Classification of breast tumors solely based on dynamic contrast enhanced magnetic resonance data is a challenge in clinical research. In this paper, we analyze how the most suspect region as group of similarly perfused and spatially connected voxels of a breast tumor contributes to distinguishing between benign and malignant tumors. We use three density-based clustering algorithms to partition a tumor in regions and depict the most suspect one, as delivered by the most stable clustering algorithm. We use the properties of this region for each tumor as input to a classifier. Our preliminary results show that the classifier separates between benign and malignant tumors, and returns predictive attributes that are intuitive to the expert.
%0 Book Section
%1 noKey
%A Glaßer, Sylvia
%A Niemann, Uli
%A Preim, Uta
%A Preim, Bernhard
%A Spiliopoulou, Myra
%B Bildverarbeitung für die Medizin 2013
%D 2013
%E Meinzer, Hans-Peter
%E Deserno, Thomas Martin
%E Handels, Heinz
%E Tolxdorff, Thomas
%I Springer Berlin Heidelberg
%K myown
%P 45-50
%R 10.1007/978-3-642-36480-8_10
%T Classification of Benign and Malignant DCE-MRI Breast Tumors by Analyzing the Most Suspect Region
%U http://dx.doi.org/10.1007/978-3-642-36480-8_10
%X Classification of breast tumors solely based on dynamic contrast enhanced magnetic resonance data is a challenge in clinical research. In this paper, we analyze how the most suspect region as group of similarly perfused and spatially connected voxels of a breast tumor contributes to distinguishing between benign and malignant tumors. We use three density-based clustering algorithms to partition a tumor in regions and depict the most suspect one, as delivered by the most stable clustering algorithm. We use the properties of this region for each tumor as input to a classifier. Our preliminary results show that the classifier separates between benign and malignant tumors, and returns predictive attributes that are intuitive to the expert.
%@ 978-3-642-36479-2
@incollection{noKey,
abstract = {Classification of breast tumors solely based on dynamic contrast enhanced magnetic resonance data is a challenge in clinical research. In this paper, we analyze how the most suspect region as group of similarly perfused and spatially connected voxels of a breast tumor contributes to distinguishing between benign and malignant tumors. We use three density-based clustering algorithms to partition a tumor in regions and depict the most suspect one, as delivered by the most stable clustering algorithm. We use the properties of this region for each tumor as input to a classifier. Our preliminary results show that the classifier separates between benign and malignant tumors, and returns predictive attributes that are intuitive to the expert.},
added-at = {2014-08-07T11:55:42.000+0200},
author = {Glaßer, Sylvia and Niemann, Uli and Preim, Uta and Preim, Bernhard and Spiliopoulou, Myra},
biburl = {https://www.bibsonomy.org/bibtex/244eb5dbac512bb3933d1f9b084199fcf/uli.niemann},
booktitle = {Bildverarbeitung für die Medizin 2013},
doi = {10.1007/978-3-642-36480-8_10},
editor = {Meinzer, Hans-Peter and Deserno, Thomas Martin and Handels, Heinz and Tolxdorff, Thomas},
interhash = {414fdba6151863aa96497da6a3d29217},
intrahash = {44eb5dbac512bb3933d1f9b084199fcf},
isbn = {978-3-642-36479-2},
keywords = {myown},
language = {German},
pages = {45-50},
publisher = {Springer Berlin Heidelberg},
series = {Informatik aktuell},
timestamp = {2014-08-07T11:55:42.000+0200},
title = {Classification of Benign and Malignant DCE-MRI Breast Tumors by Analyzing the Most Suspect Region},
url = {http://dx.doi.org/10.1007/978-3-642-36480-8_10},
year = 2013
}