Medical Image Retrieval Task 2011

News

• 29.7.2011 Results for the case-based retrieval task are released
• 28.7.2011 Results for the image-based retrieval task are released
• 26.7.2011 Results for the modality classification task are released
• 15.4.2011 Topics for the medical retrieval tasks are released.
• 10.4.2011 Training data released for the modality annotation task.
• 17.3.2011 Data release for the Medical Image Retrieval task 2011.
• 8.4.2011 Release of the training data for the modality classification task.

The medical retrieval task of ImageCLEF 2011 uses a subset of PubMed Central containing 231,000 images.
This task is a use case of the Promise network of excellence and supported by the project.

There will be three types of tasks in 2011:

• Modality Classification:
  Previous studies have shown that imaging modality is an important aspect of the image for medical retrieval. In user-studies, clinicians have indicated that modality is one of the most important filters that they would like to be able to limit their search by. Many image retrieval websites (Goldminer, Yottalook) allow users to limit the search results to a particular modality. However, this modality is typically extracted from the caption and is often not correct or present. Studies have shown that the modality can be extracted from the image itself using visual features. Additionally, using the modality classification, the search results can be improved significantly. In difference to 2010 in 2011 the images will come from a larger variety of journals and the captions will not be of the same quality. The number of classes is foreseen to change adding more non-imaging-modality classes such as photograph, graphics, flow chart, etc.
  The measure used for this sub-task will be classification accuracy. The results of the modality classification can be used to filter the search in the next sub-task
  Note: participants who submit at least one run will be provided the results of the classification on this data set
  

  Class codes with descriptions (Class codes need to be specified in run files):
  [Class code : description]
  3D : 3d reconstruction
  AN : angiography
  CM : compound figure (more than one type of image)
  CT : computed tomography
  DM : dermatology
  DR : drawing
  EM : electronMicroscopy
  EN : endoscopic imaging
  FL : fluoresence
  GL : gel
  GX : graphs
  GR : gross pathology
  HX : histopathology
  MR : magnetic resonance imaging
  PX : general photo
  RN : retinography
  US : ultrasound
  XR : x-ray

• Ad-hoc image-based retrieval :
  This is the classic medical retrieval task, similar to those in organized in 2005-2010. Participants will be given a set of 30 textual queries with 2-3 sample images for each query. The queries will be classified into textual, mixed and semantic, based on the methods that are expected to yield the best results.
• Case-based retrieval:
  This task was first introduced in 2009. This is a more complex task, but one that we believe is closer to the clinical workflow. In this task, a case description, with patient demographics, limited symptoms and test results including imaging studies, is provided (but not the final diagnosis). The goal is to retrieve cases including images that might best suit the provided case description. Unlike the ad-hoc task, the unit of retrieval here is a case, not an image. For the purposes of this task, a "case" is a PubMed ID corresponding to the journal article. In the results submissions the article DOI should be used as several articles do not have PubMed IDs nor Article URLs.

Schedule:

• 1.2.2010: registration opens for all ImageCLEF tasks, and the copyright agreement is ready
• 17.3.2011: data release
• 8.4.2011: topic release for the modality classification task
• 15.4.2011: topic release for the retrieval tasks
• 9.6.2011: submission of runs
• 26.-31.7.2011: release of results
• 14.8.2011: submission of working notes papers
• 20.09.2011-23.09.2011: CLEF 2011 Conference, Amsterdam, The Netherlands

Data Download

Our database distribution includes an XML file with the image id, the captions of the images, the titles of the journal articles in which the image had appeared and the PubMed ID of the journal article. In addition, a compressed file containing the over 77,000 images will be provided.

Topics

We will provide 15 ad-hoc topics, divided into visual, mixed and semantic topic types.
We will also provide 15 case-based topics, where the retrieval unit is a case, not an image.

Data Submission

Image-based and case-based retrieval

Please ensure that your submissions are compliant with the trec_eval format prior to submission.
We will reject any runs that do not meet the required format.
Also, please note that each group is allowed a maximum of 10 runs for image-based and case-based topics each. The qrels will be distributed among the participants, so further runs can be evaluated for the working notes papers by the participants.
Do not hesitate to ask if you have questions regarding the trec_eval format.

At the time of submission, the following information about each run will be requested. Please let us know if you would like clarifications on how to classify your runs.

1. What was used for the retrieval: Image, text or mixed (both)
2. Was other training data used?
3. Run type: Automatic, Manual, Interactive
4. Query Language

trec_eval format

The format for submitting results is based on the trec_eval program (http://trec.nist.gov/trec_eval/) as follows:

1 1 27431 1 0.567162 OHSU_text_1
1 1 27982 2 0.441542 OHSU_text_1
.............
1 1 52112 1000 0.045022 OHSU_text_1
2 1 43458 1 0.9475 OHSU_text_1
.............
25 1 28937 995 0.01492 OHSU_text_1

where:

• The first column contains the topic number, in our case from 1-30 (or 31-40 for the case-based topics)
• The second column is always 1
• The third column is the image identifier (IRI) without the extension jpg and without any image path (or the full article DOI for the case-based topics)
• The fourth column is the ranking for the topic (1-1000)
• The fifth column is the score assigned by the system
• The sixth column is the identifier for the run and should be the same in the entire file

Several key points for submitted runs are:

• The topic numbers should be consecutive and complete from 1-30 (or 31-40 for the case based topics)
• Case-based and image-based topics have to be submitted in separate files
• The score should be in decreasing order (i.e. the image at the top of the list should have a higher score than images at the bottom of the list)
• Up to (but not necessarily) 1000 images can be submitted for each topic.
• Each topic must have at least one image.
• Each run must be submitted in a single file. Files should be pure text files and not be zipped or otherwise compressed.

Modality classification

The format of the result submission for the modality classification subtask should be the following:

1471-2091-8-12-2 3D 0.9
1471-2091-8-29-7 GX 1
1471-2105-10-276-8 3D 0.4
1471-2105-10-379-3 GR 0.8
1471-2105-10-S1-S60-3 HX 0.9
...

where:

• The first column contains the Image-ID (IRI). This ID does not contain the file format ending and it should not represent a file path
• The second column is the classcode
• The third column represents the normalized score (between 0 and 1) that your system assigned to that specific result

You should also respect the following constraints

• Each specified image must be part of the collection (dataset)
• An Image cannot be contained more than once
• At least all images of the testset must be contained in runfile, however it would be nice to have the whole dataset classified
• Only known classcodes are accepted

Results

Modality classification

Ad-hoc image-based retrieval

Case-based retrieval

The results shown in this table are the official results calculate using 9 topics as initially the judgements of one topic were forgotten. The correct qrels files with all ten topics are available to participants for further analysis. The ranking remains basically the same with two ranks swapping in the top 10 ranks and a few more in lower ranks.

Contact

Please contact Jayashree Kalpathy-Cramer or Henning Müller for any questions about this task.