Skip to Main content Skip to Navigation
Conference papers

VisMed: A Visual Vocabulary Approach for Medical Image Indexing and Retrieval

Abstract : Voluminous medical images are generated daily. They are critical assets for medical diagnosis, research, and teaching. To facilitate automatic indexing and retrieval of large medical image databases, we propose a structured framework for designing and learning vocabularies of meaningful medical terms associated with visual appearance from image samples. These VisMed terms span a new feature space to represent medical image contents. After a multi-scale detection process, a medical image is indexed as compact spatial distributions of VisMed terms. A flexible tiling (FlexiTile) matching scheme is proposed to compare the similarity between two medical images of arbitrary aspect ratios.
Document type :
Conference papers
Complete list of metadata

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/hal-00953909
Contributor : Marie-Christine Fauvet <>
Submitted on : Friday, February 28, 2014 - 4:05:50 PM
Last modification on : Tuesday, December 8, 2020 - 10:42:35 AM
Long-term archiving on: : Wednesday, May 28, 2014 - 5:00:17 PM

File

chevallet05e_AIRS05.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00953909, version 1

Citation

Joo-Hwee Lim, Jean-Pierre Chevallet. VisMed: A Visual Vocabulary Approach for Medical Image Indexing and Retrieval. Asia Information Retrieval Symposium AIRS2005, Information Retrieval Technology, LNCS 3689, 2005, Jeju Island, Korea, pp.84--96. ⟨hal-00953909⟩

Share

Metrics

Record views

417

Files downloads

440