News | July 28, 2008

New CT Algorithm May Cut Treatment Time

July 29, 2008 - Physicians and medical physicists often spend hours drawing lines around tumors and organs in CT images, causing a major bottleneck in cancer treatment.

A new semi-automatic user-interface could reduce the time and fatigue associated with this meticulous task.

Radiation therapy begins with a CT scan in which 100 or so individual images (slices) are combined to create a 3D map of the region around the tumor. During the following segmentation step, all the organs and sensitive tissues must be identified and outlined for each slice, so that the medical physicist can plan a treatment that provides the highest dose to the target, while sparing the surrounding healthy tissue.

The resolution in CT scans is constantly increasing, which means more slices and more time required for segmentation. In addition, moving organs like the lung are starting to be scanned several times to form a time sequence. This can multiply by 10 the number of images an expert must analyze.

To help with this overwhelming load, Yu-chi Hu ([email protected]) and Gig Mageras of the Memorial Sloan-Kettering Cancer Center in New York, NY, along with Michael Grossberg of the City College of New York have developed a computer program that can segment organs with just a small amount of user input. Starting with one CT image, the user makes a crude outline of each organ. The computer takes this rough sketch and plugs it into a statistically-based algorithm, which it then uses to generate contours in subsequent images. The user checks the computer-drawn boundaries and can correct mistakes with tiny brushstrokes on the computer screen. These corrections are reincorporated by the software to better refine the algorithm.

With funding from the NIH, the team tested the user interface on several CT scans and found that on average an image could be segmented in roughly 6 seconds with the computer's help, instead of the 30 seconds or more in the unaided case. The researcher's algorithm correctly identified 98 percent of the image pixels, which was a higher precision than other contour-drawing algorithms that the researchers tested. The group is now planning to put the system into clinical use within 6 to 9 months.

For more information: www.aapm.org

Source: American Association of Physicists in Medicine

Related Content

News | Advanced Visualization | November 13, 2018
Canon Medical Systems USA and Applied Radiology will host a pair of expert-led forums in high-resolution imaging and...
Deaconess Health System Chooses Sectra as Enterprise Imaging Vendor
News | Enterprise Imaging | November 02, 2018
International medical imaging information technology (IT) and cybersecurity company Sectra will install its enterprise...
The OnSight 3D Extremity System captures weight-bearing 3D extremity exams.
Sponsored Content | Whitepapers | Advanced Visualization | October 24, 2018
The OnSight 3D Extremity System captures weight-bearing 3D extremity exams.
Enterprise imaging has been a hot topic in radiology and healthcare information technology (IT) circles for the last several years as medical image acquisition has moved beyond the exclusive purview of radiology.
Feature | Enterprise Imaging | October 03, 2018 | By Jeff Zagoudis
Enterprise imaging has been a hot topic in radiology and healthcare information technology (IT) circles for the last...
Brainlab and Magic Leap Partner in Digital Surgery
News | Advanced Visualization | September 28, 2018
September 28, 2018 — Brainlab announced a strategic development partnership with Florida-based Magic Leap, a develope
EOS Imaging Installs First Site in Mexico
News | Orthopedic Imaging | September 24, 2018
EOS imaging recently announced the first installation of an EOS system in Mexico, the largest Central American market,...
Artificial Intelligence Provides Faster, Clearer MRI Scans

A new artificial-intelligence-based approach to image reconstruction, called AUTOMAP, yields higher quality images from less data, reducing radiation doses for CT and PET and shortening scan times for MRI. Shown here are MR images reconstructed from the same data with conventional approaches, at left, and AUTOMAP, at right. Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital

News | Artificial Intelligence | July 17, 2018
A research team with funding from the National Institute for Biomedical Imaging and Bioengineering (NIBIB) has...
iSchemaView Brings RAPID Imaging Platform to Australia and New Zealand
News | Stroke | July 13, 2018
iSchemaView has signed Diagnostic Imaging Australia (DIA) to be the exclusive distributor for the RAPID cerebrovascular...
3-D Imaging and Computer Modeling Capture Breast Duct Development

An image of a developing mammary duct. Image courtesy of Andrew Ewald.

News | Breast Imaging | June 28, 2018
A team of biologists has joined up with civil engineers to create what is believed to be the first 3-D computer model...
3D Systems Announces On Demand Anatomical Modeling Service
Technology | Medical 3-D Printing | June 18, 2018
3D Systems announced availability of its new On Demand Anatomical Modeling Service. This new service provides a wide...