Robust autonomous model learning from 2D and 3D data sets

Authors:
Georg Langs;René Donner;Philipp Peloschek;Horst Bischof
Affiliations:
GALEN Group, Laboratoire de Mathématiques Appliquées aux Systèmes, Ecole Centrale de Paris, France and Institute for Computer Graphics and Vision, Graz University of Technology, Aus ...;Institute for Computer Graphics and Vision, Graz University of Technology, Austria and Pattern Recognition and Image Processing Group, Vienna University of Technology, Austria;Department of Radiology, Medical University of Vienna, Austria;Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Venue:
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Year:
2007

Citing 7
Cited 9

Statistical analysis with missing data

Statistical analysis with missing data
An introduction to genetic algorithms

An introduction to genetic algorithms
Active Appearance Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
3D Statistical Shape Models Using Direct Optimisation of Description Length

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Multiple appearance models

Pattern Recognition
Vertebral shape: automatic measurement with dynamically sequenced active appearance models

MICCAI'05 Proceedings of the 8th international conference on Medical image computing and computer-assisted intervention - Volume Part II
A unified information-theoretic approach to groupwise non-rigid registration and model building

IPMI'05 Proceedings of the 19th international conference on Information Processing in Medical Imaging

Weakly Supervised Group-Wise Model Learning Based on Discrete Optimization

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Wavelet-driven knowledge-based MRI calf muscle segmentation

ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Evaluating deformation patterns of the thoracic aorta in gated CTA sequences

ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Constructing part-based models for groupwise registration

ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Facial contour labeling via congealing

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Automatic learning sparse correspondences for initialising groupwise registration

MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part II
Automatic part selection for groupwise registration

IPMI'11 Proceedings of the 22nd international conference on Information processing in medical imaging
Semi-supervised facial landmark annotation

Computer Vision and Image Understanding
VISCERAL: towards large data in medical imaging -- challenges and directions

MCBR-CDS'12 Proceedings of the Third MICCAI international conference on Medical Content-Based Retrieval for Clinical Decision Support

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we propose a weakly supervised learning algorithm for appearance models based on the minimum description length (MDL) principle. From a set of training images or volumes depicting examples of an anatomical structure, correspondences for a set of landmarks are established by group-wise registration. The approach does not require any annotation. In contrast to existing methods no assumptions about the topology of the data are made, and the topology can change throughout the data set. Instead of a continuous representation of the volumes or images, only sparse finite sets of interest points are used to represent the examples during optimization. This enables the algorithm to efficiently use distinctive points, and to handle texture variations robustly. In contrast to standard elasticity based deformation constraints the MDL criterion accounts for systematic deformations typical for training sets stemming from medical image data. Experimental results are reported for five different 2D and 3D data sets.