most citedCurrent validation practice undermines surgical AI development

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2026

Towards Global AI-Driven Cervical Cancer Screening

Thuy Nuong Tran, Ömer Sümer, Evangelia Christodoulou +15

The global elimination of cervical cancer is a key public health goal set by the World Health Organization (WHO), with screening programs reducing mortality by up to 80%. However,…

cs.CV2026

A multi-center analysis of deep learning methods for video polyp detection and segmentation

Noha Ghatwary, Pedro Chavarias Solano, Mohamed Ramzy Ibrahim +24

Colonic polyps are well-recognized precursors to colorectal cancer (CRC), typically detected during colonoscopy. However, the variability in appearance, location, and size of these…

cs.CV20262 cited

Performance uncertainty in medical image analysis: a large-scale investigation of confidence intervals

Pascaline André, Pascaline André, Charles Heitz +12

Performance uncertainty quantification is essential for reliable validation and eventual clinical translation of medical imaging artificial intelligence (AI). Confidence intervals…

cs.CV20261 cited

Beyond Knowledge Silos: Task Fingerprinting for Democratization of Medical Imaging AI

Patrick Godau, Akriti Srivastava, Constantin Ulrich +3

The field of medical imaging AI is currently undergoing rapid transformations, with methodical research increasingly translated into clinical practice. Despite these successes, res…

cs.CV2025

False Promises in Medical Imaging AI? Assessing Validity of Outperformance Claims

Evangelia Christodoulou, Annika Reinke, Pascaline Andrè +23

Performance comparisons are fundamental in medical imaging Artificial Intelligence (AI) research, often driving claims of superiority based on relative improvements in common perfo…

cs.CV2025

Challenging Vision-Language Models with Surgical Data: A New Dataset and Broad Benchmarking Study

Leon Mayer, Tim Rädsch, Dominik Michael +8

While traditional computer vision models have historically struggled to generalize to endoscopic domains, the emergence of foundation models has shown promising cross-domain perfor…