AI Exchange
timezone
+00:00 GMT
SIGN IN
  • Home
  • Events
  • Content
  • People
  • Messages
  • Channels
  • Help
Sign In
Sign in or Join the community to continue

Challenges of Developing Models for Gigapixel-Scale Pathology

Posted Oct 19
# TransformX 2022
# Breakout Session
Share
SPEAKER
Nathan Silberman
Nathan Silberman
Nathan Silberman
Formerly, VP of AI at PathAI, Butterfly @ ML Executive

Nathan is a seasoned technology leader with deep expertise in machine learning. Most recently, Nathan was the VP of Machine Learning at PathAI where his organization was responsible for developing state-of-the-art machine learning models that interpret gigapixel-scale pathology images to identify tissue types, discover novel biomarkers, and produce clinical and diagnostic results. Prior to PathAI, Nathan was the VP of Artificial Intelligence at Butterfly Network where he led the development of a suite of real-time ultrasound products that assist clinicians in acquiring and interpreting diagnostic images. Nathan also previously worked at Google Research where he co-developed an internal library that became the Google TensorFlow 1.0 API. He obtained his PhD and BA from New York University.

+ Read More

Nathan is a seasoned technology leader with deep expertise in machine learning. Most recently, Nathan was the VP of Machine Learning at PathAI where his organization was responsible for developing state-of-the-art machine learning models that interpret gigapixel-scale pathology images to identify tissue types, discover novel biomarkers, and produce clinical and diagnostic results. Prior to PathAI, Nathan was the VP of Artificial Intelligence at Butterfly Network where he led the development of a suite of real-time ultrasound products that assist clinicians in acquiring and interpreting diagnostic images. Nathan also previously worked at Google Research where he co-developed an internal library that became the Google TensorFlow 1.0 API. He obtained his PhD and BA from New York University.

+ Read More
SUMMARY

Interpretation of pathology slides is a crucial part of diagnosing disease and an increasingly important part of drug discovery and drug development pipelines. The massive and ever-growing volume of data being produced for each of these areas has led to increased interest in harnessing machine learning in order to produce new biological insights, discover novel biomarkers, steer patient selection for clinical trials, and improve diagnostic accuracy. Effectively training and deploying computer vision models to interpret pathology images must overcome a massive hurdle: pathology slides are typically 100,000 x 100,000 pixels each, many orders of magnitude larger than is typical in computer vision pipelines. However, a number of approaches have been developed over the last few years which have made automatic interpretation of pathology slides not just feasible but a valuable tool used by many healthcare companies around the world. ML Executive; Formerly, VP of AI at PathAI, Butterfly, Nathan Silberman walks attendees through a number of these novel and creative approaches.

+ Read More

Watch More

42
Posted Sep 09 | Views 39.4K
# Large Language Models (LLMs)
# Natural Language Processing (NLP)
40:10
Posted Oct 06 | Views 1.4K
# TransformX 2021
# Fireside Chat
28:29
Posted Oct 08 | Views 2K
# Tech Talk