ImageCLEF 2009 medical image annotation task: PCTs for hierarchical multi-label classification

Authors:
Ivica Dimitrovski;Dragi Kocev;Suzana Loskovska;Sašo Džeroski
Affiliations:
Department of Knowledge Technologies, Jozef Stefan Institute, Ljubljana, Slovenia and Department of Computer Science, Faculty of Electrical Engineering and Information Technologies, Skopje, Macedo ...;Department of Knowledge Technologies, Jozef Stefan Institute, Ljubljana, Slovenia;Department of Computer Science, Faculty of Electrical Engineering and Information Technologies, Skopje, Macedonia;Department of Knowledge Technologies, Jozef Stefan Institute, Ljubljana, Slovenia
Venue:
CLEF'09 Proceedings of the 10th international conference on Cross-language evaluation forum: multimedia experiments
Year:
2009

Citing 11
Cited 3

A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Bagging predictors

Machine Learning
Random Forests

Machine Learning
Top-Down Induction of Clustering Trees

ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Discriminative Training for Object Recognition Using Image Patches

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Discriminative cue integration for medical image annotation

Pattern Recognition Letters
Decision trees for hierarchical multi-label classification

Machine Learning
Ensembles of Multi-Objective Decision Trees

ECML '07 Proceedings of the 18th European conference on Machine Learning
Analysis of time series data with predictive clustering trees

KDID'06 Proceedings of the 5th international conference on Knowledge discovery in inductive databases
Overview of the CLEF 2009 medical image annotation track

CLEF'09 Proceedings of the 10th international conference on Cross-language evaluation forum: multimedia experiments

Superpixel-Based interest points for effective bags of visual words medical image retrieval

MCBR-CDS'11 Proceedings of the Second MICCAI international conference on Medical Content-Based Retrieval for Clinical Decision Support
Evaluation of fast 2d and 3d medical image retrieval approaches based on image miniatures

MCBR-CDS'11 Proceedings of the Second MICCAI international conference on Medical Content-Based Retrieval for Clinical Decision Support
A genetic algorithm for Hierarchical Multi-Label Classification

Proceedings of the 27th Annual ACM Symposium on Applied Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we describe an approach to the automatic medical image annotation task of the 2009 CLEF cross-language image retrieval campaign (ImageCLEF). This work focuses on the process of feature extraction from radiological images and their hierarchical multi-label classification. To extract features from the images we use two different techniques: edge histogram descriptor (EHD) and Scale Invariant Feature Transform (SIFT) histogram. To annotate the images, we use predictive clustering trees (PCTs) which are able to handle target concepts that are organized in a hierarchy, i.e., perform hierarchical multi-label classification. Furthermore, we construct ensembles (Bagging and Random Forests) that use PCTs as base classifiers: this improves the predictive/ classification performance.