RARE25: Recognition of Anomalies in Low-Prevalance Cancer
Challenge at MICCAI 2025, Deajeon, South-Korea, and part of EndoVis
Challenge at MICCAI 2025, Deajeon, South-Korea, and part of EndoVis
Early-stage cancers are difficult to detect in routine clinical practice. They often present with subtle or non-specific signs and are easily missed among the many normal or benign findings seen every day. Catching these cases early is crucial, as timely diagnosis can significantly improve patient outcomes (Etzioni et al., 2003). However, these cancers are rare, and their subtle features make them hard to distinguish—even for experienced clinicians. This rarity poses a major challenge when developing automated tools to support diagnosis. Most data comes from normal or non-cancerous cases, making it difficult to train models that can reliably identify the few critical anomalies without being overwhelmed by the common findings.
Given the difficulty of detecting rare and subtle early-stage cancers, there is a pressing need for well-designed tools to support clinicians. Computer-aided detection (CADe) systems hold promise—but developing and evaluating these systems in low-prevalence settings remains a major hurdle. In real-world clinical environments, early cancers are vastly outnumbered by normal or benign findings. This imbalance can skew model performance and lead to misleading results if not properly addressed during development (Godau et al., 2025). Systems trained on artificially balanced datasets may appear accurate in testing but often fail in clinical practice, where the true distribution is heavily skewed. Without rigorous benchmarking, CADe systems risk two major pitfalls: being too sensitive and generating a flood of false positives, or being too conservative and missing early cancers. Striking the right balance between sensitivity and specificity is essential. That’s why a carefully constructed benchmark is crucial—to provide a realistic, standardized way to evaluate performance under conditions that mirror the clinical reality. This challenge aims to fill that gap.
The RARE 2025 Challenge focuses on building a classification system that can accurately detect early-stage cancer in a real-world, low-prevalence setting—specifically, in patients with Barrett’s Esophagus (BE). BE is a condition where the lining of the esophagus changes, increasing the risk of developing cancer. During routine endoscopic surveillance, early signs of cancer in BE can be very subtle and are often missed. Yet catching these changes early is critical. When found in time, patients can be treated with a simple endoscopic procedure, with long-term success rates above 90% (Pech et al., 2014). But if these early signs are missed and the disease progresses, outcomes become much worse—with five-year survival rates dropping to around 15% (American Cancer Society, 2025). Despite these high stakes, the prevalence of early neoplasia during surveillance of BE patients is exceptionally low—typically below 1% (Hvid-Jensen et al., 2011). This makes it especially difficult to gather enough data for model training and evaluation, and increases the risk of systems being either too cautious or too aggressive. This challenge is designed to address exactly that. Participants are asked to develop models that can detect these rare but vital cases—without overwhelming clinicians with false alarms. Success in this task means building systems that are not just accurate in theory, but practical and trustworthy in the clinic.
All the participating teams will be invited to contribute to the research paper and be listed as authors on the forthcoming journal publication summarizing the outcomes of our challenge.
Additionally, the top 5 teams will receive the following prizes:
🥇 1st place: €tba
🥈 2nd place: €tba
🥉 3rd place: €tba
🏅 4th place: €tba
🏅 5th place: €tba
Interested in participating? Or just curious about the progress of our challenge? Enter your email address below to receive the latest updates about the RARE 2025 Challenge directly in your mailbox.