Zigang Wang

Reduction of False Positives by Internal Features for Polyp Detection in CT-Based Virtual Colonoscopy

In this paper, we present a computer-aided detection (CAD) method to extract and use internal features to reduce false positive (FP) rate generated by surface-based measures on the inner colon wall in computed tomographic (CT) colonography. Firstly, a new shape description global curvature, which can provide an overall shape description of the colon wall, is introduced to improve the detection of suspicious patches on the colon wall whose geometrical features are similar to that of the colonic polyps. By a ray-driven edge finder, the volume of each detected patch is extracted as a fitted ellipsoid model. Within the ellipsoid model, CT image density distribution is analyzed. Three types of (geometrical, morphological, and textural) internal features are extracted and applied to eliminate the FPs from the detected patches. The presented CAD method was tested by a total of 153 patient datasets in which 45 patients were found with 61 polyps of sizes 4-30 mm by optical colonoscopy. For a 100% detection sensitivity (on polyps), the presented CAD method had an average FPs of 2.68 per patient dataset and eliminated 93.1% of FPs generated by the surface-based measures. The presented CAD method was also evaluated by different polyp sizes. For polyp sizes of 10-30 mm, the method achieved mean number of FPs per dataset of 2.0 with 100% sensitivity. For polyp sizes of 4-10 mm, the method achieved 3.44 FP per dataset with 100% sensitivity.

An Improved Electronic Colon Cleansing Method for Detection of Colonic Polyps by Virtual Colonoscopy

Electronic colon cleansing (ECC) aims to segment the colon lumen from a patient abdominal image acquired using an oral contrast agent for colonic material tagging, so that a virtual colon model can be constructed. Virtual colonoscopy (VC) provides fly-through navigation within the colon model, looking for polyps on the inner surface in a manner analogous to that of fiber optic colonoscopy. We have built an ECC pipeline for a commercial VC navigation system. In this paper, we present an improved ECC method. It is based on a partial-volume (PV) image-segmentation framework, which is derived using the well-established statistical expectation-maximization algorithm. The presented ECC method was evaluated by both visual inspection and computer-aided detection of polyps (CADpolyp) within the cleansed colon lumens obtained using 20 patient datasets. Compared to our previous ECC pipeline, which does not sufficiently consider the PV effect, the method presented in this paper demonstrates improved polyp detection by both visual judgment and CADpolyp measure

Speedup OS-EM image reconstruction by PC graphics card technologies for quantitative SPECT with varying focal-length fan-beam collimation

In the paper, we present a new hardware acceleration method to speedup the ordered-subsets expectation-maximization (OS-EM) algorithm for quantitative SPECT (single photon emission computed tomography) image reconstruction with varying focal-length fan-beam (VFF) collimation. By utilizing the geometrical symmetry of VFF point-spread function (PSF), compensation for object-specific attenuation and system-specific PSF are accelerated using currently available PC video/graphics card technologies. A ten-fold acceleration of quantitative SPECT reconstruction is achieved.

A new partial volume segmentation approach to extract bladder wall for computer-aided detection in virtual cystoscopy

We propose a new partial volume (PV) segmentation scheme to extract bladder wall for computer aided detection (CAD) of bladder lesions using multispectral MR images. Compared with CT images, MR images provide not only a better tissue contrast between bladder wall and bladder lumen, but also the multispectral information. As multispectral images are spatially registered over three-dimensional space, information extracted from them is more valuable than that extracted from each image individually. Furthermore, the intrinsic T1 and T2 contrast of the urine against the bladder wall eliminates the invasive air insufflation procedure. Because the earliest stages of bladder lesion growth tend to develop gradually and migrate slowly from the mucosa into the bladder wall, our proposed PV algorithm quantifies images as percentages of tissues inside each voxel. It preserves both morphology and texture information and provides tissue growth tendency in addition to the anatomical structure. Our CAD system utilizes a multi-scan protocol on dual (full and empty of urine) states of the bladder to extract both geometrical and texture information. Moreover, multi-scan of transverse and coronal MR images eliminates motion artifacts. Experimental results indicate that the presented scheme is feasible towards mass screening and lesion detection for virtual cystoscopy (VC).

An Improved Electronic Colon Cleansing Method for Detection of Polyps by Virtual Colonoscopy

Electronic colon cleansing (ECC) aims to segment the colon lumen from the patient abdominal image acquired with colonic material tagging by oral contrast and other means, so that a virtual colon model can be constructed. Virtual colonoscopy (VC) navigates through the colon model looking for polyps in a similar manner as the fiber optic colonoscopy does. We had built an ECC pipeline for the commercial VC system of Viatronix Inc. In this paper, we present an improved ECC method. It is based on a partial-volume image-segmentation framework, which is derived using the well-established statistical expectation-maximization algorithm. The presented ECC method was evaluated by both visual inspection on the cleansed colon lumens and computer-aided detection of polyps (CADpolyp) using 20 patient datasets. Compared to our previous ECC pipeline, this presented new method demonstrates improvement in both visual judgment and CADpolyp

Optical coherence tomography for noninvasive diagnosis of epithelial cancers.

We summarize our recent progress in the development of the optical coherence tomography (OCT) systems suitable for clinical diagnosis and the preliminary results for in vivo diagnosis of epithelial cancers (e.g., bladder cancers). The endoscopic spectral-domain OCT system allows simultaneous, real-time, cross-sectional OCT images of tissue structure and functions (i.e., local Doppler blood flow) of biological tissue for enhanced diagnosis. A new approach to use spectral demodulation of elastic scattering is discussed for potential cancer grading. The transverse and axial resolutions of the OCT scopes are 12mum and 10mum, respectively. Results of the preliminary clinical studies show that unlike animal carcinogenesis models, bladder cancers in humans are more complicated in terms of epithelial backscattering changes: some lesions exhibit enhanced backscattering; some show reduced scattering owing to complex surface condition changes such as asperities or invaginations induced by tumorigenesis (e.g., papillary transitional cell cancers). Nevertheless, promising results can be provided by incorporating other diagnostic parameters such as changes in local vasculature and urothelial heterogeneity

Computer-aided detection and diagnosis of colon polyps with morphological and texture features

In this paper, we propose a new technique to utilize both the morphological and the texture information of the colon wall for detection of colonic polyps. Firstly this method can quickly identify suspicious patches of the colon wall by employing special local and global geometrical information, different from other methods of utilizing local geometry only. By our edge-detection technology, the growing region of suspected polyps is identified and its internal textures are quantitatively analyzed based on an assumed ellipsoid polyp model. Both the extracted texture and morphological information are then applied to eliminate the false positives from the identified suspicious patches. With all the extracted geometrical, morphological and texture features, this presented computer-aided detection method have demonstrated significant improvement in detection of the colonic polyps for virtual colonoscopy.

Skeleton-based 3D computer-aided detection of colonic polyps

In this paper, we propose a new computer aided detection (CAD) technique to utilize both global and local shape information of the colon wall for detection of colonic polyps. Firstly, the whole colon wall is extracted by our mixture-based image segmentation method. This method uses partial volume percentages to represent the distribution of different materials in each voxel, so it provides the most accurate information on the colon wall, especially the mucosa layer. Local geometrical measure of the colon mucosa layer is defined by the curvature and gradient information extracted from the segmented colon-wall mixture data. Global shape information is provided by applying an improved linear integral convolution operation to the mixture data. The CAD technique was tested on twenty patient datasets. The local geometrical measure extracted from the mixture segmentation represents more accurately the polyp variation than that extracted from conventional label classification, leading to improved detection. The added global shape information further improves the polyp detection.

Feature-Based Texture Display for Detection of Polyps on Flattened Colon Volume

This paper presents a volume-based algorithm to flatten the colon. Based on the flattened colon volume, three different display schemes are adapted to transfer the three-dimensional (3D) flattened colon volume into a 2D image. One display scheme is surface-based rendering, one is volume-based rendering, and the third one is feature-based texture display. These three displays generate not only a traditional flattened-colon surface image, but also a feature-based texture image which can be utilized to characterize and detect the colonic polyps, resulting in a new way to visualize the entire colon

Diagnosis of Biological Tissue Morphology and Function with Endoscopic Optical Coherence Tomography

We present some of the recent technological advances in our MEMS-based endoscopic optical coherence tomography (OCT) system for the enhancement of image fidelity and diagnosis. The endoscopic OCT system permits simultaneous cross-sectional OCT imaging and en face white-light visual guidance as well as fluorescence imaging guidance. The transverse and axial resolutions of the OCT scope are roughly 12 mum and 10 mum, respectively, and the axial resolution can be enhanced to 3 mum if connecting it to our recent custom sub-8 fs Ti:Al2O3 laser. To test the endoscopic OCT system for imaging diagnosis of early epithelial cancers, rat bladder cancer models were used and the results show over 90% sensitivity and specificity. Applications in imaging of bladder functions and engineering tissue growth are demonstrated