Deep Learning Paves Way for Better Diagnostics

By Tiffany Trader

September 19, 2016

Stanford researchers are leveraging GPU-based machines in the Amazon EC2 cloud to run deep learning workloads with the goal of improving diagnostics for a chronic eye disease, called diabetic retinopathy. The disease is a complication of diabetes that can lead to blindness if blood sugar is poorly controlled. It affects about 45 percent of diabetics and 100 million people worldwide, many in developing nations.

Final-year Stanford PhD students Apaar Sadhwani and Jason Su got involved in developing the diagnostic solution as part of a class project and corresponding Kaggle competition that was held last year. Sponsor Amazon provided AWS cloud credits in support of the research.

diabetic-retinopathy_5-classes_sadhwani-su_400x
Source: Automatic Grading of Eye Diseases Through Deep Learning, 2016

After Kaggle, the duo decided to turn their research project into a cloud-based platform that hospitals and clinics can use to guide the diagnosis of eye diseases. Their approach relies on a convolutional neural net (CNN) that grades the severity of diabetic retinopathy disease states into five categories: 0-4, with 0 being normal and 4 being the most severe.

The researchers have been training their model with a data set of 80,000 images from EYEPACS, a web-based application for exchanging eye-related clinical information, run by the California Health Foundation. “Getting data is the most constraining part of applying deep learning to a medical setting,” said Sadhwani, “but we are working closely with partners to get more data.”

They’ve also had to address a class imbalance in the data set. “We have a lot more 0’s and 1’s than 3’s and 4’s, for example,” said Sadhwani. As the disease progresses to stage four (known as proliferative diabetic retinopathy, or PDR), image data is more rare. A total of about 10,000 stage four images are required for optimal results.

The training problem is run on AWS Elastic Compute Cloud (EC2) with single-GPU and multi-GPU nodes. Some S3 storage and Elastic Block Store (EBS) services are also employed. The training takes about three days to a week for a given model.

Within EC2, the researchers are using Starcluster which lets them build custom clusters among the nodes and network them together. They used a master node to store all their training data and up to 28 different training nodes. All these separate training nodes would access the master node so they wouldn’t have to mirror the data onto each of the nodes.

“With Starcluster and AWS you can bring up different node types independently on demand,” said Su. “So we would run this experiment that would only need a single-GPU node and then after that finished we could shut down that node and save money. Then we would scale it up to a larger resolution image and we would need four-GPU nodes for that – so we’d spin that up, train on that, and come back three days later and shut that off. AWS provides this flexibility for scaling up and scaling down for cost and for trying out different ideas.”

The researchers relied on AWS spot instance pricing to further improve the economics. Their program saves a state every “epoch,” which relates to one pass through the data set, so losing a node did not incur a big setback. With 55 epochs in a run, the most they would lose is 1/55th of their training progress.

They used the g2.2xlarge instance type and the g2.8xlarge instance type for training their final models. They trained two kinds of models, one on low-res images and the final model on high-res images, for which they employed the larger multi-GPU nodes.

Amazon’s GPU instances are based on older Nvidia GRID K520 graphics cards, which at 4 GB per GPU do not have an ideal memory profile for training based on very high-resolution images.

“Typically in deep learning, you have a 256×256 image, or about one-sixteenth of a megapixel and we’re at four megapixels, so memory is a huge part of doing this problem,” said Sadhwani. “Our workaround was to scale to 4-GPU nodes, which effectively had 4 gigabytes of memory each [GPU], but we lose some to overhead because we have to have the model independently at each of the separate GPUs. It would be more advantageous to have a single GPU with a full 16 gigabytes.”

Because their model was dealing with these high-resolution images, they used Torch to split it across the 4-GPU node to fine-tune its parameters. Currently, they are moving to a distributed training model, which enables several different nodes to train essentially the same model but with independent data. This gives them the ability to train one model across many GPUs, rather than a single model on a single GPU node and thus accelerates the training.

The researchers are eyeing clouds with higher-memory GPUs, which could mean holding out for upgraded Amazon instances or moving to the Microsoft Azure cloud with its Tesla K80s.

They are not interested in CPUs. “It would take significantly longer, at least a factor of 50,” said Sadhwani. “The kind of neural networks we are using [convolutional neural nets] harness parallelization a lot. Even if we were not using this special class of network, there is at least a 10x speedup going from CPUs to GPUs, but for this particular variety that speedup is magnified a lot more, in the neighborhood of 100x.”

Diabetic retinopathy is a disease of the blood vessels in the eye. As the sugar level in the blood rises, it causes the walls of the blood vessels to thin and eventually they’ll crack and bleed. The most important thing to look for is tiny dot bleeds, called hemorrhages. They are very small and difficult to locate even with advanced algorithms. The deep learning model must also be trained to ignore or flag likely camera artifacts, which appear in approximately 40 percent of the images, and can obscure identification of disease traits.

To address these challenges, the Stanford team’s approach uses two networks, a lesion detector and a main network. The lesion detector looks at a small part of the image and outputs a number between 0 and 1, a probability. The lesion detector has so far achieved an accuracy of 99 percent for negatives and 76 percent for positives. The purpose of the main network is to characterize details about where the disease-related features are with respect to the important parts of the eye.

deep-learning-fused-architecture_sadhwani-su_800x
Source: Automatic Grading of Eye Diseases Through Deep Learning, 2016

The outputs of these two pipelines are then fused together. This provides a way to combine low-level details about where there are dot hemorrhages with high-level information like which parts of the image should actually be ignored because they are corrupted by artifacts. The fuse network is responsible for integrating all these signals together to deliver a final probability for the disease class.

Right now the team has been working with five classes, but they say that in the clinical setting, these grades are not tracked with such granularity. In terms of intervention, there are really three stages: 0) no action is required; 1) monitor the progress of the disease; and 2) medical intervention such as surgery is required.

“Moving to three-classes would increase the accuracy of our models because it’s a simpler problem and easier to solve,” said Su.

The ultimate goal here is to deliver a digital assistant to radiologists, opthamologists and other clinicians, so they can screen more patients, more frequently.

“Using an automated tool to augment human resources, you can more closely monitor the changes in the disease state as they progress to more effectively treat the disease,” said Su.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

SC Bids Farewell to Denver, Heads to Dallas for 30th

November 17, 2017

After a jam-packed four-day expo and intensive six-day technical program, SC17 has wrapped up another successful event that brought together nearly 13,000 visitors to the Colorado Convention Center in Denver for the larg Read more…

By Tiffany Trader

SC17 Keynote – HPC Powers SKA Efforts to Peer Deep into the Cosmos

November 17, 2017

This week’s SC17 keynote – Life, the Universe and Computing: The Story of the SKA Telescope – was a powerful pitch for the potential of Big Science projects that also showcased the foundational role of high performance computing in modern science. It was also visually stunning. Read more…

By John Russell

How Cities Use HPC at the Edge to Get Smarter

November 17, 2017

Cities are sensoring up, collecting vast troves of data that they’re running through predictive models and using the insights to solve problems that, in some cases, city managers didn’t even know existed. Speaking Read more…

By Doug Black

HPE Extreme Performance Solutions

Harness Scalable Petabyte Storage with HPE Apollo 4510 and HPE StoreEver

As a growing number of connected devices challenges IT departments to rapidly collect, manage, and store troves of data, organizations must adopt a new generation of IT to help them operate quickly and intelligently. Read more…

SC17 Student Cluster Competition Configurations: Fewer Nodes, Way More Accelerators

November 16, 2017

The final configurations for each of the SC17 “Donnybrook in Denver” Student Cluster Competition have been released. Fortunately, each team received their equipment shipments on time and undamaged, so the teams are r Read more…

By Dan Olds

SC Bids Farewell to Denver, Heads to Dallas for 30th

November 17, 2017

After a jam-packed four-day expo and intensive six-day technical program, SC17 has wrapped up another successful event that brought together nearly 13,000 visit Read more…

By Tiffany Trader

SC17 Keynote – HPC Powers SKA Efforts to Peer Deep into the Cosmos

November 17, 2017

This week’s SC17 keynote – Life, the Universe and Computing: The Story of the SKA Telescope – was a powerful pitch for the potential of Big Science projects that also showcased the foundational role of high performance computing in modern science. It was also visually stunning. Read more…

By John Russell

How Cities Use HPC at the Edge to Get Smarter

November 17, 2017

Cities are sensoring up, collecting vast troves of data that they’re running through predictive models and using the insights to solve problems that, in some Read more…

By Doug Black

Student Cluster LINPACK Record Shattered! More LINs Packed Than Ever before!

November 16, 2017

Nanyang Technological University, the pride of Singapore, utterly destroyed the Student Cluster Competition LINPACK record by posting a score of 51.77 TFlop/s a Read more…

By Dan Olds

Hyperion Market Update: ‘Decent’ Growth Led by HPE; AI Transparency a Risk Issue

November 15, 2017

The HPC market update from Hyperion Research (formerly IDC) at the annual SC conference is a business and social “must,” and this year’s presentation at S Read more…

By Doug Black

Nvidia Focuses Its Cloud Containers on HPC Applications

November 14, 2017

Having migrated its top-of-the-line datacenter GPU to the largest cloud vendors, Nvidia is touting its Volta architecture for a range of scientific computing ta Read more…

By George Leopold

HPE Launches ARM-based Apollo System for HPC, AI

November 14, 2017

HPE doubled down on its memory-driven computing vision while expanding its processor portfolio with the announcement yesterday of the company’s first ARM-base Read more…

By Doug Black

OpenACC Shines in Global Climate/Weather Codes

November 14, 2017

OpenACC, the directive-based parallel programming model used mostly for porting codes to GPUs for use on heterogeneous systems, came to SC17 touting impressive Read more…

By John Russell

US Coalesces Plans for First Exascale Supercomputer: Aurora in 2021

September 27, 2017

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, in Arlington, Va., yesterday (Sept. 26), it was revealed that the "Aurora" supercompute Read more…

By Tiffany Trader

NERSC Scales Scientific Deep Learning to 15 Petaflops

August 28, 2017

A collaborative effort between Intel, NERSC and Stanford has delivered the first 15-petaflops deep learning software running on HPC platforms and is, according Read more…

By Rob Farber

Oracle Layoffs Reportedly Hit SPARC and Solaris Hard

September 7, 2017

Oracle’s latest layoffs have many wondering if this is the end of the line for the SPARC processor and Solaris OS development. As reported by multiple sources Read more…

By John Russell

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

Google Releases Deeplearn.js to Further Democratize Machine Learning

August 17, 2017

Spreading the use of machine learning tools is one of the goals of Google’s PAIR (People + AI Research) initiative, which was introduced in early July. Last w Read more…

By John Russell

GlobalFoundries Puts Wind in AMD’s Sails with 12nm FinFET

September 24, 2017

From its annual tech conference last week (Sept. 20), where GlobalFoundries welcomed more than 600 semiconductor professionals (reaching the Santa Clara venue Read more…

By Tiffany Trader

Amazon Debuts New AMD-based GPU Instances for Graphics Acceleration

September 12, 2017

Last week Amazon Web Services (AWS) streaming service, AppStream 2.0, introduced a new GPU instance called Graphics Design intended to accelerate graphics. The Read more…

By John Russell

EU Funds 20 Million Euro ARM+FPGA Exascale Project

September 7, 2017

At the Barcelona Supercomputer Centre on Wednesday (Sept. 6), 16 partners gathered to launch the EuroEXA project, which invests €20 million over three-and-a-half years into exascale-focused research and development. Led by the Horizon 2020 program, EuroEXA picks up the banner of a triad of partner projects — ExaNeSt, EcoScale and ExaNoDe — building on their work... Read more…

By Tiffany Trader

Leading Solution Providers

Reinders: “AVX-512 May Be a Hidden Gem” in Intel Xeon Scalable Processors

June 29, 2017

Imagine if we could use vector processing on something other than just floating point problems.  Today, GPUs and CPUs work tirelessly to accelerate algorithms Read more…

By James Reinders

Delays, Smoke, Records & Markets – A Candid Conversation with Cray CEO Peter Ungaro

October 5, 2017

Earlier this month, Tom Tabor, publisher of HPCwire and I had a very personal conversation with Cray CEO Peter Ungaro. Cray has been on something of a Cinderell Read more…

By Tiffany Trader & Tom Tabor

Cray Moves to Acquire the Seagate ClusterStor Line

July 28, 2017

This week Cray announced that it is picking up Seagate's ClusterStor HPC storage array business for an undisclosed sum. "In short we're effectively transitioning the bulk of the ClusterStor product line to Cray," said CEO Peter Ungaro. Read more…

By Tiffany Trader

Intel Launches Software Tools to Ease FPGA Programming

September 5, 2017

Field Programmable Gate Arrays (FPGAs) have a reputation for being difficult to program, requiring expertise in specialty languages, like Verilog or VHDL. Easin Read more…

By Tiffany Trader

HPC Chips – A Veritable Smorgasbord?

October 10, 2017

For the first time since AMD's ill-fated launch of Bulldozer the answer to the question, 'Which CPU will be in my next HPC system?' doesn't have to be 'Whichever variety of Intel Xeon E5 they are selling when we procure'. Read more…

By Dairsie Latimer

IBM Advances Web-based Quantum Programming

September 5, 2017

IBM Research is pairing its Jupyter-based Data Science Experience notebook environment with its cloud-based quantum computer, IBM Q, in hopes of encouraging a new class of entrepreneurial user to solve intractable problems that even exceed the capabilities of the best AI systems. Read more…

By Alex Woodie

How ‘Knights Mill’ Gets Its Deep Learning Flops

June 22, 2017

Intel, the subject of much speculation regarding the delayed, rewritten or potentially canceled “Aurora” contract (the Argonne Lab part of the CORAL “ Read more…

By Tiffany Trader

Graphcore Readies Launch of 16nm Colossus-IPU Chip

July 20, 2017

A second $30 million funding round for U.K. AI chip developer Graphcore sets up the company to go to market with its “intelligent processing unit” (IPU) in Read more…

By Tiffany Trader

  • arrow
  • Click Here for More Headlines
  • arrow
Share This