Motion artifact detection in confocal laser endomicroscopy images
Standard
Motion artifact detection in confocal laser endomicroscopy images. / Stoeve, Maike; Aubreville, Marc; Oetter, Nicolai; Knipfer, Christian; Neumann, Helmut; Stelzle, Florian; Maier, Andreas.
In: Informatik aktuell, No. 211279, 2018, p. 328-333.Research output: SCORING: Contribution to journal › Conference article in journal › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Motion artifact detection in confocal laser endomicroscopy images
AU - Stoeve, Maike
AU - Aubreville, Marc
AU - Oetter, Nicolai
AU - Knipfer, Christian
AU - Neumann, Helmut
AU - Stelzle, Florian
AU - Maier, Andreas
PY - 2018
Y1 - 2018
N2 - Confocal Laser Endomicroscopy (CLE), an optical imaging technique allowing non-invasive examination of the mucosa on a (sub)- cellular level, has proven to be a valuable diagnostic tool in gastroenterology and shows promising results in various anatomical regions including the oral cavity. Recently, the feasibility of automatic carcinoma detection for CLE images of sufficient quality was shown. However, in real world data sets a high amount of CLE images is corrupted by artifacts. Amongst the most prevalent artifact types are motion-induced image deteriorations. In the scope of this work, algorithmic approaches for the automatic detection of motion artifact-tainted image regions were developed. Hence, this work provides an important step towards clinical applicability of automatic carcinoma detection. Both, conventional machine learning and novel, deep learning-based approaches were assessed. The deep learning-based approach outperforms the conventional approaches, attaining an AUC of 0.90.
AB - Confocal Laser Endomicroscopy (CLE), an optical imaging technique allowing non-invasive examination of the mucosa on a (sub)- cellular level, has proven to be a valuable diagnostic tool in gastroenterology and shows promising results in various anatomical regions including the oral cavity. Recently, the feasibility of automatic carcinoma detection for CLE images of sufficient quality was shown. However, in real world data sets a high amount of CLE images is corrupted by artifacts. Amongst the most prevalent artifact types are motion-induced image deteriorations. In the scope of this work, algorithmic approaches for the automatic detection of motion artifact-tainted image regions were developed. Hence, this work provides an important step towards clinical applicability of automatic carcinoma detection. Both, conventional machine learning and novel, deep learning-based approaches were assessed. The deep learning-based approach outperforms the conventional approaches, attaining an AUC of 0.90.
UR - http://www.scopus.com/inward/record.url?scp=85043326711&partnerID=8YFLogxK
U2 - 10.1007/978-3-662-56537-7_85
DO - 10.1007/978-3-662-56537-7_85
M3 - Conference article in journal
AN - SCOPUS:85043326711
SP - 328
EP - 333
IS - 211279
T2 - Workshop on Bildverarbeitung fur die Medizin, 2018
Y2 - 11 March 2018 through 13 March 2018
ER -