This work involves the computer-aided diagnosis (CAD) of pulmonary embolism (PE) in contrast-enhanced computed
tomography pulmonary angiography (CTPA). Contrast plays an important role in analyzing and identifying PE in CTPA.
At times the contrast mixing in blood may be insufficient due to several factors such as scanning speed, body weight and
injection duration. This results in a suboptimal study (mixing artifact) due to non-homogeneous enhancement of blood's
opacity. Most current CAD systems are not optimized to detect PE in sub optimal studies. To this effect, we propose new
techniques for CAD to work robustly in both optimal and suboptimal situations.
First, the contrast level at the pulmonary trunk is automatically detected using a landmark detection tool. This
information is then used to dynamically configure the candidate generation (CG) and classification stages of the
algorithm. In CG, a fast method based on tobogganing is proposed which also detects wall-adhering emboli. In addition,
our proposed method correctly encapsulates potential PE candidates that enable accurate feature calculation over the
entire PE candidate. Finally a classifier gating scheme has been designed that automatically switches the appropriate
classifier for suboptimal and optimal studies.
The system performance has been validated on 86 real-world cases collected from different clinical sites. Results
show around 5% improvement in the detection of segmental PE and 6% improvement in lobar and sub segmental PE
with a 40% decrease in the average false positive rate when compared to a similar system without contrast detection.
Advances in multi-detector technology have made CT pulmonary angiography (CTPA) a popular radiological tool for
pulmonary emboli (PE) detection. CTPA provide rich detail of lung anatomy and is a useful diagnostic aid in highlighting
even very small PE. However analyzing hundreds of slices is laborious and time-consuming for the practicing radiologist
which may also cause misdiagnosis due to the presence of various PE look-alike.
Computer-aided diagnosis (CAD) can be a potential second reader in providing key diagnostic information. Since
PE occurs only in vessel arteries, it is important to mark this region of interest (ROI) during CAD preprocessing. In
this paper, we present a new lung and vessel segmentation algorithm for extracting contrast-enhanced vessel ROI in
CTPA. Existing approaches to segmentation either provide only the larger lung area without highlighting the vessels or
is computationally prohibitive.
In this paper, we propose a hybrid lung and vessel segmentation which uses an initial lung ROI and determines the
vessels through a series of refinement steps. We first identify a coarse vessel ROI by finding the "holes" from the lung
ROI. We then use the initial ROI as seed-points for a region-growing process while carefully excluding regions which are
not relevant. The vessel segmentation mask covers 99% of the 259 PE from a real-world set of 107 CTPA. Further, our
algorithm increases the net sensitivity of a prototype CAD system by 5-9% across all PE categories in the training and
validation data sets. The average run-time of algorithm was only 100 seconds on a standard workstation.
Colon cancer is a widespread disease and, according to the American Cancer Society, it is estimated that in 2006
more than 55,000 people will die of colon cancer in the US. However, early detection of colorectal polyps helps
to drastically reduces mortality. Computer-Aided Detection (CAD) of colorectal polyps is a tool that could help
physicians finding such lesions in CT scans of the colon.
In this paper, we present the first phase, candidate generation (CG), of our technique for the detection of
colonic polyp candidate locations in CT colonoscopy. Since polyps typically appear as protrusions on the surface
of the colon, our cutting-plane algorithm identifies all those areas that can be "cut-off" using a plane. The key
observation is that for any protruding lesion there is at least one plane that cuts a fragment off. Furthermore,
the intersection between the plane and the polyp will typically be small and circular. On the other hand, a
plane cannot cut a small circular cross-section from a wall or a fold, due to their concave or elongated paraboloid
morphology, because these structures yield cross-sections that are much larger or non-circular.
The algorithm has been incorporated as part of a prototype CAD system. An analysis on a test set of
more than 400 patients yielded a high per-patient sensitivity of 95% and 90% in clean and tagged preparation
respectively for polyps ranging from 6mm to 20mm in size.
Most methods for classifier design assume that the training samples
are drawn independently and identically from an unknown data
generating distribution (i.i.d.), although this assumption is violated in several real life problems. Relaxing this i.i.d. assumption, we
develop training algorithms for the more realistic situation where
batches or sub-groups of training samples may have internal
correlations, although the samples from different batches may be
considered to be uncorrelated; we also consider the extension to
cases with hierarchical--i.e. higher order--correlation structure
between batches of training samples. After describing efficient
algorithms that scale well to large datasets, we provide some
theoretical analysis to establish their validity. Experimental
results from real-life Computer Aided Detection (CAD) problems
indicate that relaxing the i.i.d. assumption leads to statistically
significant improvements in the accuracy of the learned classifier.
Objective: To investigate the feasibility of laxative-free bowel preparation to relieve the patient stress in colon cleansing for virtual colonoscopy. Materials and Methods: Three different bowel-preparation protocols were investigated by 60 study cases from 35 healthy male volunteers. All the protocols utilize low-residue diet for two days and differ in diet for the third day - the day just prior to image acquisition in the fourth day morning. Protocol Diet-1 utilizes fluid or liquid diet in the third day, Diet-2 utilizes a food kit, and Diet-3 remains the low-residue diet. Oral contrast of barium sulfate (2.1%, 250 ml) was added respectively to the dinner in the second day and the three meals in the third day. Two doses of MD-Gastroview (60 ml) were ingested each in the evening of the third day and in the morning before image acquisition. Images were acquired by a single-slice detector spiral CT (computed tomography) scanner with 5 mm collimation, 1 mm reconstruction, 1.5-2.0:1.0 pitch, 100-150 mA, and 120 kVp after the colons were inflated by CO2. The contrasted colonic residue materials were electronically removed from the CT images by specialized computer-segmentation algorithms. Results: By assumptions that the healthy young volunteers have no polyp and the image resolution is approximately 4 mm, a successful electronic cleansing is defined as “no more than five false positives and no removal of a colon fold part greater than 4 mm” for each study case. The successful rate is 100% for protocol Diet-1, 77% for Diet-2 and 57% for Diet-3. Conclusion: A laxative-free bowel preparation is feasible for virtual colonoscopy.
Objective: To investigate a less stressful bowel preparation for polyp screening by virtual colonoscopy (VC) with follow-up biopsy on the positive findings by optical colonoscopy (OC). Materials and Methods: Fifty-eight volunteers of age older than 40 -- receiving low-residue diet and laxatives of magnesium citrate, bisacodyl tablets and suppository -- were divided into three groups. In Group I, 16 volunteers took three 40cc oral doses of MD-Gastroview with the three meals respectively, the day prior to VC procedure. In Group II, 18 volunteers ingested barium sulfate suspension (2% w/v, 250 cc/dose) at bedtime and in the next day morning of VC. In Group III, 24 volunteers received 60 cc of MD-Gastroview at bedtime and in the next day morning of VC. Following colon inflation with CO2, computer tomography (CT) abdominal images were acquired by a standard single-slice detector-band VC protocol, i.e., 5 mm collimation, 1 mm reconstruction, 1.5-2.0:1.0 pitch, 120 kVp and 100-150 mA. The CT density of the tagged residual fluid was measured. An image segmentation algorithm was applied to remove electronically the residue fluid. Results: The average fluid density was 97 HU for Group I, 221 HU for Group II2, and 599 HU for Group III. These three groups’ density means are significantly different (p < 0.001 one-way ANOVA). After the electronic cleansing, the % of cleansed fluid regions was 5.5%, 16.5% and 93.1% (p<0.0001 Chi square) for these groups respectively. Conclusion: A less-stressful bowel preparation with low residue diet and MD-Gastroview oral contrast is feasible for VC screening with follow-up biopsy on the positive findings by OC.
We present an automatic and robust tagged-residue detection technique using vector quantization based classification. This technique enables electronic cleansing even on poorly tagged datasets, leading to more effective virtual colonoscopy.
In order to reduce the sensitivity towards intensity variation among the tagged residual material, we use a multi-step technique. First, we apply classification using an unsupervised and self-adapting vector quantization algorithm. Then, we sort the resultant classes by their average intensities. We apply thresholding on these classes based on a conservative threshold. This helps us in differentiating soft tissue inside tagged material from poorly tagged region or noise.
Virtual colonoscopy provides a safe, minimal-invasive approach to detect colonic polyps using medical imaging and computer graphics technologies. Residual stool and fluid are problematic for optimal viewing of the colonic mucosa. Electronic cleansing techniques combining bowel preparation, oral contrast agents, and image segmentation were developed to extract the colon lumen from computed tomography (CT) images of the colon. In this paper, we present a new electronic colon cleansing technology, which employs a hidden Markov random filed (MRF) model to integrate the neighborhood information for overcoming the non-uniformity problems within the tagged stool/fluid region. Prior to obtaining CT images, the patient undergoes a bowel preparation. A statistical method for maximum a posterior probability (MAP) was developed to identify the enhanced regions of residual stool/fluid. The method utilizes a hidden MRF Gibbs model to integrate the spatial information into the Expectation Maximization (EM) model-fitting MAP algorithm. The algorithm estimates the model parameters and segments the voxels iteratively in an interleaved manner, converging to a solution where the model parameters and voxel labels are stabilized within a specified criterion. Experimental results are promising.
We present an electronic colon cleansing algorithm using a new segmentation technique based on segmentation rays. These rays are specially designed to analyze the intensity profile as they traverse through the dataset. When this intensity profile matches any of the pre-defined profiles, the rays perform certain task of reconstruction. We use these rays to detect the intersection between air and residual fluid, and between residual fluid and soft-tissue. One of the most important advantages of segmentation rays over other segmentation techniques is the detection of partial volume regions. Segmentation rays can accurately detect partial volume regions and remove them if needed. Once partial volume is eliminated, removal of other unwanted regions (e.g., tagged fluid) is relatively easy. This approach to electronic cleansing is extremely fast as it requires minimal computation.
We propose an interactive electronic biopsy technique for more accurate colon cancer diagnoses by using advanced volume rendering technologies. The volume rendering technique defines a transfer function to map different ranges of sample values of the original volume data to different colors and opacities, so that the interior structure of the polyps can be clearly recognized by human eyes. Specifically, we provide a user- friendly interface for physicians to modify various parameters in the transfer function, so that the physician can interactively change the transfer function to observe the interior structures inside the abnormalities. Furthermore, to speed up the volume rendering procedure, we propose an efficient space-leaping technique by observing that the virtual camera parameters are often fixed when the physician modifies the transfer function. In addition, we provide an important tool to display the original 2D CT image at the current 3D camera position, so that the physician is able to double check the interior structure of a polyp with the density variation in the corresponding CT image for confirmation. Compared with the traditional biopsy in the procedure of optical colonoscopy, our method is more flexible, noninvasive, and therefore without risk.
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.