TY - JOUR
T1 - Multi-disciplinary modality classification for medical images
AU - Gál, Viktor
AU - Solt, Illés
AU - Gedeon, Tom
AU - Nachtegael, Mike
PY - 2011
Y1 - 2011
N2 - Modality is a key facet in medical image retrieval, as a user is likely interested in only one of e.g. radiology images, flowcharts, and pathology photos. While assessing image modality is trivial for humans, reliable automatic methods are required to deal with large un-annotated image bases, such as figures taken from the millions of scientific publications. We present a multi-disciplinary approach to tackle the classification problem by combining image features, meta-data, textual and referential information. Our system achieved an accuracy of 96.86% in cross-validation on the ImageCLEF 2011 training dataset having 18 imbalanced modality classes, and an accuracy of 90.2% on the Image- CLEF2010 dataset having 8 well-balanced modality classes. We evaluate the importance of the individual feature sets in detail, and provide an error analysis pointing at weaknesses of our method and obstacles in the classification task. For the benefit of the image classification community, we make the results of our feature extraction methods publicly available at http://categorizer.tmit.bme.hu/illes/imageclef2011modality. Keywords: image classification, image feature extraction, image modality, text mining.
AB - Modality is a key facet in medical image retrieval, as a user is likely interested in only one of e.g. radiology images, flowcharts, and pathology photos. While assessing image modality is trivial for humans, reliable automatic methods are required to deal with large un-annotated image bases, such as figures taken from the millions of scientific publications. We present a multi-disciplinary approach to tackle the classification problem by combining image features, meta-data, textual and referential information. Our system achieved an accuracy of 96.86% in cross-validation on the ImageCLEF 2011 training dataset having 18 imbalanced modality classes, and an accuracy of 90.2% on the Image- CLEF2010 dataset having 8 well-balanced modality classes. We evaluate the importance of the individual feature sets in detail, and provide an error analysis pointing at weaknesses of our method and obstacles in the classification task. For the benefit of the image classification community, we make the results of our feature extraction methods publicly available at http://categorizer.tmit.bme.hu/illes/imageclef2011modality. Keywords: image classification, image feature extraction, image modality, text mining.
UR - http://www.scopus.com/inward/record.url?scp=84922022467&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:84922022467
SN - 1613-0073
VL - 1177
JO - CEUR Workshop Proceedings
JF - CEUR Workshop Proceedings
T2 - 2011 Cross Language Evaluation Forum Conference, CLEF 2011
Y2 - 19 September 2011 through 22 September 2011
ER -