GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Presentation
Media
Abstract:
The talk will focus on our 2 year journey to develop deep learning algorithms for the detection of pancreatic cancer on CT scans. The effort of a multi-disciplinary teams of Computer Scientists, Radiologists, Oncologists, and Pathologists determined that deep learning could potentially change the trajectory of pancreatic cancer survival (currently under 7% at 5 years) by early detection and avoiding what has been documented as an up to 25% false negative rate. The session will address the challenges of creating over 1100 normal studies to train the computer and then over 1500 pancreatic cancer studies to train the algorithms in booth organ segmentation and then tumor detection and analysis We will discuss what successes we have had in lesion detection and what changes remain . We will also discuss the role of Radiomics with deep learning as a way of potentially improving lesion detection and eventually lesion classification , The talk will illustrate the work done with a series of cases studies showing both the successes and challenges of this work. Finally we will address we we see this work going and the opportunities for introducing this into clinical practice.
The talk will focus on our 2 year journey to develop deep learning algorithms for the detection of pancreatic cancer on CT scans. The effort of a multi-disciplinary teams of Computer Scientists, Radiologists, Oncologists, and Pathologists determined that deep learning could potentially change the trajectory of pancreatic cancer survival (currently under 7% at 5 years) by early detection and avoiding what has been documented as an up to 25% false negative rate. The session will address the challenges of creating over 1100 normal studies to train the computer and then over 1500 pancreatic cancer studies to train the algorithms in booth organ segmentation and then tumor detection and analysis We will discuss what successes we have had in lesion detection and what changes remain . We will also discuss the role of Radiomics with deep learning as a way of potentially improving lesion detection and eventually lesion classification , The talk will illustrate the work done with a series of cases studies showing both the successes and challenges of this work. Finally we will address we we see this work going and the opportunities for introducing this into clinical practice.  Back
 
Topics:
AI in Healthcare, Artificial Intelligence and Deep Learning
Type:
Talk
Event:
GTC Washington D.C.
Year:
2018
Session ID:
DC8195
Streaming:
Share:
 
Abstract:

This talk will present the challenges and opportunities in developing a deep learning program for use in medical imaging. It will present a hands on approach to the challenges that need to be overcome and the need for a multidisciplinary approach to help define the problems and potential solutions. The role of highly curated data for training the algorithms and the challenges in creating such datasets is addressed. The annotation of data becomes a key point in training and testing the algorithms. The role of experts in computer vision, and radiology will be addressed and how this project can prove to be a roadmap for others planning collaborative efforts will be addressed Finally I will discuss the early results of the Felix project whose goal is nothing short of the early detection of pancreatic cancer to help improve detection and ultimately improve patient outcomes.

This talk will present the challenges and opportunities in developing a deep learning program for use in medical imaging. It will present a hands on approach to the challenges that need to be overcome and the need for a multidisciplinary approach to help define the problems and potential solutions. The role of highly curated data for training the algorithms and the challenges in creating such datasets is addressed. The annotation of data becomes a key point in training and testing the algorithms. The role of experts in computer vision, and radiology will be addressed and how this project can prove to be a roadmap for others planning collaborative efforts will be addressed Finally I will discuss the early results of the Felix project whose goal is nothing short of the early detection of pancreatic cancer to help improve detection and ultimately improve patient outcomes.

  Back
 
Topics:
AI in Healthcare, Medical Imaging & Radiology
Type:
Talk
Event:
GTC Silicon Valley
Year:
2018
Session ID:
S81004
Streaming:
Share:
 
Abstract:
"AI is transforming healthcare" is the buzz around every news alert these daysbut is it true? Where is AI and deep learning affecting healthcare and how is it impacting the medical imaging space? Join a thought leadership panel as government, industry and academic experts discuss the real calibration of the spaceseparating reality from the noise to explore how deep learning is advancing clinical practice, including advancements to overcome data and regulatory challenges.
"AI is transforming healthcare" is the buzz around every news alert these daysbut is it true? Where is AI and deep learning affecting healthcare and how is it impacting the medical imaging space? Join a thought leadership panel as government, industry and academic experts discuss the real calibration of the spaceseparating reality from the noise to explore how deep learning is advancing clinical practice, including advancements to overcome data and regulatory challenges.  Back
 
Topics:
Leadership and Policy in AI, AI in Healthcare
Type:
Panel
Event:
GTC Washington D.C.
Year:
2017
Session ID:
DC7246
Download:
Share:
 
Abstract:
We'll present our experience in the development of a multidisciplinary project for the early detection of pancreatic cancer. We'll present the FELIX project goals and the challenges including how we defined our goals and collected over 1300 annotated CT datasets for developing and testing deep learning algorithms. We will describe the deep network that we are using and discuss our results and future directions. This type of research has great potential for developing assistive devices for Radiologists as a second reader, high quality annotated datasets are critical for making progress in this field and are time consuming and expensive to acquire. This type of research is performed best by teams that combine expertise in Radiology and Machine Learning.
We'll present our experience in the development of a multidisciplinary project for the early detection of pancreatic cancer. We'll present the FELIX project goals and the challenges including how we defined our goals and collected over 1300 annotated CT datasets for developing and testing deep learning algorithms. We will describe the deep network that we are using and discuss our results and future directions. This type of research has great potential for developing assistive devices for Radiologists as a second reader, high quality annotated datasets are critical for making progress in this field and are time consuming and expensive to acquire. This type of research is performed best by teams that combine expertise in Radiology and Machine Learning.  Back
 
Topics:
AI in Healthcare
Type:
Talk
Event:
GTC Washington D.C.
Year:
2017
Session ID:
DC7266
Download:
Share:
 
 
Previous
  • Amazon Web Services
  • IBM
  • Cisco
  • Dell EMC
  • Hewlett Packard Enterprise
  • Inspur
  • Lenovo
  • SenseTime
  • Supermicro Computers
  • Synnex
  • Autodesk
  • HP
  • Linear Technology
  • MSI Computer Corp.
  • OPTIS
  • PNY
  • SK Hynix
  • vmware
  • Abaco Systems
  • Acceleware Ltd.
  • ASUSTeK COMPUTER INC
  • Cray Inc.
  • Exxact Corporation
  • Flanders - Belgium
  • Google Cloud
  • HTC VIVE
  • Liqid
  • MapD
  • Penguin Computing
  • SAP
  • Sugon
  • Twitter
Next