Accurate and efficient linear structure segmentation by leveraging ad hoc features with learned filters

Authors:
Roberto Rigamonti;Vincent Lepetit
Affiliations:
CVLab, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland;CVLab, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
Venue:
MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Year:
2012

Citing 10
Cited 0

Model-based detection of tubular structures in 3D images

Computer Vision and Image Understanding
Random Forests

Machine Learning
Muliscale Vessel Enhancement Filtering

MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
The relationship between Precision-Recall and ROC curves

ICML '06 Proceedings of the 23rd international conference on Machine learning
An Interior-Point Method for Large-Scale l1-Regularized Logistic Regression

The Journal of Machine Learning Research
Three Dimensional Curvilinear Structure Detection Using Optimally Oriented Flux

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part IV
Automatic centerline extraction of irregular tubular structures using probability volumes from multiphoton imaging

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
Are sparse representations really relevant for image classification?

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Rapid automated three-dimensional tracing of neurons from confocal image stacks

IEEE Transactions on Information Technology in Biomedicine
Automatic segmentation and skeletonization of neurons from confocal microscopy images based on the 3-D wavelet transform

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Extracting linear structures, such as blood vessels or dendrites, from images is crucial in many medical imagery applications, and many handcrafted features have been proposed to solve this problem. However, such features rely on assumptions that are never entirely true. Learned features, on the other hand, can capture image characteristics difficult to define analytically, but tend to be much slower to compute than handcrafted features. We propose to complement handcrafted methods with features found using very recent Machine Learning techniques, and we show that even few filters are sufficient to efficiently leverage handcrafted features. We demonstrate our approach on the STARE, DRIVE, and BF2D datasets, and on 2D projections of neural images from the DIADEM challenge. Our proposal outperforms handcrafted methods, and pairs up with learning-only approaches at a fraction of their computational cost.