Medicsight Inc. this week said it has received FDA clearance for Medicsight Lung CAR (computer assisted reader) - an image analysis software tool that assists radiologists in evaluating lesions or nodules found during CT scans of the lung. Lung nodules can indicate early lung cancer, but are common and often difficult to distinguish as benign or malignant.
The "joint-read" software enables the radiologist to review "unfiltered" images side-by-side and simultaneously with software-enhanced regions of interest. Medicsight Lung CAR searches through spiral CT images (up to 600 slices per study) and filters them to highlight nodules that could pose a threat.
Medicsight said the software works by deploying a series of filters against the image data derived from CT scans. These filters aid the radiologist by highlighting areas of the image that contain potential nodules. The software can extract the boundaries of suspect nodules and show them in 3D with a volume measurement.
According to the American Cancer Society, lung cancer is the leading cause of cancer deaths in the United States, outnumbering deaths from breast, prostate, and colon cancer combined. Lung cancer represents 28 percent of all diagnosed cancers, and more than 160,000 Americans are expected to die from it in 2004. The vast majority of lung cancers are diagnosed late in their course: the average five year survival rate for all lung cancers is estimated to be less than 13 percent. If lung cancer is caught before the cancer has spread, patients have much better chances of survival. The five-year survival rate for lung cancer detected early is 70 percent or better.