28 February 2013 Region detection in medical images using HOG classifiers and a body landmark network
Author Affiliations +
Proceedings Volume 8670, Medical Imaging 2013: Computer-Aided Diagnosis; 867004 (2013) https://doi.org/10.1117/12.2007384
Event: SPIE Medical Imaging, 2013, Lake Buena Vista (Orlando Area), Florida, United States
Abstract
Automatic detection of anatomical structures and regions in 3D medical images is important for several computer aided diagnosis tasks. In this work, a new method for simultaneous detection of multiple anatomical areas is proposed. The method consists of two steps: first, single rectangular region candidates are detected independently using 3D variants of Histograms of Oriented Gradients (HOG) features. These features are robust against small changes between regions in rotation and scale which typically occur between different individuals. In a second step, the positions of the detected candidates are refined by incorporating a body landmark network that exploits anatomical relations between different structures. The landmark network consists of a principle component based statistical modeling of the relative positions between the detected regions in training images. The method has been evaluated on thoracic/abdominal CT images of the portal venous phase. In 216 CT images, eight different structures have been trained. Results show an increase in performance using the combination of HOGs and the landmark network in comparison to using independent classifiers without anatomical relations.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Marius Erdt, Marius Erdt, Oliver Knapp, Oliver Knapp, Klaus Drechsler, Klaus Drechsler, Stefan Wesarg, Stefan Wesarg, } "Region detection in medical images using HOG classifiers and a body landmark network", Proc. SPIE 8670, Medical Imaging 2013: Computer-Aided Diagnosis, 867004 (28 February 2013); doi: 10.1117/12.2007384; https://doi.org/10.1117/12.2007384
PROCEEDINGS
7 PAGES


SHARE
Back to Top