Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Celebrating and Supporting the Medical Imaging Community

3,068 views

Published on

This year’s MICCAI conference had record-breaking attendance. If you missed it, view this SlideShare to catch up on all the highlights and NVIDIA news.

Published in: Healthcare

Celebrating and Supporting the Medical Imaging Community

  1. 1. Key Takeaways from MICCAI 2018 CELEBRATING AND SUPPORTING THE MEDICAL IMAGING COMMUNITY
  2. 2. INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING & COMPUTER ASSISTED INTERVENTION (MICCAI) The 21st MICCAI annual conference was held in Granada from September 16th to 20th and brought together leading biomedical scientists, engineers, and clinicians from a wide range of disciplines.
  3. 3. MICCAI: BY THE NUMBERS 1,400+ Registered Delegates: 33% Increase over 2017 1600+ Attendees over the 2-day Satellite Events 1000+ Papers Submitted 373 Accepted Papers: 70% Feature AI 79 Posters 40 Workshops 14 Tutorials 12 Challenges 4 Keynote Speakers
  4. 4. Now in its 21st year, MICCAI is the preeminent conference on medical imaging research, bringing together a wide range of experts from academia to industry and healthcare organizations. NVIDIA was a dedicated and active participant at MICCAI with hosted workshops, engaging talks, and a number of accepted papers and posters. MICCAI 2018 LEARN MORE ABOUT MICCAI Source: https://blogs.nvidia.com/blog/2018/09/17/medical-imaging-deep-learning-miccai/
  5. 5. CELEBRATING RESEARCH MICCAI 2018 boasted a robust scientific program. With over 1,000 papers submitted, the 373 accepted papers represented the best of the best. NVIDIA had a dozen accepted papers, and 6 poster presentations. Among the research presented, the team used an AI technique called generative adversarial networks (GANs) to generate synthetic images which can be used to train AI-based medical imaging systems. Source: https://youtu.be/BMuFk2PjEuM WATCH NOW
  6. 6. NVIDIA DEEP LEARNING INSTITUTE (DLI) NVIDIA hosted 200 attendees for our workshop “Deep Learning for Healthcare Image Analysis.” The two-part workshop featured hands-on, instructor led training that focused on healthcare applications including generative networks for medical imaging and coarse to fine contextual memory for medical imaging. Source: https://www.nvidia.com/en-us/deep-learning-ai/education/ LEARN MORE ABOUT DLI
  7. 7. SPONSORED PAPERS AND CHALLENGES At this year’s MICCAI Conference, NVIDIA sponsored several papers and challenge, including: 1st Workshop on PRedictive Intelligence in MEdicine (PRIME-MICCAI) Statistical Atlases and Computational Modelling of the Heart Workshop (STATCOM) Deep Learning in Medical Image Analysis (DLMIA) Multi-shell Diffusion MRI Harmonisation Challenge (MUSHAC) Medical Segmentation Decathlon (MSD) Source: ttps://www.miccai2018.org/en/WORKSHOP---CHALLENGE---TUTORIAL.html LEARN MORE
  8. 8. PRIME-MICCAI CHALLENGE WINNER "Generation of Amyloid PET Images via Conditional Adversarial Training for Predicting Progression to Alzheimer’s Disease” Yu Yan, Hoileong Lee, Edward Somer, Vicente Grau Their paper highlights an application of conditional generative adversarial networks to the generation of florbetapir PET images from corresponding MRI images. Source: http://basira-lab.com/events-workshops/PRIME-MICCAI18/ READ MORE
  9. 9. DLMIA BEST PAPER WINNER “Automatic Segmentation of Pulmonary Lobes Using a Progressive Dense V-Network” Abdullah-Al-Zubaer Irman, Ali Hatamizadeh, Shilpa Pundi Ananth, Xuaiwei Ding, Demetri Terzopoulos, Nima Tajbakhsh Using one NVIDIA Titan XP GPU, their demonstrated method can segment lung lobes in one forward pass of the network, with an average run time of 2 seconds. Source: https://cs.adelaide.edu.au/~dlmia4/ LEARN MORE ABOUT DLMIA
  10. 10. MEDICAL SEGMENTATION DECATHLON The MSD challenge tests the generalizability of machine learning algorithms when applied to 10 different semantic segmentation tasks. The aim is to develop an algorithm or learning system that can solve each task, separately, without human interaction. Source: http://medicaldecathlon.com/ READ MORE Winner: Fabian Isensee, German Cancer Research Center (DKFZ), Team nnU-Net (Phase 1 and 2) 1st Runner-Up: Yingda Xia, Johns Hopkins University/NVIDIA, Team NVDLMED 2nd Runner-Up BeomHee Park, Asan Medical Center, Team beomheep
  11. 11. BRATS CHALLENGE WINNER BraTS (Multimodal Brain Tumor Segmentation) has always been focused on the evaluation of state-of-the-art methods for the segmentation of brain tumors in multimodal magnetic resonance imaging (MRI) scans. This year, NVIDIA’s own Andriy Myronenko, Lead Scientist of Brain Segmentation, won first place in the challenge from 390 participants. Source: https://www.cbica.upenn.edu/sbia/Spyridon.Bakas/MICCAI_BraTS/MICCAI_BraTS_2018_proceedings_shortPapers.pdf LEARN MORE
  12. 12. THE YOUNG SCIENTIST IMPACT AWARD The MICCAI Young Scientist Impact Award recognizes those who have had a significant impact in their field so early in their career. This year, NVIDIA’s Dr. Holger Roth won the Young Scientist Impact Award for pioneering deep learning in medical imaging. VIEW RECENT WORK Source: http://www.cs.jhu.edu/~lelu/publication/MICCAI2018_Colonoscopy.pdf
  13. 13. DON’T MISS NVIDIA AT GTC DC Discover the latest advances in deep learning across healthcare at the premier AI conference. Learn from expert trainers and connect with key opinion leaders and luminaries from renowned institutions,including Johns Hopkins University, OSU Wexner Medical Center, and the National Institutes of Health. Use discount code CMHEALTH20 for a 20% discount off regular prices. Source: https://www.nvidia.com/en-eu/gtc/, https://www.nvidia.com/en-us/gtc-dc/pricing/ REGISTER TODAY
  14. 14. To learn more about NVIDIA in healthcare, visit: http://www.nvidia.com/healthcare

×