NVIDIA AI Podcast

How SDSC Uses AI to Transform Surgical Training and Practice - Ep. 241

· Summarized

Share this episode
Anyone with this link can open it.
Share Link
Start at 0:00

Key takeaways

  • AI can significantly enhance surgical practices by analyzing video data to provide immediate feedback to surgeons.
  • Collecting high-quality surgical videos is a fundamental challenge due to various factors, including data storage practices and awareness among surgeons.
  • Collaboration between machine learning professionals and surgical practice experts is essential to developing meaningful AI applications.
  • The use of AI in surgical education is poised to transform how training is conducted, potentially improving outcomes globally.
  • There is a strong need for diverse data to train AI models effectively in the surgical domain.

Summary

Introduction to AI in Surgery

In this episode, host Noah Krabitz welcomes Margaux Masson-Forsythe, director of machine learning at the Surgical Data Science Collective (SDSC). They discuss her background and experience in machine learning and AI, particularly her passion for projects that focus on social good, sustainability, and healthcare. Margaux emphasizes her excitement about using AI to analyze surgical videos that can provide valuable insights for surgeons.

The Impact of AI on Surgical Practices

Margaux elaborates on how AI can help surgeons improve their techniques and patient outcomes. SDSC's mission is to analyze a vast repository of surgical data to empower global health improvements. Despite the challenges of collecting these videos—which are often long and underutilized—Margaux highlights the importance of gathering diverse data to train effective AI models.

Challenges and Innovations in AI Data Collection

The podcast delves into the obstacles of acquiring and processing surgical videos. Margaux shares that many surgical videos go unrecorded due to busy schedules or a lack of awareness about their future utility. Moreover, when videos are collected, they often come from various sources, leading to a mix of filming techniques and perspectives that can complicate analysis. The episode underscores the need for AI to adapt to the temporal complexities of these video data.

Collaboration Between Engineers and Clinicians

Margaux emphasizes the importance of collaboration between computer scientists and surgical experts at SDSC. They work closely with clinicians to ensure that AI tools developed are not only technically sound but also clinically relevant. The innovations stem from understanding the needs of surgeons and translating those into actionable AI analyses.

Education and Future Directions

One of the key benefits discussed is the potential for AI to transform surgical education, moving beyond traditional textbooks to real surgical scenarios through video analysis. Margaux expresses hope for more standardized practices in surgery, driven by collaborative analysis of these recorded surgeries. The conversation wraps up with an invitation for listeners in the medical and engineering fields to engage with SDSC's initiatives.

Sponsors

  • Nvidia · Helping to power advanced AI technologies for health and beyond.

Show notes

Margaux Masson-Forsythe, director of machine learning at the Surgical Data Science Collective (SDSC), discusses how AI-driven video analysis is transforming surgical training and practice, making surgery safer and more accessible to billions of people worldwide.

Follow this show on AudioBrevity and new episodes get summarized for you. Create a free account

Couldn't load the audio. A blocker may be stopping the show's tracking links. Open the file