Save Focus

Challenge

Enter the ORena: Help push long-range video understanding to make surgery safer.
ORena SAVE FOCUS is the first challenge to test whether AI can truly comprehend full-length surgeries in order to solve crucial clinical problems that matter everywhere in the world.

Challenge results

The results of the ORena SAVE FOCUS Challenge, organized by the German Cancer Research Center (DKFZ), were presented at the ORena Workshop held during MICCAI 2026 in Luxembourg on October 1, 2026. The workshop welcomed approximately 100 attendees and featured invited speakers from academia (Stanford University) and industry (AWS and Intuitive), who discussed the clinical and technical challenges of integrating AI into the operating room, with a particular focus on long-context surgical video understanding.

200+
Challenge participants
33
Countries represented
60K
Prize pool (USD)

The challenge attracted over 200 participants from 33 countries, with the best-performing solutions outperforming state-of-the-art vision-language models, including recent Gemini and GPT models. A total prize pool of $60,000 was awarded to the winning teams across three tracks.

ORena participation World map of participants from 33 countries and top 10 country counts. Countries are shaded from 1–4 to 30+ registered accounts. Fiji Tanzania W. Sahara Canada United States of America: 27 registered accounts Kazakhstan Uzbekistan Papua New Guinea Indonesia Argentina Chile Dem. Rep. Congo Somalia Kenya Sudan Chad Haiti Dominican Rep. Russia Bahamas Falkland Is. Norway Greenland Fr. S. Antarctic Lands Timor-Leste South Africa Lesotho Mexico Uruguay Brazil Bolivia Peru Colombia Panama Costa Rica Nicaragua Honduras El Salvador Guatemala Belize Venezuela Guyana Suriname France: 13 registered accounts Ecuador Puerto Rico Jamaica Cuba Zimbabwe Botswana Namibia Senegal Mali Mauritania Benin Niger Nigeria Cameroon Togo Ghana Côte d'Ivoire Guinea Guinea-Bissau Liberia Sierra Leone Burkina Faso Central African Rep. Congo Gabon Eq. Guinea Zambia Malawi Mozambique eSwatini Angola Burundi Israel Lebanon Madagascar Palestine Gambia Tunisia Algeria Jordan United Arab Emirates: 6 registered accounts Qatar Kuwait Iraq Oman Vanuatu Cambodia Thailand Laos Myanmar Vietnam North Korea South Korea: 9 registered accounts Mongolia India: 13 registered accounts Bangladesh: 7 registered accounts Bhutan Nepal Pakistan Afghanistan Tajikistan Kyrgyzstan Turkmenistan Iran Syria Armenia Sweden Belarus Ukraine Poland Austria Hungary Moldova Romania Lithuania Latvia Estonia Germany: 24 registered accounts Bulgaria Greece Turkey Albania Croatia Switzerland Luxembourg Belgium Netherlands Portugal Spain Ireland New Caledonia Solomon Is. New Zealand Australia Sri Lanka China: 35 registered accounts Taiwan Italy Denmark United Kingdom: 30 registered accounts Iceland Azerbaijan Georgia Philippines Malaysia Brunei Slovenia Finland Slovakia Czechia Eritrea Japan: 8 registered accounts Paraguay Yemen Saudi Arabia N. Cyprus Cyprus Morocco Egypt Libya Ethiopia Djibouti Somaliland Uganda Rwanda Bosnia and Herz. Macedonia Serbia Montenegro Kosovo Trinidad and Tobago S. Sudan 30+ 20–29 10–19 5–9 1–4 TOP 10 BY REGISTERED ACCOUNTS China 35 United Kingdom 30 United States 27 Germany 24 France 13 India 13 South Korea 9 Japan 8 Bangladesh 7 UAE 6

The Medical Goal

To help prevent retained surgical items by enabling models to track, contextualize, count, and localize foreign objects, such as sponges and needles, throughout an entire surgical procedure.

The Technical Goal

To benchmark and advance long-context video understanding, spanning the full spectrum from single-frame perception to procedure-level surgical understanding.

Why It Matters

Unintentionally retaining foreign objects during minimally invasive surgery can cause serious complications requiring reoperation (Badiee et al., 2025). SAVE FOCUS addresses this patient safety challenge by benchmarking AI on tasks surgeons face intraoperatively: continuous counting and tracking of surgical items, real-time localization of unaccounted objects, and verification of complete retrieval before closure.

At the same time, the challenge targets a critical technical frontier: can vision-language models (VLMs) maintain accurate understanding across hours-long procedures when safety decisions depend on remembering what happened much earlier in the operation?

A Global Need

Lack of access to essential surgery results in 1.5 million deaths per year (Mock et al., 2015). An additional 143 million operations are needed annually, most urgently in low-resource settings where over one-third of the world's population lives without sufficient surgical workforce (Rose et al.).

Minimally invasive surgery holds promise for expanding access by reducing complications and training time. The SAVE (Surgery: Assess / Validate / Expand) program aims to double the number of surgical providers trained each year, creating an additional 100,000 within a decade. By advancing AI systems that provide scalable quality assurance for foreign object tracking and retrieval verification, SAVE FOCUS supports this mission to democratize surgical safety by creating tools that can scale to underserved regions everywhere surgical care is delivered.

The Gap

Recent progress in general-domain VLMs has enabled increasingly strong temporal reasoning over extended video streams (Bai et al., 2025). However, it is so far unclear whether these emerging capabilities translate to real clinical workflows, where critical events unfold over tens of minutes to hours. This gap is important: many clinically meaningful questions in minimally invasive surgery require persistent memory, temporal consistency, and reasoning across long time horizons. And it is particularly urgent in low-resource settings where surgical teams face higher patient volumes and fewer support personnel, thus making reliable AI assistance even more valuable.

The ORena SAVE FOCUS challenge addresses this unmet need by providing a structured benchmark that targets an urgent patient-safety problem in minimally invasive procedures: ensuring the retrieval of foreign objects, such as sponges and needles, from the abdomen at the end of the operation.

FOCUS aims to generate scientific progress by tackling two fundamental research questions:

Clinical utility: Can VLMs generate clinically meaningful and safety-relevant information about surgical foreign objects that supports quality assurance in diverse healthcare settings? 

Technical limits: What are the current limitations of VLMs in surgical scene reasoning, and how can we advance long-context understanding to meet the demands of real surgical workflows? 

By establishing a rigorous benchmark on this critical safety problem, SAVE FOCUS aims to accelerate AI capabilities that can democratize surgical assistance—making advanced quality assurance accessible not only in high-income countries, but in the regions of Asia, Africa, and Latin America where surgical workforce expansion is most urgently needed.