Recently, the development of multi-row multi-slice CT scanner proves precise measure of whole lung area in short time period. The CT scanner improves spatial resolution along z-axis and time resolution. Therefore, this CT image is effective for diagnosis of lung cancer as well as the other lung lesion, and leads the early detection. The development of a diagnosis support system is expected to diagnose these images.
So far, we have developed a computer-aided diagnosis (CAD) system to automatically detect suspicious regions based on helical CT image. However, the algorithm isn't enough in multi-slice CT images because of two-dimensional algorithm and un-recognizing of the chest structure. This paper presents an algorithm of nodules detection using the three-dimensional (3-D) algorithm and recognizing of the chest structure based on multi-slice CT images, and we show the validity of detection algorithm of isolated nodules using 286 data sets.
Recently, multi-slice helical CT technology was developed. Unlike the conventional helical CT, we can obtain CT images of two or more slices with 1 time of scan. Therefore, we can get many pictures with a clear contrast images and thin slice images in one time of scanning. The nodule is expected to be picture more clearly, and it is expected an high diagnostic ability of screening by the expert physicians. Multi-slice CT is z-axial high-contrast resolution, but the number of images is 10 times the single-slice helical CT. Therefore, the development of a diagnosis support system is expected to diagnose these images. We have developed a computer aided diagnosis (CAD) system to detect the lung cancer from multi-slice CT images. Using the conventional algorithm, it was difficult to detect the ground glass shadow and the nodules in contact with the blood vessel. The purpose of this study is to develop a detection algorithm using the 3-D filter by orientation map of gradient vectors and the 3-D distance transformation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.