The MED-SEG™ system, developed by Bartron Medical Imaging LLC, a New Haven, CT-based company, was recently approved by the FDA for use by trained professionals to process images. The system is based on an innovative software program originally developed at NASA's Goddard Space Flight Center in Greenbelt, MD to analyze imagery of Earth. Now, that technology is being applied to aid in the interpretation of mammograms, ultrasounds, and other medical imagery.

“The use of this computer-based technology could minimize human error that occurs when evaluating radiologic films and might allow for earlier detection of abnormalities within the tissues being imaged,” said Dr. Thomas Rutherford, a medical doctor and director of gynecologic oncology at Yale University.

The left image shows an original mammogram before MED-SEG™ processing. The image on the right, with region of interest (white) labeled, shows a mammogram after MED-SEG processing. (Bartron Medical Imaging)

More than 25 years ago, James C. Tilton of NASA’s Goddard Space Flight Center developed an algorithm with the goal of advancing a totally new approach for analyzing digital images, which are made up of thousands of pixels. Like a single piece of a jigsaw puzzle, a pixel often does not provide enough information about where it fits into the overall scene. To overcome the deficiency, Tilton focused on an approach called hierarchical segmentation (HSEG) to develop a software package based on a type of image segmentation that organizes and groups an image’s pixels together at different levels of detail. Tilton’s approach to image segmentation was different than other approaches in that it not only finds region objects, but also groups spatially separated region objects together into region classes.

For example, an Earth satellite image may contain several lakes of different depths. Deep lakes appear dark blue, while shallow lakes are a lighter shade of blue. HSEG first finds each individual lake; then it groups together all shallow lakes into one class and the deeper lakes into another. Because lakes are more similar than they are to trees, grass, roads, buildings, and other objects, the software then groups all lakes together, regardless of their varying colors. As a result, HSEG allows the user to distinguish important features in the scene accurately and quickly.

Since Tilton developed the algorithm, scientists have used it to analyze Earth-imaging data from NASA’s Landsat and Terra spacecraft, using it to improve the accuracy of snow and ice maps produced from the data. Scientists have also used it to find potential locations for archeological digs, the premise being that vegetation covering a long-abandoned human settlement would look different than the surround flora.

“My original concept was geared to Earth science,” Tilton said. “I never thought it would be used for medical imaging.” In fact, he initially was skeptical — until he processed cell images and was able to see details not visible in unprocessed displays of the image. “The cell features stood out real clearly and this made me realize that Barton was onto something.”

Bartron learned of the software through Goddard’s Innovative Partnerships Program (IPP) Office, and in 2003 licensed the patented technology to create a system that would differentiate hard-to-see details in complex medical images.

How it Works

MED-SEG is a software device that receives medical images and data from various imaging sources (including but not limited to CT, MR, US, RF units), computed and direct radiographic devices, and secondary capture devices (scanners, imaging gateways, or imaging sources). Images and data can be stored, communicated, processed, and displayed within the system or across computer networks at distributed locations.

Bartron’s exclusive license of NASA’s HSEG technologies in the medical imaging field allows the company to contribute to the work of doctors who analyze images obtained from computed tomography (CT), magnetic resonance imaging (MRI), ultrasound, radio frequency, and other imaging sources.

“Trained professionals can use the MED-SEG system to separate two-dimensional images into digitally related sections or regions that, after colorization, can be individually labeled by the user,” explained Fitz Walker, president and CEO of Bartron Medical Imaging.

With the MED-SEG system, medical centers will be able to send images via a secure Internet connection to a Bartron data center for processing by the company's imaging application. The data are then sent back to the medical center for use by medical personnel during diagnosis. Bartron has installed the system at the University of Connecticut Health Center, with the possibility of installing evaluation systems at New York University Medical Center, Yale-New Haven Medical Center, and the University of Maryland Medical Center.

Where it Stands

In July 2010, the MED-SEG system received FDA 510(k) clearance to be used by trained professionals — physicians, radiologists, nurses, and medical technicians — to process images. The MED-SEG can be used to process images from various sources such as MRIs, CT scans, X-rays, ultrasounds, and mammograms. These images can be used in radiologists’ reports and communications, but the processed images should not be used for primary image diagnosis.

Through a Cooperative Research and Development Agreement, Tilton worked with Bartron to develop, test, and document a new, three-dimensional version of HSEG, which the company plans to incorporate into the next version of the MED-SEG product.

In the future, Dr. Molly Brewer, a professor with the Division of Gynecologic Oncology, University of Connecticut Health Center, plans to conduct clinical trials with the MED-SEG system. The goal, she said, would be improving mammography as a diagnostic tool for detecting breast cancer.

“One problem with mammograms is they often give a false negative for detecting abnormalities in women’s breasts. Women who either have high breast density or a strong family history of breast cancer are often sent for MRIs, which are costly, very uncomfortable, and have a high false positive rate resulting in many unnecessary biopsies. Neither imaging modality can detect cancers without a significant number of inaccuracies either missing cancer or overcalling cancer,” said Brewer. “In addition, reading these tests relies on detecting differences in density, which is highly subjective. The MED-SEG processes the image, allowing a doctor to see a lot more detail in a more quantitative way. This new software could save patients a lot of money by reducing the number of costly and unnecessary tests.”

Since radiologists use personal judgment to look for differences in density when they read a mammogram, CT scan, or MRI, this process may be subject to human error. Dr. Brewer hopes to use results from the clinical trials to develop an algorithm that can more objectively distinguish cancerous mammogram results from noncancerous results.

More Information

For more information on Bartron’s MED-SEG system, visit .