header lang header lang EN
sambanova-logo-black
Products
SambaNova’s AI platform is the technology backbone for the next decade of AI innovation. Customers are turning to SambaNova to quickly deploy state-of-the-art AI and deep learning capabilities that help them outcompete their peers.
SambaNova Suite
The only, enterprise grade full stack platform, purpose built for generative AI
DataScale®
The platform for generative AI development and innovation
Use Cases
Public Sector | AI for Science | Sovereign AI
Technology
RDU: The GPU Alternative
Power the most demanding generative and agentic AI workloads with the most performant & capable processor, purpose-built for AI
Composition of Experts
Easily run your custom models, accelerate discovery, & power the next generation of high performance computing
Developers
SambaNova delivers the only enterprise-grade full stack platform, from chips to models, purpose built for generative AI
SambaNova Cloud
Supercharge your AI-powered applications across Llama 3 8B, 70B, & 405B models.
For free.
Resources
Developer Community
Starter Kits
Research
Technical Documentation
Resources
Find what you need to accelerate your AI journey.
About
Customers are turning to SambaNova to quickly deploy state-of-the-art AI capabilities to gain competitive advantage. Our purpose-built enterprise-scale AI platform is the technology backbone for the next generation of AI computing. We power the foundation models that unlock the valuable business insights trapped in data.
Try It Now »
sambanova-logo-black
header lang header lang EN
Try It Now »
Try It Now »
PUSHING COMPUTER VISION BOUNDARIES TO 50K AND BEYOND

Determining MSI Status for Effective Cancer Treatment

PUSHING COMPUTER VISION BOUNDARIES TO 50K AND BEYOND

The microsatellite instability (MSI) status of a patient’s cancerous tissue can be used to determine the proper cancer treatment.

MSI status is an indicator of the extent of genetic mutations and can be used to predict whether immunotherapy (a new type of cancer treatment) will be effective.

MSI MSI

Currently, the standard methods of determining MSI status are immunohistochemistry (IHC) analysis and polymerase chain reaction (PCR)-based assays. However, both of these methods require trained professionals to process the tissue samples and additional costs. Therefore, many patients globally are not given these tests in clinical practice, missing the opportunity to get better treatment.

pcr_ihc PCR & IHC

In order to make MSI profiling accessible to more patients, researchers have attempted to build prediction models using the standard hematoxylin and eosin (H&E)-stained histology images. Images of patients’ cancerous tissue samples, obtained using the inexpensive, common procedure of H&E staining, served as the input of machine learning models to predict the MSI status.

histology_deep_learning Histology Deep Learning

However, H&E histology using deep learning was not very accurate in determining MSI status. A study using this method published in 2019 reported a 77% area under the receiver operating characteristic curve (AUC, a representation of ML model performance). In contrast, IHC is approximately 92% accurate when using PCR genotyping results as the ground truth.

AUC_comparison.5b7b6977 PCR genotyping results

Fast-forwarding to today, by using a more complex model and SambaNova’s Reconfigurable Dataflow Architecture™, an 89.4% AUC is achieved on the same data set. This boost in model performance is the combined result of using a more sophisticated model architecture and the fact that SambaNova’s Reconfigurable Dataflow Units™ (RDUs) can take large images as input that other chips cannot. As we support even larger image sizes in the future, we can expect the AUC percentage to further increase, which could potentially bring accurate, economic, and universal MSI status testing to all patients.

To demonstrate the effect of using larger images as input, we compare the AUC achieved by training a model using 5760x5760 images as the input versus that achieved by two other models trained using 512x512 images as the input (see next section for details). These models use the same advanced model architecture (RescaleNet50) and are run on the same hardware (RDUs). The result shows that input image size has a significant impact on AUC.

Why Input Image Size Matters in Machine Learning:
Using True Resolution Images

By using high resolution images as input in machine learning applications, a feat achieved only by SambaNova, better results can be attained.

Each hardware, be it GPU or RDU, has an input size limit. When working with images larger than the size limit, there are two common techniques to overcome this limitation.

Technique 1:
TILING
Tiling Tiling

The parent image is tiled into an array of smaller images, which are used as individual input. If the percentage of tiles that gave a positive prediction exceeds a certain threshold, an overall positive prediction is made.

tiling_comparison tiling_comparison_mobile.4a5acca0

When images of cancerous tissues were tiled into 5760x5760 patches, 89.4% AUC was achieved. Meanwhile, tiling them into 512x512 patches resulted in 83.5% AUC.

Generally, the smaller the size of the tiles, the more the information loss, and consequently less model accuracy. Consider the extreme case where each tile is only one pixel large. These individual single pixels don’t give much information about about the image, does it? In contrast with other IC chips on the market, SambaNova’s RDUs support significantly larger tile sizes, bringing impressive improvements to model accuracy.

Technique 2:
DOWNSAMPLING
downsampling downsampling_mobile.4eeba047

Alternatively, an image can be downsampled so that the size is below the limit.

However, just as a low resolution image looks blurry to us, models trained on these downsampled images suffer a lower accuracy.

downsampling_comparison downsampling_comparison_mobile.bd58e77a

To demonstrate the effect of downsampling, we first break the entire image into tiles of 5760x5760 pixels then downsample these tiles into to 512x512-pixel tiles.

Compare the Different Methods

Try running the simulation below. This demonstrates an example of when using a large tile size at original resolution produces the correct prediction while using smaller tiles or large tiles with lower resolution generates an erroneous prediction.

Reference MSI Status Testing Result (obtained using PCR)

MSI Status: Microsatellite Stable (MSS)

Recommendation: Immunotherapy not recommended

large tile size
LARGER TILE SIZE - LOW RESOLUTION
Each 5760x5760 pixel tiles are downsampled into 512x512 blocks and then fed to the machine learning model. This technique generates the lowestest accuracy compared to that of the other two.
MSI %: --
MSI Status: --
Recommendation: --
sim image
large tile size
SMALLER TILE SIZE - ORIGINAL RESOLUTION
512x512 pixel tiles are fed to the machine learning model to acquire predictions. This takes more time and is less accurate compared to using larger tiles.
MSI %: --
MSI Status: --
Recommendation: --
sim image
large tile size
LARGER TILE SIZE - ORIGINAL RESOLUTION
5760x5760 pixel tiles are fed to the machine learning model to acquire predictions.

Only Supported By

logo
MSI %: --
MSI Status: --
Recommendation: --
sim image
With SambaNova’s true resolution vision ML technology, accurate universal MSI testing for cancer patients could be made possible.
What do you think you can achieve
with this ground-breaking technology
?
image resolution image resolution

Schedule a meeting

Learn how SambaNova can advance your AI initiatives to help you achieve your impossible.
Get Started
logotype_sambanova_orange
Our Headquarters:
2200 Geng Road, Unit 100
Palo Alto, CA 94303
(650) 263-1153
Terms & Conditions Privacy Policy
Copyright © 2024 SambaNova Systems, Inc. All rights reserved

Products

Technology

Resources

About

Contact

Customers turn to SambaNova to quickly deploy state-of-the-art AI capabilities to meet the demands of the AI-enabled world. Our purpose-built enterprise-scale AI platform is the technology backbone for the next generation of AI computing. We enable customers to unlock the valuable business insights trapped in their data. Our flagship offering, SambaNova Suite, overcomes the limitations of legacy technology to power the large complex foundation models that enable customers to discover new services and revenue streams, and boost operational efficiency. Headquartered in Palo Alto, California, SambaNova Systems was founded in 2017 by industry luminaries, and hardware and software design experts from Sun/Oracle and Stanford University. Investors include SoftBank Vision Fund 2, funds and accounts managed by BlackRock, Intel Capital, GV, Walden International, Temasek, GIC, Redline Capital, Atlantic Bridge Ventures, Celesta, and several others.
Our Headquarters:
2200 Geng Road, Unit 100
Palo Alto, CA 94303
(650) 263-1153
Terms & Conditions Privacy Policy
Copyright © 2024 SambaNova
Systems, Inc. All rights reserved