论文信息 - Localization of intervertebral lumbar discs

Localization of intervertebral lumbar discs

Aim of this study is to localize intervertebral discs from MR images. The study implements a system that uses HOG-SVM based method which was used in previous studies. In addition to this, the study uses projection method to obtain better results. Intensity values of MR images can vary from sample to sample. HOG features provide better results by using gradient values instead of using pure intensity values. Vertical and horizontal gradient information is used through the features obtained by projection method. This information provides better detection results.

Ayse Betül Oktay | Yusuf Sinan Akgül | Nur Banu Albayrak

[1] Ayse Betül Oktay,et al. Localization of the Lumbar Discs Using Machine Learning and Exact Probabilistic Inference , 2011, MICCAI.

[2] Du-Yih Tsai,et al. Automatic determination of the imaging plane in lumbar MRI , 2006, SPIE Medical Imaging.

[3] Sebastian P. M. Dries,et al. Spine Detection and Labeling Using a Parts-Based Graphical Model , 2007, IPMI.

[4] Paul A. Viola,et al. Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[5] Paul A. Viola,et al. Robust Real-time Object Detection , 2001 .

[6] Jason J. Corso,et al. Lumbar Disc Localization and Labeling with a Probabilistic Model on Both Pixel and Object Features , 2008, MICCAI.

[7] Jason J. Corso,et al. Labeling of Lumbar Discs Using Both Pixel- and Object-Level Features With a Two-Level Probabilistic Model , 2011, IEEE Transactions on Medical Imaging.

[8] Andrew Zisserman,et al. Representing shape with a spatial pyramid kernel , 2007, CIVR '07.