Overview of the CLEF 2011 Medical Image Classification and Retrieval Tasks

The eighth edition of the ImageCLEF medical retrieval task was organized in 2011. A subset of the open access collection of PubMed Central was used as the database in 2011. This database contains 231,000 images and is substantially larger than previously used collections. Additionally, there was a larger fraction of non–clinical images such as graphs and charts. As in 2010, we had three subtasks: modality classification, image–based and case–based retrieval. A new, simple hierarchy for article figures was created. Our belief is that the use of the detected modality should help filter out non–relevant images, thereby improving precision. The goal of the image–based retrieval task was to retrieve an ordered set of images from the collection that best meet the information need specified as a textual statement and a set of sample images, while the goal of the case–based retrieval task was to return an ordered set of articles (rather than images) that best meet the information need provided as a description of a “case”. The number of registrations to the medical task increased to 55 research groups. However, groups submitting runs have remained stable at 17, with the number of submitted runs increasing to 207. Of these, 130 were image–based retrieval runs, 43 were case–based runs while the remaining 34 were modality classification runs. Combining textual and visual cues most often led to best results, but results fusion needs to be used with care.