.; Horswell, S.; Larkin, J.; Endesfelder, D.; Gronroos, E.; Martinez, P.; Matthews, N.; Stewart, A.; Tarpey, P.; Varela, I.; Phillimore, B.; Begum, S.; McDonald, N. Q.; Butler, A.; Jones, D.; Raine, K.; Latimer, C.; Santos, C. R.; Nohadani, M.; Eklund, A. C.; Spencer-Dene, B.; Clark, G.; Pickering, L.; Stamp, G.; Gore, M.; Szallasi, Z.; Downward, J.; Futreal, P. A. & Swanton, C.
Intratumor Heterogeneity and Branched Evolution Revealed by Multiregion Sequencing
New England Journal of Medicine, 2012, 366, 883-892
[Gurcan2009] Gurcan, M. N.; Boucheron, L. E.; Can, A.; Madabhushi, A.; Rajpoot, N. M. & Yener, B.
Histopathological Image Analysis: A Review
IEEE Reviews in Biomedical Engineering, 2009, 2, 147-171
[Haidekker2011]Haidekker, M. A.
Texture Analysis
Advanced Biomedical Image Analysis, John Wiley & Sons, Inc., 2010, 236-275
[Haralick1979]Haralick, R. M.
Statistical and Structural Approaches to Texture
Proceedings of the IEEE, 1979, 67, 786-804
[Malik2001] Malik, J.; Belongie, S.; Leung, T. & Shi, J.
Contour and Texture Analysis for Image Segmentation
International Journal of Computer Vision, Kluwer Academic Publishers, 2001, 43, 7-27
[Ojala2002] Ojala, T.; Pietikäinen, M. & Mäenpää, T.
Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24, 971-987
[Petrou2006] Petrou, M. & Garcia Sevilla, P.
Image Processing: Dealing with Texture
Wiley, 2006
[Petrou2011] Petrou, M.
Deserno, T. M. (Ed.)
Texture in Biomedical Images
Biomedical Image Processing, Springer-Verlag Berlin Heidelberg, 2011, 157-176
[Romeny2011] ter Haar Romeny, B. M.
Deserno, T. M. (Ed.)
Multi-Scale and Multi-Orientation Medical Image Analysis
Biomedical Image Processing, Springer-Verlag Berlin Heidelberg, 2011, 177-196
[Sifre2014] Sifre, L. & Mallat, S.
Rigid-Motion Scattering for Texture Classification
Submitted to International Journal of Computer Vision, 2014, abs/1403.1687, 1-19
[Storath2014] Storath, M.; Weinmann, A. & Unser, M.
Unsupervised Texture Segmentation Using Monogenic Curvelets and the Potts Model
IEEE International Conference on Image Processing (ICIP), 2014, 4348-4352
[Szczypinski2009]Szczypinski, P. M.; Strzelecki, M.; Materka, A. & Klepaczko, A.
MaZda - A Software Package for Image Texture Analysis
Computer Methods and Programs in Biomedicine, 2009, 94, 66-76
[Unser2013] Unser, M. & Chenouard, N.
A Unifying Parametric Framework for 2D Steerable Wavelet Transforms
SIAM Journal on Imaging Sciences, 2013, 6, 102-135
[Varma2005] Varma, M. & Zisserman, A.
A Statistical Approach to Texture Classification from Single Images
International Journal of Computer Vision, Kluwer Academic Publishers, 2005, 62, 61-81

More publications from the organizers can be found here.