Automatic Spatial Plausibility Checks for Medical Object Recognition
Results Using a Spatio-Anatomical Ontology
M. Möller, P. Ernst, D. Sonntag, and A. Dengel. Proc. of the International Conference on Knowledge Discovery and Information Retrieval (KDIR 2010), Valencia, Spain, (25 - 28 October 2010)
Abstract
We present an approach to use medical expert knowledge represented
in formal ontologies to check the results of automatic medical object
recognition algorithms for spatial plausibility. Our system is based
on the comprehensive Foundation Model of Anatomy ontology which we
extend with spatial relations between a number of anatomical entities.
These relations are learned inductively from an annotated corpus
of 3D volume data sets. The induction process is split into two parts:
First, we generate a quantitative anatomical atlas using fuzzy sets
to represent inherent imprecision. From this atlas we abstract onto
a purely symbolic level to generate a generic qualitative model of
the spatial relations in human anatomy. In our evaluation we describe
how this model can be used to check the results of a state-of-the-art
medical object recognition system for 3D CT volume data sets for
spatial plausibility. Our results show that the combination of medical
domain knowledge in formal ontologies and sub-symbolic object recognition
yields improved overall recognition precision.
%0 Conference Paper
%1 Moeller2010b
%A Möller, Manuel
%A Ernst, Patrick
%A Sonntag, Daniel
%A Dengel, Andreas
%B Proc. of the International Conference on Knowledge Discovery and Information Retrieval (KDIR 2010)
%C Valencia, Spain
%D 2010
%K medico
%T Automatic Spatial Plausibility Checks for Medical Object Recognition
Results Using a Spatio-Anatomical Ontology
%X We present an approach to use medical expert knowledge represented
in formal ontologies to check the results of automatic medical object
recognition algorithms for spatial plausibility. Our system is based
on the comprehensive Foundation Model of Anatomy ontology which we
extend with spatial relations between a number of anatomical entities.
These relations are learned inductively from an annotated corpus
of 3D volume data sets. The induction process is split into two parts:
First, we generate a quantitative anatomical atlas using fuzzy sets
to represent inherent imprecision. From this atlas we abstract onto
a purely symbolic level to generate a generic qualitative model of
the spatial relations in human anatomy. In our evaluation we describe
how this model can be used to check the results of a state-of-the-art
medical object recognition system for 3D CT volume data sets for
spatial plausibility. Our results show that the combination of medical
domain knowledge in formal ontologies and sub-symbolic object recognition
yields improved overall recognition precision.
@inproceedings{Moeller2010b,
abstract = {We present an approach to use medical expert knowledge represented
in formal ontologies to check the results of automatic medical object
recognition algorithms for spatial plausibility. Our system is based
on the comprehensive Foundation Model of Anatomy ontology which we
extend with spatial relations between a number of anatomical entities.
These relations are learned inductively from an annotated corpus
of 3D volume data sets. The induction process is split into two parts:
First, we generate a quantitative anatomical atlas using fuzzy sets
to represent inherent imprecision. From this atlas we abstract onto
a purely symbolic level to generate a generic qualitative model of
the spatial relations in human anatomy. In our evaluation we describe
how this model can be used to check the results of a state-of-the-art
medical object recognition system for 3D CT volume data sets for
spatial plausibility. Our results show that the combination of medical
domain knowledge in formal ontologies and sub-symbolic object recognition
yields improved overall recognition precision.},
added-at = {2010-07-13T09:30:13.000+0200},
address = {Valencia, Spain},
author = {M\"oller, Manuel and Ernst, Patrick and Sonntag, Daniel and Dengel, Andreas},
biburl = {https://www.bibsonomy.org/bibtex/2973c6aaf46703816d1db62573e43b742/manuelm},
booktitle = {Proc. of the International Conference on Knowledge Discovery and Information Retrieval (KDIR 2010)},
interhash = {7d89e8b417712b843a7cc1758ba077e3},
intrahash = {973c6aaf46703816d1db62573e43b742},
keywords = {medico},
month = {25 - 28 October},
timestamp = {2010-07-13T09:30:56.000+0200},
title = {Automatic Spatial Plausibility Checks for Medical Object Recognition
Results Using a Spatio-Anatomical Ontology},
year = 2010
}