Medicine and Health

Impact of data on generalization of AI for surgical intelligence applications

O. Bar, D. Neimark, et al.

This study explores how data volume influences AI's ability to generalize in surgical applications. Researchers developed a deep learning system using a diverse cholecystectomy video dataset, achieving impressive accuracy and demonstrating robustness across different medical settings. This work emphasizes the critical role of large datasets for advancing AI in surgery, conducted by Omri Bar, Daniel Neimark, Maya Zohar, Gregory D. Hager, Ross Girshick, Gerald M. Fried, Tamir Wolf, and Dotan Asselmann.

00:00

~3 min • Beginner • English

Index

Abstract

AI is becoming ubiquitous, revolutionizing many aspects of our lives. In surgery, it is still a promise. AI has the potential to improve surgeon performance and impact patient care, from post-operative debrief to real-time decision support. But, how much data is needed by an AI-based system to learn surgical context with high fidelity? To answer this question, we leveraged a large-scale, diverse, cholecystectomy video dataset. We assessed surgical workflow recognition and report a deep learning system, that not only detects surgical phases, but does so with high accuracy and is able to generalize to new settings and unseen medical centers. Our findings provide a solid foundation for translating AI applications from research to practice, ushering in a new era of surgical intelligence.

Publisher

Scientific Reports

Published On

Dec 17, 2020

Authors

Omri Bar, Daniel Neimark, Maya Zohar, Gregory D. Hager, Ross Girshick, Gerald M. Fried, Tamir Wolf, Dotan Asselmann

DOI

https://doi.org/https://doi.org/10.1038/s41598-020-79173-6

Related Publications

Explore these studies to deepen your understanding of the subject.

Computer Science

BALANCING COMPLIANCE, CREATIVITY, AND ENGAGEMENT: EVALUATING THE IMPACT OF NSFW GOVERNANCE ON USER BEHAVIORS FOR GEN AI PLATFORMS

J. Cao, K. Zhao, et al.

Business

Understanding continuance intention of artificial intelligence (AI)-enabled mobile banking applications: an extension of AI characteristics to an expectation confirmation model

J. Lee, Y. Tang, et al.

Education

Impact of an evidence-based training for educators on bystander intervention for the prevention of violence against LGBTI+ youth

O. Rios-gonzalez, J. C. Peña-axt, et al.

Medicine and Health

The COVID-AGICT study: COVID-19 and advanced gastro-intestinal cancer surgical treatment. A multicentric Italian study on the SARS-CoV-2 pandemic impact on gastro-intestinal cancers surgical treatment during the 2020. Analysis of perioperative and short-term oncological outcomes

G. Giuliani, F. Guerra, et al.

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny