Invasive cardiac angiography (catheterization) is still the standard in clinical practice for diagnosing coronary artery disease (CAD) but it involves a high amount of risk and cost. New generations of CT scanners can acquire high-quality images of coronary arteries which allow for an accurate identification and delineation of stenoses. Recently, computational fluid dynamics (CFD) simulation has been applied to coronary blood flow using geometric lumen models extracted from CT angiography (CTA). The computed pressure drop at stenoses proved to be indicative for ischemia-causing lesions, leading to non-invasive fractional flow reserve (FFR) derived from CTA. Since the diagnostic value of non-invasive procedures for diagnosing CAD relies on an accurate extraction of the lumen, a precise segmentation of the coronary arteries is crucial. As manual segmentation is tedious, time-consuming and subjective, automatic procedures are desirable. We present a novel fully-automatic method to accurately segment the lumen of coronary arteries in the presence of calcified and non-calcified plaque. Our segmentation framework is based on three main steps: boundary detection, calcium exclusion and surface optimization. A learning-based boundary detector enables a robust lumen contour detection via dense ray-casting. The exclusion of calcified plaque is assured through a novel calcium exclusion technique which allows us to accurately capture stenoses of diseased arteries. The boundary detection results are incorporated into a closed set formulation whose minimization yields an optimized lumen surface. On standardized tests with clinical data, a segmentation accuracy is achieved which is comparable to clinical experts and superior to current automatic methods.
Quantitative analysis of lymphatic function is crucial for understanding the lymphatic system and diagnosing
the associated diseases. Recently, a near-infrared (NIR) fluorescence imaging system is developed for real-time
imaging lymphatic propulsion by intradermal injection of microdose of a NIR fluorophore distal to the
lymphatics of interest. However, the previous analysis software3, 4 is underdeveloped, requiring extensive time
and effort to analyze a NIR image sequence. In this paper, we develop a number of image processing techniques to
automate the data analysis workflow, including an object tracking algorithm to stabilize the subject and remove
the motion artifacts, an image representation named flow map to characterize lymphatic flow more reliably,
and an automatic algorithm to compute lymph velocity and frequency of propulsion. By integrating all these
techniques to a system, the analysis workflow significantly reduces the amount of required user interaction and
improves the reliability of the measurement.
Recently, we demonstrated near-infrared (NIR) fluorescence imaging for quantifying real-time lymphatic propulsion in
humans following intradermal injections of microdose amounts of indocyanine green. However computational methods
for image analysis are underdeveloped, hindering the translation and clinical adaptation of NIR fluorescent lymphatic
imaging. In our initial work we used ImageJ and custom MatLab programs to manually identify lymphatic vessels and
individual propulsion events using the temporal transit of the fluorescent dye. In addition, we extracted the apparent
velocities of contractile propagation and time periods between propulsion events. Extensive time and effort were
required to analyze the 6-8 gigabytes of NIR fluorescent images obtained for each subject. To alleviate this bottleneck,
we commenced development of ALFIA, an integrated software platform which will permit automated, near real-time
analysis of lymphatic function using NIR fluorescent imaging. However, prior to automation, the base algorithms
calculating the apparent velocity and period must be validated to verify that they produce results consistent with the
proof-of-concept programs. To do this, both methods were used to analyze NIR fluorescent images of two subjects and
the number of propulsive events identified, the average apparent velocities, and the average periods for each subject were
compared. Paired Student's t-tests indicate that the differences between their average results are not significant. With
the base algorithms validated, further development and automation of ALFIA can be realized, significantly reducing the
amount of user interaction required, and potentially enabling the near real-time, clinical evaluation of NIR fluorescent
lymphatic imaging.
KEYWORDS: Tumors, Image segmentation, Ultrasonography, Breast, Image processing algorithms and systems, Breast cancer, Computer aided diagnosis and therapy, Detection and tracking algorithms, Databases, Medical imaging
Ultrasonography is a valuable technique for diagnosing breast cancer. Computer-aided tumor detection and
segmentation in ultrasound images can reduce labor cost and streamline clinic workflows. In this paper, we
propose a fully automatic system to detect and segment breast tumors in 2D ultrasound images. Our system,
based on database-guided techniques, learns the knowledge of breast tumor appearance exemplified by expert
annotations. For tumor detection, we train a classifier to discriminate between tumors and their background.
For tumor segmentation, we propose a discriminative graph cut approach, where both the data fidelity and
compatibility functions are learned discriminatively. The performance of the proposed algorithms is demonstrated
on a large set of 347 images, achieving a mean contour-to-contour error of 3.75 pixels with about 4.33 seconds.
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.