Back
Full-text
Journal article

Comparing fusion techniques for the ImageCLEF 2013 medical case retrieval task.

  • G Seco de Herrera A University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland. Electronic address: alba.garcia@hevs.ch.
  • Schaer R University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland. Electronic address: roger.schaer@hevs.ch.
  • Markonis D University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland. Electronic address: dimitrios.markonis@hevs.ch.
  • Müller H University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland. Electronic address: henning.mueller@hevs.ch.
Show more…
  • 2014-05-13
Published in:
  • Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society. - 2015
ImageCLEF
MedGIFT
Medical case-based retrieval
Multimodal fusion
Visual reranking
Algorithms
Artificial Intelligence
Documentation
Information Storage and Retrieval
Multimodal Imaging
Natural Language Processing
Pattern Recognition, Automated
Radiology Information Systems
Subtraction Technique
Terminology as Topic
User-Computer Interface
Vocabulary, Controlled
English Retrieval systems can supply similar cases with a proven diagnosis to a new example case under observation to help clinicians during their work. The ImageCLEFmed evaluation campaign proposes a framework where research groups can compare case-based retrieval approaches. This paper focuses on the case-based task and adds results of the compound figure separation and modality classification tasks. Several fusion approaches are compared to identify the approaches best adapted to the heterogeneous data of the task. Fusion of visual and textual features is analyzed, demonstrating that the selection of the fusion strategy can improve the best performance on the case-based retrieval task.
Language
  • English
Open access status
green
Identifiers
Persistent URL
https://folia.unifr.ch/global/documents/279207
Statistics
Document views: 8 File downloads:
  • fulltext.pdf: 0