The 103rd annual RSNA conference brought over 55,000 radiologists and medical physicists together. NVIDIA announced partnerships with GE Healthcare and Nuance to bring AI to medical imaging devices and platforms. AI and machine learning were major topics, with demos of segmentation, visualization and image reconstruction using deep learning. Over 1,000 people received deep learning training in the inaugural Deep Learning Classroom. The future of AI in medical imaging looks promising, with algorithms extracting new information from images and potentially changing imaging device design.
3. This year’s 103rd Annual Meeting of the Radiological Society
of North America (RSNA) brought together the largest
gathering of radiologists and medical physicists.
More than 55,000 attended.
4. RSNA 2017: AN OVERVIEW
At RSNA 2017, NVIDIA announced new key
partnerships, showcased the latest
technologies revolutionizing medical imaging,
offered NVIDIA Deep Learning Institute (DLI)
workshops and much more.
“As healthcare professionals strive to increase
their efficiency to serve an ever-growing
population, the industry is turning to AI and
machine learning as essential tools to improve
productivity and patient outcomes.
And NVIDIA is playing a leading role in that
effort.”
Source: https://blogs.nvidia.com/blog/2017/11/26/ai-medical-imaging/
READ BLOG
5. NVIDIA PARTNERS WITH GE HEALTHCARE
To kick off RSNA 2017, NVIDIA announced the first of
two major partnerships.
The collaboration with GE Healthcare brings
NVIDIA’s AI computing platform to GE’s 500,000
imaging devices.
“GE announced the new NVIDIA GPU-powered
Revolution Frontier CT, a CAT scan system
that is ‘two times faster in imaging
processing than its predecessor, due to its
use of NVIDIA’s AI computing platform.’”
Source: https://www.forbes.com/sites/davealtavilla/2017/11/28/nvidia-and-ge-partner-to-bring-ai-assisted-data-analytics-and-visualization-to-healthcare/#4b4155e31309
READ ARTICLE
6. THE IMPACT OF AI IN HEALTHCARE
A trending topic throughout RSNA 2017 was machine
learning applications for radiology, and AI continues to
open the door for intelligent medical instruments.
“The combination of deep learning, NVIDIA GPU
computing and medical imaging is spurring a new age
of intelligent medical instruments. Pioneers in the
diagnostic imaging community have jumped on the
NVIDIA GPU platform to achieve amazing results in
each of the major stages of the medical imaging
pipeline — reconstruction, image processing and
visualization.”
Source: https://blogs.nvidia.com/blog/2017/11/26/intelligent-medical-instruments/
READ BLOG
7. NVIDIA PARTNERS WITH NUANCE
On Day 2 of RSNA 2017, NVIDIA announced its
second partnership: bringing the NVIDIA AI
platform to Nuance’s AI Marketplace.
“The AI Marketplace combines the power of
NVIDIA’s deep learning platform with
Nuance’s PowerScribe radiology reporting
and PowerShare image exchange network, used
by 70% of all radiologists in the U.S.
The Nuance AI Marketplace is designed to be a
prime source for imaging algorithms that
augment the capabilities of radiologists and
provide rapid, open access to the industry’s
most advanced research.”
Source: http://hitconsultant.net/2017/11/27/nuance-artificial-intelligence-marketplace/
READ ARTICLE
8. CUTTING-EDGE AI DEMOS
Our booth featured demos that covered volumetric
segmentation, cinematic rendering for visualization
and image reconstruction. One featured demo from
the A.A. Martinos Center for Biomedical Imaging
presents a data-driven unified image reconstruction
approach: AUTOMAP.
“Image reconstruction plays a critical role in the
implementation of all contemporary imaging
modalities across the physical and life sciences…
We implement AUTOMAP with a deep neural network
and exhibit its flexibility in learning reconstruction
transforms for a variety of MRI acquisition
strategies.”
Source: https://arxiv.org/pdf/1704.08841.pdf
VIEW PAPER
9. THE INAUGURAL DEEP LEARNING CLASSROOM
The RSNA Deep Learning Classroom, presented by
NVIDIA Deep Learning Institute (DLI), trained over
1000 people during the 5 day span of the show.
Workshops included hands-on training in image
classification, image segmentation, quantitative
imaging and Radiomics.
Missed it? Visit the DLI website for self-paced
online labs.
VIEW ONLINE LABS
10. INCEPTION HEALTHCARE MEMBERS
Less than 18 months after its launch, NVIDIA’s
Inception program — which helps accelerate startups
pushing the frontiers of AI and data science — has
signed up its 2,000th member company.
NVIDIA currently has over 100 AI healthcare startups
in our Inception program. Several shared their
cutting-edge technology and demos in the NVIDIA
booth—including Aidence, 16 Bit, DesAcc, Vuno,
LPixel, CureMetrix, Lunit, Quantib, Aidoc, and
RadLogics .
LEARN MORE
11. CASE STUDY: DEEP LEARNING MODELS IN THE HOSPITAL
As the field of deep learning in medicine
progresses from research to clinical deployment,
practical considerations quickly become a
primary concern for operational leadership.
See how MGH & BWH Center for Clinical Data
Science approaches building a hardware
infrastructure on-premises.
“Our goal is to help other teams jumpstart their
hardware efforts as they seek to implement
deep learning in a hospital environment.”
Source: http://www.nvidia.com/object/developing-deep-learning-models-in-the-hospital
VIEW PAPER
12. PARTING THOUGHTS: AI IN MEDICAL IMAGING
“From precision imaging and Easy PACS to 3-D
viewing, cloud technology and machine learning,
radiology is indeed at the forefront of technology and
innovation in medicine.”
“…AI algorithms are deriving new information from
sometimes very low quality image data, and may
someday change the way imaging devices are
designed.”
“Radiology needs universally accepted ways to
develop and incorporate AI, similar to the DICOM
image standard, in order to make it easy for
developers to create new applications and integrate
them into imaging devices and clinical information
systems.”
WHERE IS AI HEADED?
Sources: https://rsna2017.rsna.org/dailybulletin/pdf/TEC_wed.pdf, https://rsna2017.rsna.org/dailybulletin/index.cfm?pg=17tue01, https://rsna2017.rsna.org/dailybulletin/index.cfm?pg=17wed02
13. To learn more about NVIDIA in
healthcare, visit:
http://www.nvidia.com/healthcare