We present a semi-automated approach to comprehensively examine coronary remodeling over the entire length of intravascular ultrasound (IVUS) imaged vessels. Serial measurements at baseline and 12-month follow-up are analyzed rather than static data obtained at a single time point. Every IVUS pullback is segmented automatically, and then reviewed and algorithmically refined by an expert using a computer-aided just-enough-interaction approach. Subsequently, pairs of serial IVUS pullbacks are registered automatically using 3D graph optimization approach. Based on plaque volume increases or decreases over time, pullback frames are divided into two groups — progression and regression. It is shown that plaque progression rates are positively correlated with percent stenosis (PS) indices (p≪0.01) while plaque regression rates are negatively correlated with percent stenosis indices (p≪0.01). Moreover, for the progression group, adventitia area increases in direct relation with the baseline percent stenosis (p=0.007) when PS is less than 50%. Significance of such a correlation is not observed when percent stenosis exceeds 50%. Conversely, for the regression group, change of adventitia area is relatively constant for percent stenosis <50%; but decreases in direct relation with baseline stenosis (p≪0.01) when stenosis > 50%. This strongly suggests that lipid lowering treatment may effectively suppress plaque progression and accelerate plaque regression, especially for larger values of percent stenosis, and further accelerate the corresponding adventitia-remodeling process.
A novel method for simultaneous registration of location and orientation of baseline and follow-up intravascular ultrasound (IVUS) pullbacks is reported. The main idea is to represent the registration problem as a 3D graph optimization problem (finding a minimum-cost path) solvable by dynamic programming. Thus, global optimality of the resulting location and orientation registration is guaranteed according to the employed cost function and node connections. The cost function integrates information related to vessel/plaque morphology, plaque shape and plaque/perivascular image data. The node connections incorporate the prior information about angular twisting between consecutively co-registered IVUS image pairs. Pilot validation of our method is currently available for four pairs of IVUS pullback sequences consisting of 323 IVUS image frames from four patients. Results showed the average location and orientation registration errors were 0.26 mm and 5.2°, respectively. Compared with our previous results, the new method offers significant alignment improvement (p < 0.001).
Reliable segmentation of abnormal nuclei in cervical cytology is of paramount importance in automation-assisted screening techniques. This paper presents a general method for improving the segmentation of abnormal nuclei using a graph-search based approach. More specifically, the proposed method focuses on the improvement of coarse (initial) segmentation. The improvement relies on a transform that maps round-like border in the Cartesian coordinate system into lines in the polar coordinate system. The costs consisting of nucleus-specific edge and region information are assigned to the nodes. The globally optimal path in the constructed graph is then identified by dynamic programming. We have tested the proposed method on abnormal nuclei from two cervical cell image datasets, Herlev and H and E stained liquid-based cytology (HELBC), and the comparative experiments with recent state-of-the-art approaches demonstrate the superior performance of the proposed method.
Spatio-temporal registration of baseline and follow-up intravascular ultrasound (IVUS) pullbacks is of paramount importance in studying the progression/regression of coronary artery disease. Automating these two tasks has the potential to increase productivity when studying large patient populations. Current automated methods are often designed for only one of the two tasks - spatial or temporal. In this paper, we propose an integrated framework which combines the two tasks and employs side-branches to constrain the IVUS pullback registration tasks. For temporal registration, canonical time warping technique optimizes extracted features and weighs cumulative distances. For spatial registration, the search range of cross-correlation based method is constrained by utilizing the angular differences between side-branches. Pilot validation is currently available for ten pairs of IVUS pullback sub-sequences. Results show average spatial and temporal registration errors of 0.49 mm ± 0.51 mm and 5.56° ± 3.35°, respectively, a notable improvement over our previous approach (p < 0.001) in temporal registration. Our method has the potential to improve spatial and temporal correspondence in studies of atherosclerotic vascular disease development using IVUS.
Gestational sac (GS) diameters are commonly measured by routine ultrasound in early pregnancy. However, manually
searching for the standardized plane of GS (SPGS) and measuring the diameters are time-consuming. In this paper, we
develop a three-stage automatic solution for this procedure. In order to precisely and efficiently locate the position of GS
in each frame, a coarse to fine GS detection scheme based on AdaBoost algorithm is explored. Then, an efficient method
based on local context information is introduced to reduce the false positives (FP) generated by the above detection
process. Finally, a database (DB) guided spectral segmentation is proposed to separate GS region from the background
for further diameters measurement. Experiments carried out on 31 videos show that by using the proposed methods, the
number of SPGS searching error is only one, and the average measurement error is 0.059 for the length diameters and
0.083 for the depth diameters.
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.