AI in Medicine: Highlights from NVIDIA GTC 2023
In this blog post, I will be sharing the highlights focusing on the AI in Medicine track from the NVIDIA GTC 2023 conference including the latest advancements in AI technology and their potential applications.
I AM AI
NVIDIA opened keynotes with "I AM AI" introduction video featuring many of the latest research advancements for AI in Medicine.
- AlphaFold Protein Structure Database by DeepMind, Isomorphic Labs, and EMBL-EBI
- GenSLMs: Genome-scale language models reveal SARS-CoV-2 evolutionary dynamics by Argonne National Laboratory and Nvidia
- RadImageGAN by Mount Sinai, East River Imaging, and Nvidia
Several announcements related to medicine were made during the keynotes.
Accerelated computing and AI have arrived.
- Optimizing an Ultrarapid DNA Sequencing Technique for Critical Care Patients by Oxford Nanopore Technologies
- Long-Read Sequencing Workflows and Higher Throughputs in NVIDIA Parabricks 4.1
- Medtronic and NVIDIA Collaborate to Build AI Platform for Medical Devices — Integrating NVIDIA Technology Into Medtronic’s Real-Time AI Endoscopy Device to Help Improve Patient Care and Outcomes
- NVIDIA Launches Inference Platforms for Large Language Models and Generative AI Workloads
- Introducing G2 VMs with NVIDIA L4 GPUs — a cloud-industry first — One of the workloads that can be deployed is AlphaFold.
NVIDIA AI Foundation
During the keynotes, NVIDIA also announced the NVIDIA AI Foundation which is a set of cloud services that enable businesses to build, refine and operate custom large language models and generative AI models that are trained with their own proprietary data and created for their unique domain-specific tasks. Below are the services that are related to medicine.
- NVIDIA Unveils Large Language Models and Generative AI Service to Advance Life Sciences R&D — Part of NVIDIA AI Foundations, New BioNeMo Cloud Service Accelerates Life Sciences Research, Drug Discovery and Protein Engineering; Amgen and a Dozen Startups Among Early Access Customers
- BioNeMo — Accelerate early drug discovery with generative AI.
More details about some of the sessions will be coming soon if I have time.
- 3D Molecule Generation with the Equivariant Score-Based Diffusion Process
- Accelerate Smart Healthcare with AI-Powered Infrastructures (Presented by QCT)
- Accelerating Generative AI in Biology and Healthcare
- Acceleration and Deep Learning for Genomics on GPUs
- Actionable Insights for Surgical Practice
- Advancing Healthcare with Federated Learning: A Panel Discussion on How to Overcome Challenges and Achieve Success
- AI-Powered Drug Discovery
- Artificial Intelligence Captures the Language of Life Written in Proteins
- A Transformative AI Platform to Accelerate Biologics Discovery
- Developing Rapid DNA Sequencing to Accelerate Cancer Research and Care
- Examples of AI Development using DGX and MONAI, and Multi-Parametric Diagnostic Aid AI for Breakthrough Breast Cancer Screening Tests
- From Photons to Clinical Decisions: Image Reconstruction in Photon-Counting CT
- Generative Deep Learning with BioNeMo for Protein Therapeutics
- High Performance Genome-Wide Association Study Using Mixed-Precision Ridge Regression
- How Short-Term Hybrid HPC-QC can Accelerate Drug Discovery
- Imaging AI Factory Powered by MONAI and NVIDIA Enterprise
- Learn How to Develop and Deploy Real-Time AI Applications in Healthcare
- Multimodal Deep Learning for Protein Engineering
- RadImageGAN: Multi-Modal Generative AI for Medical Imaging
- Scaling Deep Learning for Drug Development with an AI Factory and MONAI
- Scaling Long-Read Sequencing Throughput and Accessibility with Deep Learning and NVIDIA
- Posters Spotlight: Healthcare