Featured Video
This Week in Quality Digest Live
Innovation Features
Mike Richman
An extravaganza of industry coverage on Manufacturing Day 2018
Nicole Radziwill
Getting started with Quality 4.0
Dan Jacob
It’s a once-in-a-career opportunity to lead quality and safety transformation
Ryan E. Day
Sorting through the chaff of Industry 4.0 hyperbole
Paul Sloane
Tackle the common obstacles first

More Features

Innovation News
The FDA wants medical device manufactures to succeed, new technologies in supply chain managment
Other exhibits will feature machine tools to demonstrate tool setting, probing, machine monitoring, and robotic gauging
The custom-built, 727 cu in. Hemi engine will be raffled to support Victory Junction children’s camp
At annual entrepreneurship competition, eight teams pitched business ideas, and three took home cash prizes
Neuroscientists train a deep neural network to analyze speech and music
Preparing your organization for the new innovative culture
IoT solution includes advanced lab testing and real-world crowd testing
New system patches security holes left open by web browsers’ private-browsing functions

More News

Lawrence Berkeley National Laboratory

Innovation

New Machine Learning

Data can be used across domains with limitations removed

Published: Wednesday, April 12, 2017 - 12:00

(Lawrence Berkeley National Lab: Berkeley, CA) -- A team of scientists at Berkeley Lab has developed an unsupervised multiscale machine learning technique that can automatically and specifically capture biomedical events or concepts directly from raw data.

In many data-driven biomedical studies, the data limitations (e.g., limited data scale, limited data label, unbalanced data, and uncontrollable experimental factors) impose great challenges to scientific discovery, which can only be addressed with advanced machine learning techniques. This work is described in the article, “Unsupervised Transfer Learning via Multi-Scale Convolutional Sparse Coding for Biomedical Applications,” published January 2017, in the IEEE Transactions on Pattern Analysis and Machine Intelligence journal. The work provides an effective and efficient way of learning and targeting sharable information so data can be used across domains. It also potentially removes limitations, especially for biomedical studies.

This multiscale machine learning technique can be applied to many biomedical tasks, allowing the efficient and effective capturing of biomedical events or concepts at different scales (e.g., physical size) without any pre-defined biomedical endpoints or studies. An example of a pre-defined endpoint could be differentiation of tumor morphology that can predict metastatic risk. Researchers have shown that the information captured through this technique can be directly deployed or fine-tuned toward new endpoints or studies in related biomedical domains.

The core group in this team, Hang Chang, Antoine M. Snijders, and Jian-Hua Mao, together with another scientist, Zhong Wang, of Berkeley Lab’s Biosciences Area, have initiated a Berkeley Biomedical Data Science Center (BBDS), which combines expertise across multiple disciplines to further facilitate and nurture data-intensive biomedical science.

“We have shown that our technique can be applied to other diverse biomedical tasks,” says Hang Chang, a research scientist in the Lab’s Biological Systems & Engineering Division. “For instance, the knowledge derived from human brain tumor histology can be directly utilized for the differentiation of mouse mammary tumor morphology between radiation-induced cancer and spontaneous cancer. This suggests that our technique can be beneficial to biomedical studies with translational potential.”

The multiscale machine learning technique helps improve the effectiveness and efficiency in learning sharable information across domains.

“When we determine basis information from data collected from cell culture or animal model studies, we think it will be possible to share and deploy the pre-attained information in human-related studies,” adds Chang.

The BBDS plans to apply this technique to three ongoing projects related to cancer risk assessment of environment exposure, early stage cancer diagnosis, and multimodal biomarkers identification for personalized medicine.

For more information, visit the BBDS website.


Berkeley Biomedical Data Science Center. Click here for larger image.

Discuss

About The Author

Lawrence Berkeley National Laboratory’s picture

Lawrence Berkeley National Laboratory

Lawrence Berkeley National Laboratory (Berkeley Lab) is a U.S. Department of Energy National Laboratory managed by the University of California; and it’s charged with conducting unclassified research across a wide range of scientific disciplines. Berkeley Lab has trained thousands of university science and engineering students. It was founded in 1931 by Ernest Orlando Lawrence, a UC Berkeley physicist and Nobel Prize winner whose belief was that scientific research is best done through teams of individuals with different fields of expertise, working together. His teamwork concept is a Berkeley Lab legacy that continues today.