30.09.2011 Tutorial Slides online.

22.09.2011 Tutorial date.

07.08.2011 Deadline for sending abstract and (spotlight or full) presentations to be included in the proceedings USB.

25.07.2011 Deadline for sending final title.

17.03.2011 Tutorial website online.

Manifold learning methods are adaptable data-representation techniques that enable dimensionality reduction and processing tasks in meaningful spaces. Their success in medical image analysis as well as in other scientific fields lies in both, their flexibility and the simplicity of their application. In medical imaging, manifold learning has been successfully used to visualize, cluster, classify and fuse high dimensional data, as well as for Content Based Image Retrieval (CBIR), segmentation, registration, statistical population analysis and shape modelling and classification.

The purpose of this tutorial is to give an overview of manifold learning theory, methods and applications. The full-day tutorial will include an introductory part where the mathematical basis and a review of important algorithms for manifold learning are explained and a second part where its applications in medical imaging and computer-aided interventions are discussed in detail. The tutorial is organized by members of three groups involved in the state-of the art development of solutions based on manifold learning.

Diana Mateus

Selen Atasoy

Paul Aljabar

Anant Madabhushi

Daniel Rueckert

Nassir Navab
Computer Aided Medical Procedures (CAMP) - Technical University Munich

CAMP - Technical University Munich / Imperial College London (ICL)

Biomedical Image Analysis Group (BioMedIA) - Imperial College London (ICL)

Laboratory for Computational Imaging and Bioinformatics (LCIB) - Rutgers University

Biomedical Image Analysis Group (BioMedIA) - Imperial College London (ICL)

Computer Aided Medical Procedures (CAMP) - Technical University Munich
  • Robert Pless, (Washington University).
  • Diana Mateus, Selen Atasoy, Christian Wachinger (CAMP-TUM).
  • Robin Wolz, Paul Aljabar (BioMedAI-ICL).
  • Satish Viswanath, Pallavi Tiwari, Anant Madabhushi (LCIB-Rutgers).
  • Samuel Gerber (University of Utah).
  • Samuel Kadoury (Philips Research North America).

The tutorial material will address the technical background and applications of manifold learning, and will include an introductory part designed for delegates with different backgrounds. We welcome:
  • MICCAI attendants who want to become aware of what manifold learning is.
  • Students and researchers working with manifold learning interested in:
    • Further applications where the methods are used.
    • Discussing difficulties encountered, open questions, new trends, etc.

Morning session (09:00 - 12:00) - Introduction to Manifold Learning

09:00 - 09:15 Organisers Welcome
09:15 - 10:15 Robert Pless (Washington University) KEYNOTE: Learning, Using, and Visualizing Manifolds of Images (Slides)
10:15 - 10:30 Discussion Discussion
10:30 - 10:45 Break Break
10:45 - 11:15 Diana Mateus Manifold Learning: Practical Difficulties and Current Solutions (Slides, audio on request)
11:15 - 11:45 Pallavi Tiwari Multi-kernel learning and semi-supervised embeddings
11:45 - 12:00 Discussion Discussion
Afternoon session (13:00-17:30) - Applications
13:00 - 13:30 Samuel Kadoury Manifold embedding for modeling spinal deformations (Slides)
13:30 - 14:00 Selen Atasoy Image Similarities for learning video manifolds (Slides)
14:00 - 14:30 Satish Viswanath Consensus Embedding: object detection and data fusion
14:30 - 15:00 Samuel Gerber Statistical Underpinnings of manifold learning on brain MRI (Best Paper Award MICCAI 2009) (Slides)
15:00 - 15:15 Discussion Discussion
15:15 - 15:45 Break Break
15:45 - 16:15 Rachel Sparks Manifold learning for shape retrieval (Slides)
16:15 - 16:45 Christian Wachinger/Loren Schwarz Multi-modal registration/Ultrasound Gating (Slides)
16:45 - 17:15 Robin Wolz LEAP: Learning embeddings for atlas propagation (Slides)
17:15 - 17:30 Discussion Discussion