You are here

Medical Image Classification and Retrieval 2012

Primary tabs

News

  • 04.08.2012 Results for the image-based and case-base retrieval task are released.
  • 13.07.2012 Results for the modality classification task are released.
  • 17.04.2012 Training data for the modality classification task is released.
  • 20.03.2012 Data for the medical task is released.
  • 15.2.2012 Registration of ImageCLEF 2012 is open.
  • 1.12.2011 ImageCLEF is accepted as CLEF 2012 lab.

Schedule:

  • 15.2.2012: registration opens for all ImageCLEF tasks
  • 15.3.2012: data release
  • 17.4.2012: training data release for the modality classification task
  • 10.5.2012: topic release for the retrieval tasks
  • 15.6.2012: submission of runs
  • 15.7.2012: release of results
  • 17.8.2012: submission of working notes papers
  • 17.09.2012-20.09.2012: CLEF 2012 Conference, Rome, Italy

Citations

  • When referring to ImageCLEFmed 2012 task general goals, general results, etc. please cite the following publication:
    • Henning Müller, Alba García Seco de Herrera, Jayashree Kalpathy-Cramer, Dina Demner-Fushman, Sameer Antani and Ivan Eggel, Overview of the ImageCLEF 2012 medical image retrieval and classification tasks, in: CLEF 2012 working notes, 2012
    • BibText:

      @InProceedings{MGK2012,
        Title = {Overview of the {ImageCLEF} 2012 Medical Image Retrieval and Classification Tasks},
        Author = {M\"uller, Henning and Garc\'ia Seco de Herrera, Alba and Kalpathy--Cramer, Jayashree and Demner Fushman, Dina and Antani, Sameer and Eggel, Ivan},
        Booktitle = {Working Notes of {CLEF} 2012 (Cross Language Evaluation Forum)},
        Year = {2012},
        Month = {September},
        Location = {Rome, Italy}

      }

  • When referring to ImageCLEFmed task in general, please cite the following publication:
    • Jayashree Kalpathy-Cramer, Alba García Seco de Herrera, Dina Demner-Fushman, Sameer Antani, Steven Bedrick and Henning Müller, Evaluating Performance of Biomedical Image Retrieval Systems –an Overview of the Medical Image Retrieval task at ImageCLEF 2004-2014 (2014), in: Computerized Medical Imaging and Graphics
    • BibText:

      @Article{KGD2014,
        Title = {Evaluating Performance of Biomedical Image Retrieval Systems-- an Overview of the Medical Image Retrieval task at {ImageCLEF} 2004--2014},
        Author = {Kalpathy--Cramer, Jayashree and Garc\'ia Seco de Herrera, Alba and Demner--Fushman, Dina and Antani, Sameer and Bedrick, Steven and M\"uller, Henning},
        Journal = {Computerized Medical Imaging and Graphics},
        Year = {2014}

      }

Tasks overview

The medical retrieval task of ImageCLEF 2012 uses a subset of PubMed Central containing 305,000 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 2012:

  • 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.
  • Ad-hoc image-based retrieval :
    This is the classic medical retrieval task, similar to those in organized in 2005-2011. 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.

Modality classification

The following hierarchy will be used for the modality classification, different form the classes in ImageCLEF 2011.

Class codes with descriptions (class codes need to be specified in run files):
([Class code] Description)

  • [COMP] Compound or multipane images (1 category)
  • [Dxxx] Diagnostic images:
    • [DRxx] Radiology (7 categories):
      • [DRUS] Ultrasound
      • [DRMR] Magnetic Resonance
      • [DRCT] Computerized Tomography
      • [DRXR] X-Ray, 2D Radiography
      • [DRAN] Angiography
      • [DRPE] PET
      • [DRCO] Combined modalities in one image
    • [DVxx] Visible light photography (3 categories):
      • [DVDM] Dermatology, skin
      • [DVEN] Endoscopy
      • [DVOR] Other organs
    • [DSxx] Printed signals, waves (3 categories):
      • [DSEE] Electroencephalography
      • [DSEC] Electrocardiography
      • [DSEM] Electromyography
    • [DMxx] Microscopy (4 categories):
      • [DMLI] Light microscopy
      • [DMEL] Electron microscopy
      • [DMTR] Transmission microscopy
      • [DMFL] Fluorescence microscopy
    • [D3DR] 3D reconstructions (1 category)
  • [Gxxx] Generic biomedical illustrations (12 categories):
    • [GTAB] Tables and forms
    • [GPLI] Program listing
    • [GFIG] Statistical figures, graphs, charts
    • [GSCR] Screenshots
    • [GFLO] Flowcharts
    • [GSYS] System overviews
    • [GGEN] Gene sequence
    • [GGEL] Chromatography, Gel
    • [GCHE] Chemical structure
    • [GMAT] Mathematics, formulae
    • [GNCP] Non-clinical photos
    • [GHDR] Hand-drawn sketches

Data Download

Our database distribution includes an XML file and a compressed file containing the over 300,000 images of 75'000 articles of the biomedical open access literature.
The login/password for accessing the data is not your login/password for the registration system. In the registration system under collections, details, you can find all information on accessing the data.

Topics

We will provide 22 ad-hoc topics, divided into visual, mixed and semantic topic types.
We will also provide 26 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.
  • 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.
  • 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 DRUS 0.9
1471-2091-8-29-7 GTAB 1
1471-2105-10-276-8 DMLI 0.4
1471-2105-10-379-3 D3DR 0.8
1471-2105-10-S1-S60-3 COMP 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.

Please note that each group is allowed a maximum of 10 runs.

Results

Modality classification

Runs Group name Run type Correctly classified in %
Mixed
medgift-nb-mixed-reci-14-mc.txt medGIFT Automatic 66,2
medgift-orig-mixed-reci-7-mc.txt medGIFT Automatic 64,6
medgift-nb-mixed-reci-7-mc.txt medGIFT Automatic 63,6
Visual_Text_Hierarchy_w_Postprocessing_4_Illustration.txt ITI Automatic 63,2
Visual_Text_Flat_w_Postprocessing_4_Illustration.txt ITI Automatic 61,7
Visual_Text_Hierarchy.txt ITI Automatic 60,1
Visual_Text_Flat.txt ITI Automatic 59,1
medgift-b-mixed-reci-7-mc.txt medGIFT Automatic 58,8
Image_Text_Hierarchy_Entire_set.txt ITI Automatic 44,2
IPL_MODALITY_SVM_LSA_BHIST_324segs_50k_WithTextV.txt IPL Automatic 23,8
Textual
Text_only_Hierarchy.txt ITI Automatic 41,3
Text_only_Flat.txt ITI Automatic 39,4
Visual
preds_Mic_Combo100Early_MAX_extended100.txt IBM Multimedia Analytics Automatic 69,7
LL_fusion_nfea_20_rescale.txt IBM Multimedia Analytics Automatic 61,8
preds_Mic_comboEarly_regular.txt IBM Multimedia Analytics Automatic 57,9
UESTC-MKL3.txt UESTC Automatic 57,9
UESTC-MKL2.txt UESTC Automatic 56,7
UESTC-MKL5.txt UESTC Automatic 56,0
UESTC-MKL6.txt UESTC Automatic 56,0
UESTC-SIFT.txt UESTC Automatic 52,8
NCFC_ORIG_2_EXTERNAL_SUBMIT.txt IBM Multimedia Analytics Automatic 52,7
Visual_only_Hierarchy.txt ITI Automatic 51,6
Visual_only_Flat.txt ITI Automatic 50,3
gist84_01_ETFBL.txt ETFBL Automatic 48,6
gist84_02_ETFBL.txt ETFBL Automatic 48,0
LL_2_EXTERNAL.txt IBM Multimedia Analytics Automatic 46,5
medgift-nb-visual-mnz-14-mc.txt medGIFT Automatic 42,2
medgift-nb-visual-mnz-7-mc.txt medGIFT Automatic 41,8
modality_visualonly.txt GEIAL Automatic 39,5
medgift-orig-visual-mnz-7-mc.txt medGIFT Automatic 38,1
medgift-b-visual-mnz-7-mc.txt medGIFT Automatic 34,2
NCFC_500_2_EXTERNAL_SUBMIT.txt IBM Multimedia Analytics Automatic 33,4
preds_Mic_comboLate_MAX_regular.txt IBM Multimedia Analytics Automatic 27,5
IPL_AllFigs_MODALITY_SVM_LSA_BHIST_324segs_50k.txt IPL Automatic 26,6
IPL_MODALITY_SVM_LSA_BHIST_324segs_50k.txt IPL Automatic 26,4
preds_Mic_comboLate_MAX_extended100.txt IBM Multimedia Analytics Feedback or/and human assistance 22,1
UNED_UV_04_CLASS_IMG_ADAPTATIVEADJUST.txt UNED Automatic 15,7
UNED_UV_03_CLASS_IMG_ADJUST2MINRELEVANTS.txt UNED Automatic 13,4
UNED_UV_02_CLASS_IMG_ADJUST2AVGRELEVANTS.txt UNED Automatic 13,1
UNED_UV_01_CLASS_IMG_NOTADJUST.txt UNED Automatic 11,9
baseline-sift-k11-mc.txt medGIFT Automatic 11,1
testimagelabelres.txt GEIAL Automatic 10,1
ModalityClassificaiotnSubmit.txt BUAA AUDR Manual 3,0

Ad-hoc image-based retrieval

Runid Run type MAP GM-MAP bpref P10 P30
nlm-se Mixed 0.2377 0.0665 0.2542 0.3682 0.2712
Merge_RankToScore_weighted Mixed 0.2166 0.0616 0.2198 0.3682 0.2409
mixedsum(CEDD,FCTH,CLD)+1.7TFIDFmax2012 Mixed 0.2111 0.0645 0.2241 0.3636 0.2242
mixedFCTH+1.7TFIDFsum2012 Mixed 0.2085 0.0621 0.2204 0.3545 0.2152
medgift-ef-mixed-mnz-ib Mixed 0.2005 0.0917 0.1947 0.3091 0.2
mixedCEDD+1.7TFIDFsum2012 Mixed 0.1954 0.0566 0.2096 0.3455 0.2182
nlm-lc Mixed 0.1941 0.0584 0.1871 0.2727 0.197
nlm-lc-cw-mf Mixed 0.1938 0.0413 0.1924 0.2636 0.2061
nlm-lc-scw-mf Mixed 0.1927 0.0395 0.194 0.2636 0.203
nlm-se-scw-mf Mixed 0.1914 0.0206 0.2062 0.2864 0.2076
Txt_Img_Wighted_Merge Mixed 0.1846 0.0538 0.2039 0.3091 0.2621
mixedsum(CEDD,FCTH,CLD)+TFIDFmax2012 Mixed 0.1817 0.0574 0.1997 0.3409 0.2121
mixedFCTH+TFIDFsum2012 Mixed 0.1816 0.0527 0.1912 0.3409 0.2076
finki/td> Mixed 0.1794 0.049 0.1851 0.3 0.1894
finki Mixed 0.1784 0.0487 0.1825 0.2955 0.1864
nlm-se-cw-mf Mixed 0.1774 0.0141 0.1868 0.2909 0.2091
mixedCEDD+textsum2012 Mixed 0.1682 0.0478 0.1825 0.3136 0.2061
FOmixedsum(CEDD,FCTH,CLD)+1.7TFIDFmax2012 Mixed 0.1637 0.0349 0.1705 0.2773 0.1758
RFBr24+91qMixedsum(CEDD,FCTH,CLD)+1.7TFIDFmax2012 Mixed 0.1589 0.0424 0.1773 0.3136 0.1985
medgift-ef-mixed-reci-ib Mixed 0.1167 0.0383 0.1238 0.1864 0.1485
UNED_UV_04_TXTIMG_AUTO_LOWLEVEL_FEATURES_TWOVECTORS.txt Mixed 0.004 0.0001 0.0104 0.0409 0.0258
UNED_UV_05_IMG_EXPANDED_FEATURES_UNIQUEVECTOR.txt Mixed 0.0036 0.0001 0.0111 0.0455 0.0303
UNED_UV_02_IMG_AUTO_LOWLEVEL_FEATURES.txt Mixed 0.0034 0.0001 0.0114 0.0455 0.0273
UNED_UV_08_IMG_AUTO_CONCEPTUAL_FEATURES.txt Mixed 0.0033 0.0001 0.0104 0.0227 0.0197
IPL_AUEB_SVM_CLASS_LSA_BlockHist324Seg_50k Mixed 0.0032 0.0002 0.0103 0.0409 0.0303
IPL_AUEB_SVM_CLASS_TEXT_LSA_BlockHist324Seg_50k Mixed 0.0025 0.0001 0.0095 0.0318 0.0258
IPL_AUEB_CLASS_LSA_BlockColorLayout64Seg_50k Mixed 0.0023 0.0002 0.0095 0.0318 0.0227
UNED_UV_09_TXTIMG_AUTO_CONCEPTUAL_FEATURES.txt Mixed 0.0021 0.0001 0.005 0.0091 0.0061
IPL_AUEB_CLASS_LSA_BlockColorLayout64Seg_20k Mixed 0.0019 0.0001 0.0066 0.0227 0.0197
UNED_UV_03_TXTIMG_AUTO_LOWLEVEL_FEATURES.txt Mixed 0.0015 0.0001 0.0037 0.0045 0.0061
UNED_UV_07_TXTIMG_AUTO_EXPANDED_FEATURES_UNIQUEVECTOR.txt Mixed 0.0015 0.0001 0.0036 0.0045 0.0061
UNED_UV_06_TXTIMG_AUTO_EXPANDED_FEATURES_TWOVECTORS.txt Mixed 0.0013 0.0001 0.0034 0.0091 0.0045
UNAL Textual 0.2182 0.082 0.2173 0.3409 0.2045
AUDR_TFIDF_CAPTION[QE2]_AND_ARTICLE Textual 0.2081 0.0776 0.2134 0.3091 0.2045
AUDR_TFIDF_CAPTION[QE2]_AND_ARTICLE Textual 0.2016 0.0601 0.2049 0.3045 0.1939
IPL_A1T113C335M1 Textual 0.2001 0.0752 0.1944 0.2955 0.2091
IPL_A10T10C60M2 Textual 0.1999 0.0714 0.1954 0.3136 0.2076
TF_IDF Textual 0.1905 0.0531 0.1822 0.3318 0.2152
AUDR_TFIDF_CAPTION_AND_ARTICLE Textual 0.1891 0.0508 0.1975 0.3318 0.1939
IPL_T10C60M2 Textual 0.188 0.0694 0.1957 0.3364 0.2076
AUDR_TFIDF_CAPTION[QE2] Textual 0.1877 0.0519 0.1997 0.3 0.2045
TF_IDF Textual 0.1865 0.0502 0.1981 0.25 0.1515
Laberinto_MSH_PESO_2 Textual 0.1859 0.0537 0.1939 0.3318 0.1894
IPL_TCM Textual 0.1853 0.0755 0.1832 0.3091 0.2152
IPL_T113C335M1 Textual 0.1836 0.0706 0.1868 0.3318 0.2061
UNAL Textual 0.1832 0.0464 0.1822 0.2955 0.1939
TF_IDF Textual 0.1819 0.0679 0.1921 0.2864 0.1909
TF_IDF Textual 0.1814 0.0693 0.1829 0.2864 0.1894
UESTC-ad-tc Textual 0.1769 0.0614 0.1584 0.3 0.1621
finki Textual 0.1763 0.0498 0.1773 0.2909 0.1864
Laberinto_MSH_PESO_1 Textual 0.1707 0.0512 0.1712 0.3318 0.1894
finki Textual 0.1704 0.0472 0.1701 0.3091 0.1833
Laberinto_MMTx_MSH_PESO_2 Textual 0.168 0.0555 0.1711 0.3227 0.1909
Terrier_CapTitAbs_BM25b0.75 Textual 0.1678 0.0661 0.1782 0.2818 0.1712
Laberinto_MMTx_MSH_PESO_1 Textual 0.1677 0.0554 0.1701 0.3182 0.1879
AUDR_TFIDF_CAPTION[QE2] Textual 0.1673 0.037 0.1696 0.2955 0.1894
Laberinto_BL Textual 0.1658 0.0477 0.1667 0.3 0.1939
AUDR_TFIDF_CAPTION Textual 0.1651 0.0467 0.1743 0.3 0.2076
AUDR_TFIDF_CAPTION Textual 0.1648 0.0441 0.1717 0.3318 0.1909
finki Textual 0.1638 0.0444 0.1644 0.3 0.1818
finki Textual 0.1638 0.0444 0.1644 0.3 0.1818
IPL_ATCM Textual 0.1616 0.0615 0.1576 0.2773 0.1742
Laberinto_BL_MSH Textual 0.1613 0.0462 0.1812 0.2682 0.1864
LIG_MRIM_IB_TFIDF_W_avdl_DintQ Textual 0.1586 0.0465 0.1596 0.3455 0.2136
HES-SO-VS_CAPTIONS_LUCENE Textual 0.1562 0.0424 0.167 0.3273 0.1864
TF_IDF Textual 0.1447 0.0313 0.1445 0.2864 0.1742
UESTC-ad-c Textual 0.1443 0.0352 0.1446 0.2409 0.1485
UESTC-ad-tcm Textual 0.1434 0.051 0.1397 0.2182 0.153
LIG_MRIM_IB_FUSION_TFIDF_W_TB_C_avdl_DintQ Textual 0.1432 0.0462 0.1412 0.2682 0.1955
LIG_MRIM_IB_FUSION_JM01_W_TB_C Textual 0.1425 0.0476 0.1526 0.2636 0.1924
HES-SO-VS_FULLTEXT_LUCENE Textual 0.1397 0.0436 0.1565 0.2227 0.1379
LIG_MRIM_IB_TB_PIVv2_C Textual 0.1383 0.0405 0.1463 0.2864 0.1803
TF_IDF Textual 0.1372 0.0466 0.1683 0.3 0.1818
Laberinto_MMTx_MSH Textual 0.1361 0.0438 0.157 0.2091 0.1758
LIG_MRIM_IB_TFIDF_C_avdl_DintQ Textual 0.1345 0.0402 0.1304 0.2545 0.1682
LIG_MRIM_IB_TB_JM01_C Textual 0.1342 0.0396 0.142 0.2818 0.1652
LIG_MRIM_IB_TB_BM25_C Textual 0.1165 0.036 0.1276 0.2 0.1515
LIG_MRIM_IB_TB_TFIDF_C_avdl Textual 0.1081 0.0332 0.1052 0.1818 0.1167
UESTC-ad-cm Textual 0.106 0.0206 0.1154 0.2091 0.1379
UESTC_ad_tcm_mc Textual 0.101 0.0132 0.1223 0.2 0.1333
LIG_MRIM_IB_TB_DIR_C Textual 0.0993 0.0281 0.1046 0.1864 0.1379
AUDR_TFIDF_CAPTION_AND_ARTICLE Textual 0.0959 0.0164 0.1075 0.1636 0.1152
LIG_MRIM_IB_TB_TFIDF_C Textual 0.09 0.026 0.0889 0.1409 0.1136
UESTC-ad-cm-mc Textual 0.0653 0.0078 0.0846 0.1727 0.103
UNED_UV_01_TXT_AUTO_EN Textual 0.0039 0.0001 0.0055 0.0091 0.0076
UNAL Textual 0.0024 0.0001 0.0113 0.0091 0.0045
RFBr23+91qsum(CEDD,FCTH,CLD)max2012 Visual 0,0101 0,0004 0,0193 0,0591 0,0439
IntgeretedCombsum(CEDD,FCTH,CLD)max Visual 0,0092 0,0005 0,019 0,05 0,0424
unal Visual 0,0073 0,0003 0,0134 0,0636 0,05
FOmixedsum(CEDD,FCTH,CLD)max2012 Visual 0,0066 0,0003 0,0141 0,0318 0,0288
edCEDD&FCTH&CLDmax2012 Visual 0,0064 0,0003 0,0154 0,0409 0,0318
medgift-lf-boc-bovw-mnz-ib Visual 0,0049 0,0003 0,0138 0,0364 0,0364
Combined_LateFusion_Fileterd_Merge Visual 0,0046 0,0003 0,0107 0,0318 0,0379
FilterOutEDFCTHsum2012 Visual 0,0042 0,0004 0,0109 0,0409 0,0364
finki Visual 0,0041 0,0003 0,0105 0,0318 0,0364
EDCEDDSUMmed2012 Visual 0,004 0,0003 0,0091 0,0364 0,0409
medgift-lf-boc-bovw-reci-ib Visual 0,004 0,0002 0,0103 0,0227 0,0318
edFCTHsum2012 Visual 0,0034 0,0003 0,01 0,0318 0,0318
medgift-ef-boc-bovw-mnz-ib Visual 0,0033 0,0003 0,0133 0,0364 0,0333
UNAL Visual 0,0033 0,0003 0,011 0,0455 0,0364
EDCEDD&FCTHmax2012 Visual 0,0032 0,0003 0,0111 0,0227 0,0303
medgift-ef-boc-bovw-reci-ib Visual 0,003 0,0001 0,01 0,0273 0,0227
IntgeretedCombsum(CEDD,FCTH)max Visual 0,0027 0,0003 0,0099 0,0045 0,0212
edMPEG7CLDsum2012 Visual 0,0026 0,0002 0,0058 0,0318 0,0242
UNAL Visual 0,0024 0,0001 0,0113 0,0091 0,0045
medgift-lf-boc-bovw-mnz-ib Visual 0,0022 0,0001 0,0062 0,0227 0,0318
IPL_AUEB_DataFusion_LSA_SC_CL_CSH_64seg_20k Visual 0,0021 0,0001 0,0049 0,0273 0,0242
IPL_AUEB_DataFusion_EH_LSA_SC_CL_CSH_64seg_100k Visual 0,0018 0,0001 0,0053 0,0364 0,0258
IPL_AUEB_DataFusion_EH_LSA_SC_CL_CSH_64seg_20k Visual 0,0017 0,0001 0,0053 0,0227 0,0273
IPL_AUEB_DataFusion_LSA_SC_CL_CSH_64seg_100k Visual 0,0017 0,0002 0,0046 0,0364 0,0212
baseline-sift-early-fusion-ib Visual 0,0017 0 0,0058 0,0227 0,0318
baseline-sift-late-fusion Visual 0,0016 0 0,0048 0,0273 0,0318
IPL_AUEB_DataFusion_EH_LSA_SC_CL_CSH_64seg_50k Visual 0,0011 0,0001 0,004 0,0136 0,0136
IPL_AUEB_DataFusion_LSA_SC_CL_CSH_64seg_50k Visual 0,0011 0,0001 0,0039 0,0091 0,0121
Combined_Selected_Fileterd_Merge Visual 0,0009 0 0,0028 0,0227 0,0258
reg_cityblock Visual 0,0007 0 0,0024 0,0227 0,0197
reg_diffusion Visual 0,0007 0 0,0023 0,0182 0,0182
tfidf_of_pca_euclidean Visual 0,0005 0 0,0011 0,0136 0,0136
tfidf_of_pca_cosine Visual 0,0005 0 0,0013 0,0091 0,0167
tfidf_of_pca_correlation Visual 0,0005 0 0,0011 0,0136 0,0167
itml_cityblock Visual 0,0001 0 0,0014 0,0045 0,003
itml_diffusion Visual 0,0001 0 0,0015 0,0045 0,003

Case-based retrieval

Runid Run type MAP GM-MAP bpref P10 P30
medgift-ef-mixed-mnz-cb Mixed 0,1017 0,0175 0,0857 0,1115 0,0679
medgift-ef-mixed-reci-cb Mixed 0,0514 0,009 0,0395 0,0654 0,0564
HES-SO-VS_FULLTEXT_LUCENE Textual 0,169 0,0374 0,1499 0,1885 0,109
LIG_MRIM_CB_FUSION_DIR_W_TA_TB_C Textual 0,1508 0,0322 0,1279 0,1538 0,1167
LIG_MRIM_CB_FUSION_JM07_W_TA_TB_C Textual 0,1384 0,0288 0,11 0,1615 0,1141
UESTC_case_f Textual 0,1288 0,025 0,1092 0,1231 0,0821
UESTC-case-fm Textual 0,1269 0,0257 0,1117 0,1231 0,0821
LIG_MRIM_CB_TFIDF_W_DintQ Textual 0,1036 0,0167 0,077 0,0846 0,0705
nlm-lc-total-sum Textual 0,1035 0,0137 0,1053 0,1 0,0628
nlm-lc-total-max Textual 0,1027 0,0125 0,1055 0,0923 0,0538
nlm-se-sum Textual 0,0929 0,013 0,0738 0,0769 0,0667
nlm-se-max Textual 0,0914 0,0128 0,0736 0,0769 0,0667
nlm-lc-sum Textual 0,0909 0,0133 0,0933 0,1231 0,0654
LIG_MRIM_CB_TA_TB_JM07_C Textual 0,0908 0,0156 0,0799 0,1308 0,0744
LIG_MRIM_CB_TA_TB_BM25_C Textual 0,0895 0,0143 0,0864 0,1231 0,0654
LIG_MRIM_CB_TA_TB_DIR_C Textual 0,0893 0,0137 0,0804 0,1192 0,0692
LIG_MRIM_CB_TA_TB_PIVv2_C Textual 0,0865 0,0158 0,0727 0,1192 0,0795
nlm-lc-max Textual 0,084 0,0109 0,0886 0,0923 0,0603
LIG_MRIM_CB_TA_TFIDF_C_DintQ Textual 0,0789 0,014 0,0672 0,0923 0,0692
nlm-se-frames-sum Textual 0,0771 0,0052 0,0693 0,0692 0,0526
HES-SO-VS_CAPTIONS_LUCENE Textual 0,0696 0,0028 0,0762 0,0962 0,0615
LIG_MRIM_CB_TA_TB_TFIDF_C_avdl Textual 0,0692 0,0127 0,0688 0,0769 0,0692
nlm-se-frames-max Textual 0,0672 0,0031 0,0574 0,0538 0,05
LIG_MRIM_CB_TA_TB_TFIDF_C Textual 0,0646 0,0114 0,0624 0,0692 0,0641
ibm-case-based Textual 0,0484 0,0023 0,0439 0,0577 0,0449
R1_MIRACL Textual 0,0421 0,005 0,026 0,0538 0,0462
R4_MIRACL Textual 0,0196 0,0008 0,0165 0,0308 0,0282
R3_MIRACL Textual 0,012 0,0004 0,0087 0,0192 0,0218
R6_MIRACL Textual 0,0111 0,0004 0,0074 0,0192 0,0128
R5_MIRACL Textual 0,0024 0 0,0022 0,0038 0,0013
R2_MIRACL Textual 0 0 0,0002 0 0
medgift-lf-boc-bovw-reci-IMAGES-cb Visual 0,0366 0,0014 0,0347 0,0269 0,0141
medgift-lf-boc-bovw-mnz-IMAGES-cb Visual 0,0302 0,001 0,0293 0,0231 0,009
baseline-sift-early-fusion-cb Visual 0,0016 0 0,0032 0,0038 0,0013
baseline_sift_late_fusion_cb Visual 0,0008 0 0 0,0038 0,0013
medgift-ef-boc-bovw-reci-IMAGES-cb Visual 0,0008 0,0001 0,0007 0 0,0013
medgift-ef-boc-bovw-mnz-IMAGES-cb Visual 0,0007 0 0 0 0,0013

Organizers

  • Henning Müller, HES-SO, Switzerland
  • Jayashree Kalpathy-Cramer, Harvard University, USA
  • Dina Demner-Fushman, National Library of Medicine, USA
  • Sameer Antani, National Library of Medicine, USA
  • Alba García Seco de Herrera, HES-SO, Switzerland