The UNICORN Challenge: public few-shots
Creators
- 1. Department of Pathology, Radboud University Medical Centre, Nijmegen, The Netherlands
- 2. Department of Medical Imaging, Radboud University Medical Centre, Nijmegen, The Netherlands
Description
* Shared first authors: Clément Grisi, Michelle Stegeman, Judith Lefkes, Marina D'Amato, Rianne Weber, Luc Builtjes, Lena Philipp, Fennie van der Graaf, Joeran Bosma
** Shared last authors: Alessa Hering, Francesco Ciompi
The UNICORN (Unified beNchmark for Imaging in COmputational pathology, Radiology and Natural language) challenge is an innovative benchmarking challenge that is part of the MICCAI 2025 Lighthouse Challenges. The goal of UNICORN is to address the lack of a comprehensive, public benchmark for evaluating the performance of multimodal foundation models in medical imaging. It provides a unified set of 20 tasks that span both vision and language in the fields of radiology and digital pathology.
This dataset includes publicly available few-shots cases for the challenge tasks. These examples aim to provide participants with an understanding of the data structure for each of the 20 tasks and can be used for local development.
Files
Task01_classifying_he_prostate_biopsies_into_isup_scores.zip
Files
(29.8 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:2c548bd8e38cee727d1bcf11e83c224e
|
914.6 MB | Preview Download |
|
md5:de1e9048359d4a4af0edcebaba5f9e07
|
87.9 MB | Preview Download |
|
md5:2cfa867f13d2f2d43c2207ac57c8c1a3
|
15.8 GB | Preview Download |
|
md5:c2a4c9d3359e0bc2387e3225bea79ce4
|
6.3 GB | Preview Download |
|
md5:504488aeb01dc5ee4ebac959bee61d87
|
19.4 MB | Preview Download |
|
md5:4472bfeedf54961baca28f75538cece1
|
389.4 MB | Preview Download |
|
md5:20e95c46a76a71bca5dc977594d7ff2c
|
3.5 GB | Preview Download |
|
md5:b83cb8ee5409114985a45ba0cd0ff919
|
455.7 MB | Preview Download |
|
md5:212bf0e324296bfcf0c9ef4c1fb3f641
|
52.7 MB | Preview Download |
|
md5:06f655fc278a59a2952bc7c2d0d2d7c2
|
502.9 MB | Preview Download |
|
md5:f327acce0f443f675476f24ce149125d
|
440.2 MB | Preview Download |
|
md5:132349dee2e38e770c4f95587669283b
|
4.0 kB | Preview Download |
|
md5:668f5b0422785f2bdf191d34e3a89d51
|
1.6 kB | Preview Download |
|
md5:51c0ed7f0af1817bc3385d04b9d8f28b
|
1.8 kB | Preview Download |
|
md5:b3dcb0fa08369cae35dba3f053b9569d
|
1.8 kB | Preview Download |
|
md5:38641c5662fa502dd964b867ac529ea7
|
1.3 kB | Preview Download |
|
md5:a69ec56f3831ed74bcf8fd2d12a1c6af
|
4.5 kB | Preview Download |
|
md5:8e0195f1c54a3f5479d017dac41e43b3
|
1.8 kB | Preview Download |
|
md5:90b99df99cfebf23f012926233fb33dc
|
2.4 kB | Preview Download |
|
md5:46b295917f4a34dde9e190d749f434af
|
1.4 GB | Preview Download |
Additional details
Related works
- Is documented by
- Other: 10.5281/zenodo.13981072 (DOI)
Dates
- Created
-
2025-02-07