A MICCAI 2026 benchmark for clinically meaningful AI in LI-RADS assessment of liver lesions on multi-phase CT. The challenge concluded in Strasbourg on October 1, 2026. A second challenge iteration is planned for 2027 — stay tuned for AMPLIFAI v2 and future updates.
See Challenge Results Codabench Archive Explore DatasetPost-challenge snapshot
AMPLIFAI brought together an international medical-imaging AI community around a benchmark for multi-phase CT and LI-RADS categorization. A second challenge iteration is planned for 2027; stay tuned for AMPLIFAI v2 and future updates.
1,267
Hugging Face dataset downloads
80
approved Codabench users
45
submitters with valid predictions
144
test-phase submissions
The challenge concluded with awards for the top three ranked teams and the Best Proceedings Paper.
| Rank | Team | Team Members | Institution(s) |
|---|---|---|---|
| 🥇 1st | Team Shin | Yuanye Liu | Fudan University |
| 🥈 2nd | epita | Elodie Puybareau, Guillaume Tochon, Yi Yang | EPITA |
| 🥉 3rd | Team Amplifire | Advait Madabhushi, Dharini Raghavan, Amritpal Singh, Gourav Modanwal, Anant Madabhushi | Emory University and Georgia Institute of Technology |
Best Proceedings Paper
Global participation
Approved registrations reflected a geographically broad medical-imaging AI community. Participant-city markers preserve the approximate locations mapped for the AMPLIFAI summary presentation and are shown here in a Robinson projection.
Award markers: 1 Shanghai · 2 Paris · 3 Atlanta · P Kharagpur.
Approximate city-level locations cover 63 matched approved accounts across 56 cities; 17 accounts could not be mapped confidently and are not shown. Multiple institutions in one city share a marker. Projection: Robinson.
The AMPLIFAI Challenge concluded at MICCAI 2026 in Strasbourg on Thursday, October 1, 2026. The satellite session included the challenge overview, featured talks, presentations from the top three teams, the Best Proceedings Paper talk, poster presentations, and awards.
Publication of challenge-level evaluation results remains subject to the 12-month embargo described in the Terms & Conditions.
AMPLIFAI: A Multiphase CT Dataset for Benchmarking Clinical Reasoning in LI-RADS Assessment of Liver Lesions (arXiv:2608.14778)
Public Method Overviews submitted by participating teams are available on Google Drive.
Accepted papers for the MICCAI 2026 Satellite Event Springer LNCS proceedings are listed on OpenReview.
