Convolutional Neural Networks for Organ Segmentation


Accurate automated organ and disease feature segmentation is a challenge for medical imaging analysis. The pancreas, for example, is a small, soft, organ with low uniformity of shape and volume between patients. Because of the lack of uniform image patterns, there are few features that can be used to aid in automated identification of anatomy and boundaries. Segmentation of high variability features is uniquely difficult for a computer to perform. Due to these difficulties, high variability anatomical features are currently analyzed and determined only by trained physicians who can read the images. Another challenge is that there is a shortage of trained physicians relative to the amount of image data generated.  While computer automation may help solve many limitations for human image analysis, which is time consuming and labor intensive, it has been difficult to achieve.

 

To help solve some of these challenges, researchers at the National Institutes of Health Clinical Center (NIHCC) have developed a technology that trains a computer to read and segment certain highly variable images features, such as the pancreas. This analysis is done by employing Holistically-Nested Convolutional Neural Network (HNNs) and deep learning. The resulting biomarkers are far more precise compared to other approaches and outperform current methods for automated image localization and segmentation of high variability image features. The training methods may be generalizable to enable automation of segmentation for many high variability image structures, such as tumors and diseased organs. This advancement has application for improving computer assisted diagnostic capabilities, and disease monitoring and surgical planning abilities for many diseases.

This technology is currently available for licensing and co-development partnership.



Potential Commercial Applications: Competitive Advantages:
  • Computer Assisted Diagnostics
  • Computer assisted disease monitoring
  • Computer assisted surgical planning
 
  • Improved segmentation and automation of highly variable medical image features
  • Reduced physical time in image analysis
  • Data mining and more complete analysis of medical image datasets


Development Stage:

Basic (Target Identification)



Related Invention(s):
E-056-2017


Inventors:

Le Lu (CC)  ➽ more inventions...

Holger Roth (CC)  ➽ more inventions...

Isabelle Nogues (CC)  ➽ more inventions...

Xiaosong Wang (CC)  ➽ more inventions...

Ronald Summers (CC)  ➽ more inventions...

Holger Roth (CC)  ➽ more inventions...

Le Lu (CC)  ➽ more inventions...

Adam Harrison (CC)  ➽ more inventions...


Intellectual Property:
US Provisional Application No. 62/ 345,606
US Provisional Application No. PCT/US17/35974
US Provisional Application No. 62/450,681

Collaboration Opportunity:

Licensing and research collaboration




Licensing Contact:
John Hewes, Ph.D.
Email: John.Hewes@nih.gov
Phone: 240-276-5515

OTT Reference No: E-182-2016
Updated: Jun 23, 2017