Using commercially available software to enhance breast scans done by magnetic resonance imaging (MRI) reduces the number of false positive identifications of malignant tumors and the subsequent need for biopsies, according to a new study.
Teresa Williams, M.D., and colleagues at the Seattle Cancer Care Alliance and the University of Washington Medical Center did a retrospective examination of 154 breast lesions deemed suspicious by radiologists that were only visible on MRI and that had been biopsied under MRI guidance. They compared the findings and recommendations made by radiologists at the time to new findings using computer-aided enhancement (CAE) software to enhance and evaluate the visible response to contrast agents absorbed by breast tissue.
False positives were reduced by 23 percent when CAE was set to its highest enhancement level, according to the study, which is published in the July edition of the journal Radiology. Williams was a medical resident in radiology at the Seattle Cancer Care Alliance (SCCA) when the research was done. She is now a fellow in pediatric radiology at Children's Hospital and Regional Medical Center in Seattle.
"In summary, our findings suggest that CAE has the potential to improve the discrimination of benign and malignant breast MRI lesions," the authors wrote. "We believe that CAE is useful as a tool to supplement the radiologist's subjective interpretation, but should not be relied upon exclusively to guide management."
"There are challenges associated with breast MRI and one is the time it takes to process and evaluate the many images acquired," said Constance Lehman, M.D., corresponding author and director of radiology at the SCCA. "Computer software programs such as the one evaluated in our study can assist us in interpreting breast MRI scans more easily. Our study suggests that the information provided may improve our ability to distinguish between benign and malignant lesions. Currently, MRI scans are used in addition to mammography when radiologists need a better view of tissue they suspect may be malignant. MRI as an adjunct to mammography also is standard practice at the SCCA for women who are at high risk for breast cancer and to examine the other, or contralateral, breast of women who are newly diagnosed.
One particular challenge in breast MRI is the interpretation of the morphology and kinetic features -- the amount of contrast agent absorbed by breast tissue over time -- on multiple imaging series. Typically, a woman will receive one scan without contrast agent and two more after contrast has been administered. One key analysis function performed by CAE is automatic kinetic assessment.
"The detailed CAE lesion kinetic information differs substantially from that obtained by conventional manual placement of a region of interest," the authors wrote. This is because CAE generates detailed data for the entire lesion versus only a portion of the lesion that is highlighted by region-of-placement.
The lesions in the study had been identified and biopsied during 2001-2004 and came from 125 women ages 27-86. They were processed using CADstream™ 3.0, a CAE system developed by Confirma, Inc. of Kirkland, Wash. The presence of CAE threshold enhancement was sensitive for malignancy in 38 of the 41 malignant lesions examined using the software, according to the study. However, the software did not perform perfectly; it failed to confirm the malignancy of the three lesions. "Given the presence of three false-negative lesions, a finding deemed suspicious by the radiologist should be further evaluated regardless of the enhancement features determined by CAE," according to the study.
Williams said she advocates the use of CAE software analysis of MRI scans as an aid to radiologists' interpretations. "The software is already commercially available and it has shown it is useful in reducing the false positive rate of breast MRI," she said.
Summary of how CAE software works
From the journal paper: The CAE software incorporates three MRI series into its calculations: one pre-contrast T1 weighted series, one immediate post-contrast T1 weighted series and one delayed post-contrast T1 weighted series. The program compares pixel signal intensity values on the pre-contrast and immediate post-contrast series. If a pixel value increases above a user specified minimum enhancement threshold such as a 50 percent or 100 percent increase in enhancement, the pixel is said to meet "threshold enhancement."
Once a pixel has been identified as enhancing above the established threshold, the program then compares pixel signal intensity values on the immediate and delayed post-contrast series. If a pixel value on the delayed series decreases by more than 10 percent compared to the immediate post- contrast series, it is color-coded red, indicating a washout pattern of enhancement. If a pixel value increases by more than 10 percent it is color-coded blue, indicating persistent enhancement. If a pixel value does not change in either direction by more than 10 percent it is color-coded green, for plateau enhancement. One of three colors (blue, green, or red) is applied to that pixel based on the delayed enhancement pattern.
This results in a color overlay map that is displayed on each MRI image, indicating regions of threshold enhancement. Areas of threshold enhancement determined by the CAE software algorithm to be "connected" are summed and constitute a lesion. A synopsis of the kinetic enhancement details of the total connected area or lesion is automatically generated.
Materials provided by Fred Hutchinson Cancer Research Center. Note: Content may be edited for style and length.
Cite This Page: