Sustainability

Advances in Medicine

Deep Learning

Advances in Medicine

 
AI shaping healthcare’s new age of healing

Artificial intelligence is transforming the world of medicine, and helping to reshape the diagnosis and treatment of cancer.

NVIDIA is at the forefront of this transformation, advancing new applications and discoveries through powerful technology that puts unprecedented tools into the hands of researchers and physicians around the globe.

In line with the UN Sustainable Development Goals of promoting healthy lifestyles and well-being for all citizens, we're supporting work in researching infectious diseases, such as HIV and Ebola; finding ways to help reduce deaths from noncommunicable illnesses, such as cancer and chronic respiratory disease; and, through the development of autonomous vehicles, helping curb injury and death from road accidents.

 
 
AI-Powered Healthcare

AI is driving developments in medicine that can identify genetic mutations, speed diagnosis, and manage treatment protocols.

Among a profusion of recent examples, Stanford University doctors are using AI to dramatically reduce diagnostic imaging errors. GE Healthcare is using deep learning to go beyond medical imaging to help manage challenges faced by caregivers. And Arterys, a San Francisco startup, is bringing cloud computing and deep learning into clinical settings to reduce errors in cardiac radiology.

Deep learning is helping medical researchers train neural networks to analyze medical data, including images, to identify traits in different diseases. It can speed reviews of images, aiding doctors' ability to analyze and diagnose.

AI is also advancing the future of personalized medicine. Recent efforts combining computer vision and medical prosthetics have led to the creation of glasses that allow the blind to "see."

Enormous computational muscle provided by GPUs is needed to support the rigorous image training, data processing, and diagnostic processes that are essential for the next breakthrough. A powerful new tool is the NVIDIA DGX-1 AI supercomputer, the latest version of which will provide nearly one petaflops of processing power. Already deployed in facilities like Massachusetts General Hospital, DGX-1 allows doctors to compare a single patient's tests and history with billions of data points from a vast population of other patients.

Other medical centers are also automating the analysis of MRIs, CT scans, and X-rays to assist physicians in making a diagnosis. The goal isn't for AI to replace doctors but rather provide them with tools to more efficiently assess patients faster and with fewer errors.

 
 
How AI reshapes Cancer Gameplan

Enormous energies are being put into applying the powers of AI into the scourge of cancer, a disease that nearly one in six people globally will be diagnosed with in their lifetime, World Health Organization figures show.

GPUs and AI are advancing diagnosis and treatment for breast cancer, the second leading cause of cancer death in women worldwide, thanks to researchers at Case Western Reserve University.

After diagnosing cancer in a patient, doctors are most likely to plan aggressive treatments such as chemotherapy, which comes with such side effects as nausea, hair loss, and fatigue, when other therapies may be less invasive. Researchers are using GPU-accelerated deep learning to develop an automated test that could speed diagnosis and improve accuracy without destroying the tissue specimen. The estimated cost: $200 instead of $4,000.

With a breast cancer diagnosis, doctors and patients want accurate results and information. The variety of methods used to analyze that data can make reliable predictions difficult to come by.

A team from Harvard Medical School's Beth Israel Deaconess Medical Center tackled this issue using deep learning, in the 2016 Camelyon Grand Challenge. Hosted by the International Symposium on Biomedical Imaging, the competition aims to determine how algorithms can help pathologists better identify cancer in lymph node images. The team's results were dramatic, dropping the human error rate in diagnosis by 85 percent when aiding a pathologist's efforts with GPU-powered deep learning analysis. And the learnings can be applied to different branches of medical research.

AI could help doctors diagnose brain tumors more quickly and more accurately, according to a new study by researchers at the University of Michigan Medical School and Harvard University.

"Our goal is to develop an algorithm that approaches the performance of a neuropathologist at diagnosis during an operation," said Dr. Daniel Orringer, first author of the study in Nature Biomedical Engineering and an assistant professor of neurosurgery at Michigan Medicine.

And it's not just cancer that AI is tackling, but also Alzheimer's and Parkinson's. These devastating diseases are among the hundreds that scientists are struggling to cure with new medicines in the face of soaring drug-discovery costs and testing times.

AI is also showing the potential to be a faster, more efficient tool for finding and developing new drugs. A growing number of companies and university researchers are tackling some of medicine's toughest problems by using AI computing to rapidly simulate protein shapes, and better predict which drug molecules are most likely to be effective treatments.

 
 
AI-Propelled Cancer Moonshot

In November, NVIDIA announced it's working with the U.S. National Cancer Institute, the U.S. Department of Energy, and several national laboratories to accelerate cancer research.

The initiative — known as the Cancer Moonshot, announced by U.S. President Barack Obama during his 2016 State of the Union address — aims to deliver a decade of advances in cancer prevention, diagnosis, and treatment in five years. The research efforts include a focus on building an AI framework called the Cancer Distributed Learning Environment, or CANDLE.

It will provide a common discovery platform that brings the power of AI to the fight against cancer. CANDLE will be the first AI framework designed to change the way we understand cancer, giving data scientists around the world a powerful new weapon against this disease.

 
 
NVIDIA makes it Personal

The fight against cancer is global, but for NVIDIA, it's very personal.

Finding ways to fight cancer have engaged NVIDIANs at every level — from the company funding research and employees deciding which cancer care programs to support, to inspiring charity walks and bake sales. The efforts are all aimed at funding cancer-focused nonprofits to support some of the world's most promising cancer research.

Spearheading the company's efforts is the NVIDIA Foundation, our employee-led philanthropic arm, which evaluates and assesses different research groups and nonprofits in their efforts to fight cancer and support those dealing with it. Since 2011, the foundation has deployed almost $3 million to advance cancer research and care.

This includes our annual $200,000 Compute the Cure grants to researchers using GPUs and accelerated computing to advance their work in cancer diagnostics, treatment, and drug design.

One of this year's grant recipients is a team led by Seungchan Kim at the Translational Genomics Research Institute (TGen), in Phoenix, Ariz. It aims to understand why some cancer cells respond to treatments and others don't. This could make it possible to treat different cells with different medications.

Another recipient is a team, led by Andrés Cisneros at the University of North Texas, which is searching for mutations that cause changes in the proteins that repair damage to DNA. These mutations may indicate the presence of cancer.

NVIDIA also awards four $50,000 Compute the Cure cancer care grants to nonprofits providing patient care and support around the world. Recent grants fund a radiotherapy treatment in Kenya, provide music therapy for pediatric patients in the United States, support pain relief and end-of-life care to the poor in India, and help fund the #KnowYourLemons global breast cancer awareness program.