Regression Forest-Based Organ Detection in Normalized PET Images

Conference contribution
(Original article)

Publication Details

Author(s): Fischer P, Daum V, Hahn D, Prümmer M, Hornegger J
Title edited volumes: Informatik aktuell
Publisher: Springer
Publishing place: Berlin Heidelberg
Publication year: 2014
Title of series: Informatik aktuell
Conference Proceedings Title: Bildverarbeitung für die Medizin 2014
Pages range: 384-389
ISSN: 1431-472X


The detection of organs from full-body PET images is a challenging task due to the high noise and the limited amount of anatomical information of PET imaging. The knowledge of organ locations can support many clinical applications like image registration or tumor detection. This paper is the first to propose an organ localization framework tailored on the challenges of PET. The algorithm involves intensity normalization, feature extraction and regression forests. Linear and nonlinear intensity normalization methods are compared theoretically and experimentally. From the normalized images, long-range spatial context visual features are extracted. A regression forest predicts the organ bounding boxes. Experiments show that percentile normalization is the best preprocessing method. The algorithm is evaluated on 25 clinical images with a spatial resolution of 5 mm. With 13.8mm mean absolute bounding box error, it achieves state-of-the-art results.

FAU Authors / FAU Editors

Daum, Volker Dr.
Graduiertenzentrum der FAU
Fischer, Peter
Lehrstuhl für Informatik 5 (Mustererkennung)
Hornegger, Joachim Prof. Dr.-Ing.
Lehrstuhl für Informatik 5 (Mustererkennung)

How to cite

Fischer, P., Daum, V., Hahn, D., Prümmer, M., & Hornegger, J. (2014). Regression Forest-Based Organ Detection in Normalized PET Images. In Bildverarbeitung für die Medizin 2014 (pp. 384-389). Aachen: Berlin Heidelberg: Springer.

Fischer, Peter, et al. "Regression Forest-Based Organ Detection in Normalized PET Images." Proceedings of the Bildverarbeitung für die Medizin 2014, Aachen Berlin Heidelberg: Springer, 2014. 384-389.


Last updated on 2018-19-04 at 02:53