New imaging software measures the growth of nodules in patients at risk for lung cancer -
Software medical imaging under development at Rochester Institute of Technology may someday give radiologists a tool for measuring the growth of nodules in patients at risk for lung cancer, the leading cause of cancer death in the United States, according to the Center for Disease Control and Prevention.
Nathan Cahill, an associate professor at RIT's School of Mathematical Sciences, is the creation of algorithms to quantify the growth of lung nodules imaged on computed tomography (CT) scans. The two-year longitudinal study, funded by the National Institutes of Health, compares the existing analyzes of individual patients. The algorithms analyze medical images, to measure changes in the nodules to identify small cancers or if stable avoid unnecessary biopsies, often risky.
simple factors can complicate the comparison of CT scans, creating unnecessary information in medical images, the introduction of artifacts and errors in diagnosis.
"It is not a problem apples to apples reliable correspondence between two images," said Cahill.
differences between the analysis of a single patient can lead to differences in position and inhalation during imaging. A weight gain of 10 pounds between the CT scan may also affect the way the surrounding organs and push against the lungs stretch or compress the nodules.
"Having even 1 or 2 millimeters of difference could throw off estimates of volumes of nodules because the size of the nodules can be 5 mm or more," said Cahill. "The purpose of this project is to develop an algorithm that tries to compensate for all these potential background factors. "
Dr. David Fetzer, a radiologist at the University of Pittsburgh Medical Center and a member of the collaboration, suggested that the clinical problem . Fetzer, a former student of F. Carlson center for Imaging Science RIT Chester, had worked as a student with Maria Helguera, a professor at the center and a team member of Cahill.
"devices modern CT imaging produce hundreds and sometimes thousands of images, "Fetzer said." If a patient is monitored for trouble, as a pulmonary nodule, a radiologist must compare these images visually, mentally compensating for differences such as patient position. Slight changes in technology between the two CT scans can simulate tumor growth, for example. "
radiologists calculate the doubling time of a nodule, or range of time it takes for the size of the nodule to increase twofold. A mass doubling in less than 30 days is growing rapidly and could be an infection, Cahill said. "If it takes years more than one and a half to double, it is more and more slowly and is probably benign. If it is somewhere between what one months and 1.5 years, so it could be malignant and you have to do additional tests and a biopsy. "
Cahill and Kfir Ben Zikri, a doctoral student in the Center for Imaging Science, register, or alignment, backgrounds to create a common frame of reference between the series of images. The process transforms geometrically a three-dimensional image to another and compensates for background information that blurs the edges of nodules, even when the underlying diseases such as emphysema or fibrosis are the intensities in the lighter background .
"Then we can estimate the volumes, which will allow us to more accurately estimate the doubling time and have a better chance to determine whether it is malignant or benign," said Cahill .
technology will be part of the free software libraries provided by Kitware, an open-source software company based in North Carolina that specializes in image medical analysis. Cahill and Ben Zikri work closely with scientists Kitware and Professor Marc Niethammer at the University of North Carolina at Chapel Hill.
Fetzer selects 30 CT scans of patients treated for lung cancer at the University of Pittsburgh Medical Center. The images are scrubbed information on identifying the patient and sent to Cahill and Ben Zikri. Fetzer is clinically verify the algorithmic results.
"With today's technology, we can create the data sets in three dimensions, the image data volumes that can be manipulated and analyzed non-visual way," Fetzer said. "with techniques such as this, we may be able to offset the substantial changes and, hopefully, show more precisely the growth, to assess the aggressiveness or prove the stability of a nodule . This accurate assessment could significantly affect patient care, the cost of lower unnecessary procedures and number, and improve outcomes through early detection of cancer. "
EmoticonEmoticon