Chaijie Duan

Computer-aided detection of colonic polyps with level set-based adaptive convolution in volumetric mucosa to advance CT colonography toward a screening modality

As a promising second reader of computed tomographic colonography (CTC) screening, the computer-aided detection (CAD) of colonic polyps has earned fast growing research interest. In this paper, we present a CAD scheme to automatically detect colonic polyps in CTC images. First, a thick colon wall representation, ie, a volumetric mucosa (VM) with several voxels wide in general, was segmented from CTC images by a partial-volume image segmentation algorithm. Based on the VM, we employed a level set-based adaptive convolution method for calculating the first- and second-order spatial derivatives more accurately to start the geometric analysis. Furthermore, to emphasize the correspondence among different layers in the VM, we introduced a middle-layer enhanced integration along the image gradient direction inside the VM to improve the operation of extracting the geometric information, like the principal curvatures. Initial polyp candidates (IPCs) were then determined by thresholding the geometric measurements. Based on IPCs, several features were extracted for each IPC, and fed into a support vector machine to reduce false positives (FPs). The final detections were displayed in a commercial system to provide second opinions for radiologists. The CAD scheme was applied to 26 patient CTC studies with 32 confirmed polyps by both optical and virtual colonoscopies. Compared to our previous work, all the polyps can be detected successfully with less FPs. At the 100% by polyp sensitivity, the new method yielded 3.5 FPs/dataset.

Volume-Based Features for Detection of Bladder Wall Abnormal Regions via MR Cystography

This paper proposes a framework for detecting the suspected abnormal region of the bladder wall via magnetic resonance (MR) cystography. Volume-based features are used. First, the bladder wall is divided into several layers, based on which a path from each voxel on the inner border to the outer border is found. By using the path length to measure the wall thickness and a bent rate (BR) term to measure the geometry property of the voxels on the inner border, the seed voxels representing the abnormalities on the inner border are determined. Then, by tracing the path from each seed, a weighted BR term is constructed to determine the suspected voxels, which are on the path and inside the bladder wall. All the suspected voxels are grouped together for the abnormal region. This work is significantly different from most of the previous computer-aided bladder tumor detection reports on two aspects. First of all, the T1-weighted MR images are used which give better image contrast and texture information for the bladder wall, comparing with the computed tomography images. Second, while most previous reports detected the abnormalities and indicated them on the reconstructed 3-D bladder model by surface rendering, we further determine the possible region of the abnormality inside the bladder wall. This study aims at a noninvasive procedure for bladder tumor detection and abnormal region delineation, which has the potential for further clinical analysis such as the invasion depth of the tumor and virtual cystoscopy diagnosis. Five datasets including two patients and three volunteers were used to test the presented method, all the tumors were detected by the method, and the overlap rates of the regions delineated by the computer against the experts were measured. The results demonstrated the potential of the method for detecting bladder wall abnormal regions via MR cystography.

An Adaptive Window-Setting Scheme for Segmentation of Bladder Tumor Surface via MR Cystography

This paper proposes an adaptive window-setting scheme for noninvasive detection and segmentation of bladder tumor surface in T_1 -weighted magnetic resonance (MR) images. The inner border of the bladder wall is first covered by a group of ball-shaped detecting windows with different radii. By extracting the candidate tumor windows and excluding the false positive (FP) candidates, the entire bladder tumor surface is detected and segmented by the remaining windows. Different from previous bladder tumor detection methods that are mostly focusing on the existence of a tumor, this paper emphasizes segmenting the entire tumor surface in addition to detecting the presence of the tumor. The presented scheme was validated by ten clinical T1-weighted MR image datasets (five volunteers and five patients). The bladder tumor surfaces and the normal bladder wall inner borders in the ten datasets were covered by 223 and 10 491 windows, respectively. Such a large number of the detecting windows makes the validation statistically meaningful. In the FP reduction step, the best feature combination was obtained by using receiver operating characteristics or ROC analysis. The validation results demonstrated the potential of this presented scheme in segmenting the entire tumor surface with high sensitivity and low FP rate. This study inherits our previous results of automatic segmentation of the bladder wall and will be an important element in our MR-based virtual cystoscopy or MR cystography system.

Bladder Wall Thickness Mapping for Magnetic Resonance Cystography

Clinical studies have shown evidence that the bladder wall thickness is an effective biomarker for bladder abnormalities. Clinical optical cystoscopy, the current gold standard, cannot show the wall thickness. The use of ultrasound by experts may generate some local thickness information, but the information is limited in field-of-view and is user dependent. Recent advances in magnetic resonance (MR) imaging technologies lead MR-based virtual cystoscopy or MR cystography toward a potential alternative to map the wall thickness for the entire bladder. From a high-resolution structural MR volumetric image of the abdomen, a reasonable segmentation of the inner and outer borders of the bladder wall can be achievable. Starting from here, this paper reviews the limitation of a previous distance field-based approach of measuring the thickness between the two borders and then provides a solution to overcome the limitation by an electric field-based strategy. In addition, this paper further investigates a surface-fitting strategy to minimize the discretization errors on the voxel-like borders and facilitate the thickness mapping on the three-dimensional patient-specific bladder model. The presented thickness calculation and mapping were tested on both phantom and human subject datasets. The results are preliminary but very promising with a noticeable improvement over the previous distance field-based approach.

Texture Feature Extraction and Analysis for Polyp Differentiation via Computed Tomography Colonography

Image textures in computed tomography colonography (CTC) have great potential for differentiating non-neoplastic from neoplastic polyps and thus can advance the current CTC detection-only paradigm to a new level with diagnostic capability. However, image textures are frequently compromised, particularly in low-dose CT imaging. Furthermore, texture feature extraction may vary, depending on the polyp spatial orientation variation, resulting in variable results. To address these issues, this study proposes an adaptive approach to extract and analyze the texture features for polyp differentiation. Firstly, derivative (e.g. gradient and curvature) operations are performed on the CT intensity image to amplify the textures with adequate noise control. Then Haralick co-occurrence matrix (CM) is used to calculate texture measures along each of the 13 directions (defined by the first and second order image voxel neighbors) through the polyp volume in the intensity, gradient and curvature images. Instead of taking the mean and range of each CM measure over the 13 directions as the so-called Haralick texture features, Karhunen-Loeve transform is performed to map the 13 directions into an orthogonal coordinate system so that the resulted texture features are less dependent on the polyp orientation variation. These simple ideas for amplifying textures and stabilizing spatial variation demonstrated a significant impact for the differentiating task by experiments using 384 polyp datasets, of which 52 are non-neoplastic polyps and the rest are neoplastic polyps. By the merit of area under the curve of receiver operating characteristic, the innovative ideas achieved differentiation capability of 0.8016, indicating the CTC diagnostic feasibility.

Motion Correction for MR Cystography by an Image Processing Approach

Magnetic resonance (MR) cystography or MR-based virtual cystoscopy is a promising new technology to evaluate the entire bladder in a fully noninvasive manner. It requires the anatomical bladder images be acquired at high spatial resolution and with adequate signal-to-noise ratio (SNR). This often leads to a long-time scan (>5 min) and results in image artifacts due to involuntary bladder motion and deformation. In this paper, we investigated an image-processing approach to mitigate the problem of motion and deformation. Instead of a traditional single long-time scan, six repeated short-time scans (each of approximately 1 min) were acquired for the purpose of shifting bladder motion from intrascan into interscans. Then, the interscan motions were addressed by registering the short-time scans to a selected reference and finally forming a single average motion-corrected image. To evaluate the presented approach, three types of images were generated: 1) the motion-corrected image by registration and average of the short-time scans; 2) the directly averaged image of the short-time scans (without motion correction); and 3) the single image of the corresponding long-time scan. Six experts were asked to blindly score these images in terms of two important aspects: 1) the definition of the bladder wall and 2) the overall expression on the image quality. Statistical analysis on the scores suggested that the best result in both the aspects is achieved by the presented motion-corrected average. Furthermore, the superiority of the motion-corrected average over the other two is statistically significant by the measure of a linear mixed-effect model with p-values <; 0.05. Our findings may facilitate the detection of bladder abnormality in MR cystography by mitigating the motion challenge. The effectiveness of this approach depends on the noise level of acquired short-time scans and the robustness of image registration, and future effort on these two aspects is needed.

Detecting bladder abnormalities based on inter-layer intensity curve for virtual cystoscopy

This paper presents a level set based method for bladder abnormality detection on T1-weighted MR images. First, the bladder wall is segmented by using a coupled level set framework, in which the inner and outer borders of the bladder wall are extracted by two level set functions. Then, the middle layer of the bladder wall is founded and represented by a new level set function. Finally, the new level set function divides the bladder wall into several layers. The inter-layer intensity of all voxels in each layer is sorted in ascending order to generate the inter-layer intensity curve. The results prove the effectiveness of inter-layer intensity curve in indicating the emerging of the bladder abnormalities.

A fast Fourier ptychographic microscope method with biomedical application

Fourier ptychographic microscopy (FPM) is a newly reported techniques that bypasses the SBP barrier of conventional microscope platforms, which gets high-resolution (HR) images with large FOV. FPM uses an LED matrix as the illuminating source of the microscope. Each lighted LED corresponds to a low-resolution (LR) image. An HR image is generated from a set of LR images by FPM. Larger illuminating angle provides higher frequency information for the HR image. Therefore, FPM increases the NA of the low-NA objective lens while maintaining the large FOV. However, the process of FPM is usually time-consuming, since typically hundreds of LR images are recorded and equally involved in the iteration to maintain the quality of reconstruction. In this paper, we proposed a method to accelerate FPM reconstructing process, called Adaptive-FPM. Inspired by the concept of “keyhole imaging” in MRI, we set an energy change threshold in the reconstruction for each LR image to decide whether the image can be skipped in current iteration or not. In this way, some images will be skipped in further iteration, and the total reconstruction time can be reduced. The method was tested by both simulated data and biomedical data, which showed that the new method led to similar results with the original FPM method, while the run-time was reduced a lot.

α-Information-Based Registration of Dynamic Scans for Magnetic Resonance Cystography

To continue our effort on developing magnetic resonance (MR) cystography, we introduce a novel nonrigid 3-D registration method to compensate for bladder wall motion and deformation in dynamic MR scans, which are impaired by relatively low signal-to-noise ratio in each time frame. The registration method is developed on the similarity measure of α-information, which has the potential of achieving higher registration accuracy than the commonly used mutual information (MI) measure for either monomodality or multimodality image registration. The α-information metric was also demonstrated to be superior to both the mean squares and the cross-correlation metrics in multimodality scenarios. The proposed α-registration method was applied for bladder motion compensation via real patient studies, and its effect to the automatic and accurate segmentation of bladder wall was also evaluated. Compared with the prevailing MI-based image registration approach, the presented α-information-based registration was more effective to capture the bladder wall motion and deformation, which ensured the success of the following bladder wall segmentation to achieve the goal of evaluating the entire bladder wall for detection and diagnosis of abnormality.

Detection of colonic polyp candidates with level set-based thickness mapping over the colon wall

Further improvement of computer-aided detection (CADe) of colonic polyps is vital to advance computed tomographic colonography (CTC) toward a screening modality, where the detection of flat polyps is especially challenging because limited image features can be extracted from flat polyps, and the traditional geometric features-based CADe methods usually fail to detect such polyps. In this paper, we present a novel pipeline to automatically detect initial polyp candidates (IPCs), especially flat polyps, from CTC images. First, the colon wall mucosa was extracted via a partial volume segmentation approach as a volumetric layer, where the inner border of colon wall can be obtained by shrinking the volumetric layer using level set based adaptive convolution. Then the outer border of colon wall (or the colon wall serosa) was segmented via a combined implementation of geodesic active contour and Mumford-Shah functional in a coarse-to-fine manner. Finally, the wall thickness was estimated along a unique path between the segmented inner and outer borders with consideration of the volumetric layers and was mapped onto a patient-specific three-dimensional (3D) colon wall model. The IPC detection results can usually be better visualized in a 2D image flattened from the 3D model, where abnormalities were detected by Z-score transformation of the thickness values. The proposed IPC detection approach was validated on 11 patients with 22 CTC scans, and each scan has at least one flat poly annotation. The above presented novel pipeline was effective to detect some flat polyps that were missed by our CADe system while keeping false detections in a relative low level. This preliminary study indicates that the presented pipeline can be incorporated into an existing CADe system to enhance the polyp detection power, especially for flat polyps.