As part of the GlaS@MICCAI2015 colon gland segmentation challenge, a team of researchers introduced a machine learning-based algorithm to segment glands in tissue of benign and malignant colorectal cancer.
The variability of glandular structures in biological tissue poses a challenge to automated analysis of histopathology slides. It has become a key requirement to quantitative morphology assessment and supporting cancer grading.
Using GPUs, CUDA, and Pylearn2 — a machine learning library built on top of Theano — the team trained their two deep convolution neural networks on a set of 125,000 images and achieved a classification accuracy of 98% and 94%, making use of the inherent capability of the system to distinguish between benign and malignant tissue.
In related news, the NVIDIA Foundation recently awarded $200,000 to a team of researchers from the University of Toronto for their GPU-accelerated cancer research by developing a “genetic interpretation engine” – a deep learning method for identifying cancer-causing mutations.
Read the research paper >>
Using CUDA and Machine Learning to Detect Colon Cancer
Dec 01, 2015
Discuss (0)
AI-Generated Summary
- Researchers applied GPU-accelerated deep learning to the GlaS@MICCAI2015 colon gland segmentation challenge, training two convolutional neural networks on 125,000 images using CUDA and the Pylearn2 library.
- The models achieved 98% and 94% classification accuracy in distinguishing benign from malignant colorectal tissue.
- The NVIDIA Foundation awarded $200,000 to a University of Toronto team for GPU-accelerated cancer research developing a genetic interpretation engine.
Next Step
- Read the research paper for detailed methodology and results.
Powered by NVIDIA Nemotron. AI-generated content may summarize information incompletely. Verify important information. Learn more
About the Authors
