Simultaneous Detection and Registration for Ileo-Cecal Valve Detection in 3D CT Colonography

Authors:
Le Lu;Adrian Barbu;Matthias Wolf;Jianming Liang;Luca Bogoni;Marcos Salganicoff;Dorin Comaniciu
Affiliations:
Integrated Data Systems Dept., Siemens Corporate Research, Princeton NJ 08540 and Computer Aided Diagnosis Group, Siemens Medical Solutions, Malvern, USA PA 19355;Integrated Data Systems Dept., Siemens Corporate Research, Princeton NJ 08540;Computer Aided Diagnosis Group, Siemens Medical Solutions, Malvern, USA PA 19355;Computer Aided Diagnosis Group, Siemens Medical Solutions, Malvern, USA PA 19355;Computer Aided Diagnosis Group, Siemens Medical Solutions, Malvern, USA PA 19355;Computer Aided Diagnosis Group, Siemens Medical Solutions, Malvern, USA PA 19355;Integrated Data Systems Dept., Siemens Corporate Research, Princeton NJ 08540
Venue:
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part IV
Year:
2008

Citing 0
Cited 3

Hierarchical segmentation and identification of thoracic vertebra using learning-based edge detection and coarse- to-fine deformable model

MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I
Correcting misalignment of automatic 3D detection by classification: ileo-cecal valve false positive reduction in CT colonography

MCV'10 Proceedings of the 2010 international MICCAI conference on Medical computer vision: recognition techniques and applications in medical imaging
Hierarchical segmentation and identification of thoracic vertebra using learning-based edge detection and coarse-to-fine deformable model

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

Object detection and recognition has achieved a significant progress in recent years. However robust 3D object detection and segmentation in noisy 3D data volumes remains a challenging problem. Localizing an object generally requires its spatial configuration (i.e., pose, size) being aligned with the trained object model, while estimation of an object's spatial configuration is only valid at locations where the object appears. Detecting object while exhaustively searching its spatial parameters, is computationally prohibitive due to the high dimensionality of 3D search space. In this paper, we circumvent this computational complexity by proposing a novel framework capable of incrementally learning the object parameters (IPL) of location, pose and scale. This method is based on a sequence of binary encodings of the projected true positives from the original 3D object annotations (i.e., the projections of the global optima from the global space into the sections of subspaces). The training samples in each projected subspace are labeled as positive or negative, according their spatial registration distances towards annotations as ground-truth. Each encoding process can be considered as a general binary classification problem and is implemented using probabilistic boosting tree algorithm. We validate our approach with extensive experiments and performance evaluations for Ileo-Cecal Valve (ICV) detection in both clean and tagged 3D CT colonography scans. Our final ICV detection system also includes an optional prior learning procedure for IPL which further speeds up the detection.