3D visualization of angiography data is an important preprocessing step in diagnosis of vascular disease. This paper
describes an efficient volume rendering method to emphasize feature-rich region (or focus) in the 3D angiography data.
The method takes the input 3D angiography data and computes the focus with user specification or certain feature
extraction algorithms. Then, a distance map is constructed based on the description of the focused region(s). While
rendering the 3D angiography data, the nonlinear ray tracing method is used and the gradient of the distance volume is
applied to guide ray marching. In the result image, the focused region(s) appears larger than in the normal ray-casting
image, while the context (other regions of the volume) can be still preserved in the image (maybe displayed in a shrink
size). This method avoids deforming the original volume to magnify focus regions, which is expensive to compute, thus
improves the performance.
Virtual colonoscopy (VC) is a noninvasivemethod for colonic polyp screening, by reconstructing three-dimensional
models of the colon using computerized tomography (CT). Identifying the residual fluid retained inside the colon
is a major challenge for 3D virtual colonoscopy using fecal tagging CT data. Digital bowel cleansing aims to
segment the colon lumen from a patient abdominal image acquired using an oral contrast agent for colonic material
tagging. After removing the segmented residual fluid, the clean virtual colon model can be constructed
and visualized for screening. We present a novel automatic method for digital cleansing using probability map.
The random walker algorithm is used to generate the probability map for air (inside the colon), soft tissue, and
residual fluid instead of segment colon lumen directly. The probability map is then used to remove residual fluid
from the original CT data. The proposed method was tested using VC study data at National Cancer Institute
at NIH. The performance of our VC system for polyp detection has been improved by providing radiologists
more detail information of the colon wall.
Virtual colonoscopy (VC) is a noninvasive method for colonic polyp screening, by reconstructing three-dimensional
models of the colon using computerized tomography (CT). In virtual colonoscopy fly-through navigation, it is
crucial to generate an optimal camera path for efficient clinical examination. In conventional methods, the centerline
of the colon lumen is usually used as the camera path. In order to extract colon centerline, some time
consuming pre-processing algorithms must be performed before the fly-through navigation, such as colon segmentation,
distance transformation, or topological thinning. In this paper, we present an efficient image-based
path planning algorithm for automated virtual colonoscopy fly-through navigation without the requirement of
any pre-processing. Our algorithm only needs the physician to provide a seed point as the starting camera
position using 2D axial CT images. A wide angle fisheye camera model is used to generate a depth image from
the current camera position. Two types of navigational landmarks, safe regions and target regions are extracted
from the depth images. Camera position and its corresponding view direction are then determined using these
landmarks. The experimental results show that the generated paths are accurate and increase the user comfort
during the fly-through navigation. Moreover, because of the efficiency of our path planning algorithm and
rendering algorithm, our VC fly-through navigation system can still guarantee 30 FPS.
Effective colonoscopic screening for polyps with optical or virtual means requires adequate visualization of the entire colon surface. The purpose of this study is to investigate by simulation the degree of colon surface coverage during a routine optical colonoscopy (OC). To simulate OC, a generic wide angle and fisheye camera model is used to calibrate the fisheye lens of an Olympus endoscope with a field of view of 140 degrees. Then, the colonoscopy procedure is simulated using volume rendering fly-through along the hugging corner path in the retrograde direction. This shortest path is computed using the segmented and cleansed colon CT datasets. A large number of virtual fisheye cameras are placed along the shortest path to simulate the OC. At each camera position, a discrete volumetric ray-casting method is used to determine which triangles can be seen from the camera. Then, the percentage of the covered colon surface of the OC simulation is computed. Surface coverage at this point may serve as a rough estimate of readily visualized mucosa in a standard OC examination. We also compute the percentage of the covered colon surface for the virtual colonoscopy (VC) by placing virtual pinhole cameras on the central path of the colon and flying in only the antegrade direction as well as flying in both antegrade and retrograde directions. Our simulation study reveals that about 23% of the colon surface is missed in the standard OC examination and about 9% of the colon surface is missed in the VC examination when navigating in both directions.
This work utilizes a novel pipeline for the computer-aided detection (CAD) of colonic polyps, assisting radiologists in locating polyps when using a virtual colonoscopy system. Our CAD pipeline automatically detects polyps while reducing the number of false positives (FPs). It integrates volume rendering and conformal colon flattening with texture and shape analysis. The colon is first digitally cleansed, segmented, and extracted from the CT dataset of the abdomen. The colon surface is then mapped to a 2D rectangle using conformal mapping. Using this colon flattening method, the CAD problem is converted from 3D into 2D. The flattened image is rendered using a direct volume rendering of the 3D colon dataset with a translucent transfer function. Suspicious polyps are detected by applying a clustering method on the 2D volume rendered image. The FPs are reduced by analyzing shape and texture features of the suspicious areas detected by the clustering step. Compared with shape-based methods, ours is much faster and much more efficient as it avoids computing curvature and other shape parameters for the whole colon wall. We tested our method with 178 datasets and found it to be 100% sensitive to adenomatous polyps with a low rate of FPs. The CAD results are seamlessly integrated into a virtual colonoscopy system, providing the radiologists with visual cues and likelihood indicators of areas likely to contain polyps, and allowing them to quickly inspect the suspicious areas and further exploit the flattened colon view for easy navigation and bookmark placement.
This paper introduces a video based face verification system. Stereo vision and multiple-related template matching method are used to segment facial region from the background. Facial features are extracted for geometrical normalization and followed by illumination normalization. Faces are represented by normalized face images masking out some corner points. A Support Vector Machine classifier is trained for each person for verification. Experimental results demonstrate the superior performance of this method in complex real environment.
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.