Prostate boundary segmentation from 2D ultrasound images

Level set contouring for breast tumor in sonography

The echogenicity, echotexture, shape, and contour of a lesion are revealed to be effective sonographic features for physicians to identify a tumor as either benign or malignant. Automatic contouring for breast tumors in sonography may assist physicians without relevant experience, in making correct diagnoses. This study develops an efficient method for automatically detecting contours of breast tumors in sonography. First, a sophisticated preprocessing filter reduces the noise, but preserves the shape and contrast of the breast tumor. An adaptive initial contouring method is then performed to obtain an approximate circular contour of the tumor. Finally, the deformation-based level set segmentation automatically extracts the precise contours of breast tumors from ultrasound (US) images. The proposed contouring method evaluates US images from 118 patients with breast tumors. The contouring results, obtained with computer simulation, reveal that the proposed method always identifies similar contours to those obtained with manual sketching. The proposed method provides robust and fast automatic contouring for breast US images. The potential role of this approach might save much of the time required to sketch a precise contour with very high stability.

Fast prostate segmentation in 3D TRUS images based on continuity constraint using an autoregressive model

In this article a new slice-based 3D prostate segmentation method based on a continuity constraint, implemented as an autoregressive (AR) model is described. In order to decrease the propagated segmentation error produced by the slice-based 3D segmentation method, a continuity constraint was imposed in the prostate segmentation algorithm. A 3D ultrasound image was segmented using the slice-based segmentation method. Then, a cross-sectional profile of the resulting contours was obtained by intersecting the 2D segmented contours with a coronal plane passing through the midpoint of the manually identified rotational axis, which is considered to be the approximate center of the prostate. On the coronal cross-sectional plane, these intersections form a set of radial lines directed from the center of the prostate. The lengths of these radial lines were smoothed using an AR model. Slice-based 3D segmentations were performed in the clockwise and in the anticlockwise directions, where clockwise and anticlockwise are defined with respect to the propagation directions on the coronal view. This resulted in two different segmentations for each 2D slice. For each pair of unmatched segments, in which the distance between the contour generated clockwise and that generated anticlockwise was greater than 4 mm, a method was used to select the optimal contour. Experiments performed using 3D prostate ultrasound images of nine patients demonstrated that the proposed method produced accurate 3D prostate boundaries without manual editing. The average distance between the proposed method and manual segmentation was 1.29 mm. The average intraobserver coefficient of variation (i.e., the standard deviation divided by the average volume) of the boundaries segmented by the proposed method was 1.6%. The average segmentation time of a 352 x 379 x 704 image on a Pentium IV 2.8 GHz PC was 10 s.

Computer-aided diagnosis of prostate cancer with emphasis on ultrasound-based approaches: a review

This paper reviews the state of the art in computer-aided diagnosis of prostate cancer and focuses, in particular, on ultrasound-based techniques for detection of cancer in prostate tissue. The current standard procedure for diagnosis of prostate cancer, i.e., ultrasound-guided biopsy followed by histopathological analysis of tissue samples, is invasive and produces a high rate of false negatives resulting in the need for repeated trials. It is against these backdrops that the search for new methods to diagnose prostate cancer continues. Image-based approaches (such as MRI, ultrasound and elastography) represent a major research trend for diagnosis of prostate cancer. Due to the integration of ultrasound imaging in the current clinical procedure for detection of prostate cancer, we specifically provide a more detailed review of methodologies that use ultrasound RF-spectrum parameters, B-scan texture features and Doppler measures for prostate tissue characterization. We present current and future directions of research aimed at computer-aided detection of prostate cancer and conclude that ultrasound is likely to play an important role in the field.

Boundary delineation in transrectal ultrasound image for prostate cancer

This paper presents a new advanced automatic edge delineation model for the detection and diagnosis of prostate cancer on transrectal ultrasound (TRUS) images. The proposed model is to improve prostate boundary detection system by modifying a set of preprocessing algorithms including tree-structured nonlinear filter (TSF), directional wavelet transforms (DWT) and tree-structured wavelet transform (TSWT). The model consists of a preprocessing module and a segmentation module. The preprocessing module is implemented for noise suppression, image smoothing and boundary enhancement. The active contours model is used in the segmentation module for prostate boundary detection in two-dimensional (2D) TRUS images. Experimental results show that the addition of the preprocessing module improves the accuracy and sensitivity of the segmentation module, compared to the implementation of the segmentation module alone. It is believed that the proposed automatic boundary detection module for the TRUS images is a promising approach, which provides an efficient and robust detection and diagnosis strategy and acts as "second opinion" for the physician's interpretation of prostate cancer.

Prostate volume contouring: a 3D analysis of segmentation using 3DTRUS, CT, and MR

PURPOSE

This study evaluated the reproducibility and modality differences of prostate contouring after brachytherapy implant using three-dimensional (3D) transrectal ultrasound (3DTRUS), T2-weighted magnetic resonance (MR), and computed tomography (CT) imaging.

METHODS AND MATERIALS

Seven blinded observers contoured 10 patients' prostates, 30 day postimplant, on 3DTRUS, MR, and CT images to assess interobserver variability. Randomized images were contoured twice by each observer. We analyzed length and volume measurements and performed a 3D analysis of intra- and intermodality variation.

RESULTS

Average volume ratios were 1.16 for CT/MR, 0.90 for 3DTRUS/MR, and 1.30 for CT/3DTRUS. Overall contouring variability was largest for CT and similar for MR and 3DTRUS. The greatest variability of CT contours occurred at the posterior and anterior portions of the midgland. On MR, overall variability was smaller, with a maximum in the anterior region. On 3DTRUS, high variability occurred in anterior regions of the apex and base, whereas the prostate-rectum interface had the smallest variability. The shape of the prostate on MR was rounder, with the base and apex of similar size, whereas CT contours had broad, flat bases narrowing toward the apex. The average percent of surface area that was significantly different (95% confidence interval) for CT/MR was 4.1%; 3DTRUS/MR, 10.7%; and CT/3DTRUS, 6.3%. The larger variability of CT measurements made significant differences more difficult to detect.

CONCLUSIONS

The contouring of prostates on CT, MR, and 3DTRUS results in systematic differences in the locations of and variability in prostate boundary definition between modalities. MR and 3DTRUS display the smallest variability and the closest correspondence.

Spectral clustering for TRUS images

Background

Identifying the location and the volume of the prostate is important for ultrasound-guided prostate brachytherapy. Prostate volume is also important for prostate cancer diagnosis. Manual outlining of the prostate border is able to determine the prostate volume accurately, however, it is time consuming and tedious. Therefore, a number of investigations have been devoted to designing algorithms that are suitable for segmenting the prostate boundary in ultrasound images. The most popular method is the deformable model (snakes), a method that involves designing an energy function and then optimizing this function. The snakes algorithm usually requires either an initial contour or some points on the prostate boundary to be estimated close enough to the original boundary which is considered a drawback to this powerful method.

Methods

The proposed spectral clustering segmentation algorithm is built on a totally different foundation that doesn't involve any function design or optimization. It also doesn't need any contour or any points on the boundary to be estimated. The proposed algorithm depends mainly on graph theory techniques.

Results

Spectral clustering is used in this paper for both prostate gland segmentation from the background and internal gland segmentation. The obtained segmented images were compared to the expert radiologist segmented images. The proposed algorithm obtained excellent gland segmentation results with 93% average overlap areas. It is also able to internally segment the gland where the segmentation showed consistency with the cancerous regions identified by the expert radiologist.

Conclusion

The proposed spectral clustering segmentation algorithm obtained fast excellent estimates that can give rough prostate volume and location as well as internal gland segmentation without any user interaction.

3D thoracoscopic ultrasound volume measurement validation in an ex vivo and in vivo porcine model of lung tumours

The purpose of this study was to validate the accuracy and reliability of volume measurements obtained using three-dimensional (3D) thoracoscopic ultrasound (US) imaging. Artificial "tumours" were created by injecting a liquid agar mixture into spherical moulds of known volume. Once solidified, the "tumours" were implanted into the lung tissue in both a porcine lung sample ex vivo and a surgical porcine model in vivo. 3D US images were created by mechanically rotating the thoracoscopic ultrasound probe about its long axis while the transducer was maintained in close contact with the tissue. Volume measurements were made by one observer using the ultrasound images and a manual-radial segmentation technique and these were compared with the known volumes of the agar. In vitro measurements had average accuracy and precision of 4.76% and 1.77%, respectively; in vivo measurements had average accuracy and precision of 8.18% and 1.75%, respectively. The 3D thoracoscopic ultrasound can be used to accurately and reproducibly measure "tumour" volumes both in vivo and ex vivo.

Prostate boundary segmentation from ultrasound images using 2D active shape models: optimisation and extension to 3D

Boundary outlining, or segmentation, of the prostate is an important task in diagnosis and treatment planning for prostate cancer. This paper describes an algorithm based on two-dimensional (2D) active shape models (ASM) for semi-automatic segmentation of the prostate boundary from ultrasound images. Optimisation of the 2D ASM for prostatic ultrasound was done first by examining ASM construction and image search parameters. Extension of the algorithm to three-dimensional (3D) segmentation was then done using rotational-based slicing. Evaluation of the 3D segmentation algorithm used distance- and volume-based error metrics to compare algorithm generated boundary outlines to gold standard (manually generated) boundary outlines. Minimum description length landmark placement for ASM construction, and specific values for constraints and image search were found to be optimal. Evaluation of the algorithm versus gold standard boundaries found an average mean absolute distance of 1.09+/-0.49 mm, an average percent absolute volume difference of 3.28+/-3.16%, and a 5x speed increase versus manual segmentation.

Computer technology in detection and staging of prostate carcinoma: A review

After two decades of increasing interest and research activity, computer-assisted diagnostic approaches are reaching the stage where more routine deployment in clinical practice is becoming a possibility [Kruppinski, E.A., 2004. Computer-aided detection in clinical environment: Benefits and challenges for radiologists. Radiology 231, 7-9]. This is particularly the case in the analysis of mammographic images [Helvie, M.A., Hadjiiski, L., Makariou, E., Chan, H.P., Petrick, N., Sahiner, B., Lo, S.C., Freedman, M., Adler, D., Bailey, J., Blane, C., Hoff, D., Hunt, K., Joynt, L., Klein, K., Paramagul, C., Patterson, S.K., Roubidoux, M.A., 2004. Sensitivity of noncommercial computer-aided detection system for mammographic breast cancer detection: pilot clinical trial. Radiology 231, 208-214] and in the detection of pulmonary nodules [Reeves, A.P., Kostis, W.J., 2000. Computer-aided diagnosis for lung cancer. Radiol. Clin. North Am. 38, 497-509]. However, similar approaches can be applied more widely with the promise of increasing clinical utility in other areas. We review how computer-aided approaches may be applied in the diagnosis and staging of prostatic cancer. The current status of computer technology is reviewed, covering artificial neural networks for detection and staging, computerised biopsy simulation and computer-assisted analysis of ultrasound and magnetic resonance images.

Prostate segmentation by feature enhancement using domain knowledge and adaptive region based operations

Estimation of prostate location and volume is essential in determining a dose plan for ultrasound-guided brachytherapy, a common prostate cancer treatment. However, manual segmentation is difficult, time consuming and prone to variability. In this paper, we present a semi-automatic discrete dynamic contour (DDC) model based image segmentation algorithm, which effectively combines a multi-resolution model refinement procedure together with the domain knowledge of the image class. The segmentation begins on a low-resolution image by defining a closed DDC model by the user. This contour model is then deformed progressively towards higher resolution images. We use a combination of a domain knowledge based fuzzy inference system (FIS) and a set of adaptive region based operators to enhance the edges of interest and to govern the model refinement using a DDC model. The automatic vertex relocation process, embedded into the algorithm, relocates deviated contour points back onto the actual prostate boundary, eliminating the need of user interaction after initialization. The accuracy of the prostate boundary produced by the proposed algorithm was evaluated by comparing it with a manually outlined contour by an expert observer. We used this algorithm to segment the prostate boundary in 114 2D transrectal ultrasound (TRUS) images of six patients scheduled for brachytherapy. The mean distance between the contours produced by the proposed algorithm and the manual outlines was 2.70 +/- 0.51 pixels (0.54 +/- 0.10 mm). We also showed that the algorithm is insensitive to variations of the initial model and parameter values, thus increasing the accuracy and reproducibility of the resulting boundaries in the presence of noise and artefacts.

Carotid Artery and Jugular Vein Tracking and Differentiation Using Spatiotemporal Analysis

We have derived and evaluated parameters from ultrasound images of the neck to permit a computer to automatically characterize and differentiate between the carotid artery and jugular vein at image acquisition time during vascular interventions, given manually placed seed points. Our goal is to prevent inadvertent damage to the carotid artery when targeting the jugular vein for catheterization. We used a portable 10 MHz ultrasound system to acquire cross sectional B-mode ultrasound images of these great vessels at 10 fps. An expert user identified the vessels in the first frame by touching the vessels on the screen with his fingertip, and the computer automatically tracked the vessels and calculated a best-fit ellipse for each vessel in each subsequent frame. Vessel location and radii were further analyzed to produce parameters that proved useful for differentiating between the carotid artery and jugular vein. These parameters include relative location of the vessels, distension of the vessel walls, and consistent phase difference between the arterial and venous pulsations as determined by temporal Fourier analysis.

Prostate segmentation in 2D ultrasound images using image warping and ellipse fitting

This paper presents a new algorithm for the semi-automatic segmentation of the prostate from B-mode trans-rectal ultrasound (TRUS) images. The segmentation algorithm first uses image warping to make the prostate shape elliptical. Measurement points along the prostate boundary, obtained from an edge-detector, are then used to find the best elliptical fit to the warped prostate. The final segmentation result is obtained by applying a reverse warping algorithm to the elliptical fit. This algorithm was validated using manual segmentation by an expert observer on 17 midgland, pre-operative, TRUS images. Distance-based metrics between the manual and semi-automatic contours showed a mean absolute difference of 0.67 +/- 0.18 mm, which is significantly lower than inter-observer variability. Area-based metrics showed an average sensitivity greater than 97% and average accuracy greater than 93%. The proposed algorithm was almost two times faster than manual segmentation and has potential for real-time applications.

Ultrasound image segmentation using spectral clustering

Segmentation of ultrasound images is necessary in a variety of clinical applications, but the development of automatic techniques is still an open problem. Spectral clustering techniques have recently become popular for data and image analysis. In particular, image segmentation has been proposed via the normalized cut (NCut) criterion. This article describes an initial investigation to determine the suitability of such segmentation techniques for ultrasound images. The adaptation of the NCut technique to ultrasound is described first. Segmentation is then performed on simulated ultrasound images. Tests are also performed on abdominal and fetal images with the segmentation results compared to manual segmentation. The success of the segmentation on these test cases warrants further research into NCut-based segmentation of ultrasound images.

A coarse-to-fine approach to prostate boundary segmentation in ultrasound images

Background

In this paper a novel method for prostate segmentation in transrectal ultrasound images is presented.

Methods

A segmentation procedure consisting of four main stages is proposed. In the first stage, a locally adaptive contrast enhancement method is used to generate a well-contrasted image. In the second stage, this enhanced image is thresholded to extract an area containing the prostate (or large portions of it). Morphological operators are then applied to obtain a point inside of this area. Afterwards, a Kalman estimator is employed to distinguish the boundary from irrelevant parts (usually caused by shadow) and generate a coarsely segmented version of the prostate. In the third stage, dilation and erosion operators are applied to extract outer and inner boundaries from the coarsely estimated version. Consequently, fuzzy membership functions describing regional and gray-level information are employed to selectively enhance the contrast within the prostate region. In the last stage, the prostate boundary is extracted using strong edges obtained from selectively enhanced image and information from the vicinity of the coarse estimation.

Results

A total average similarity of 98.76%(± 0.68) with gold standards was achieved.

Conclusion

The proposed approach represents a robust and accurate approach to prostate segmentation.

Quantification of carotid plaque volume measurements using 3D ultrasound imaging

An accurate and reliable technique used to quantify carotid plaque volume has practical importance in research and patient management. In this study, we develop and investigate a theoretical description of carotid plaque volume measurements made using three-dimensional (3D) ultrasound (US) images and compare it with experimental results. Multiple observers measured 48 3D US patient images of carotid plaque (13.2 to 544.0 mm(3)) by manual planimetry. Coefficients of variation in the measurement of plaque volume were found to decrease with increasing plaque size for both inter- (90.8 to 3.9%) and intraobserver (70.2 to 3.1%) measurements. Plaque volume measurement variability was found to increase with interslice distance (ISD), while the relative measurement accuracy remained constant for ISDs between 1.0 and 3.0 mm and then decreased. Root-mean-square (RMS) difference between our theoretical description of plaque volume measurement variance and the experimental results was 5.7%. Thus, our results support the clinical utility of measuring carotid plaque volume by manual planimetry noninvasively using 3D US.

Segmentation of the prostate from suprapubic ultrasound images

We present a technique for semiautomated segmentation of human prostates using suprapubic ultrasound (US) images. In this approach, a speckle reducing anisotropic diffusion (SRAD) is applied to enhance the images and the instantaneous coefficient of variation (ICOV) is utilized for edge detection. Segmentation is accomplished via a parametric active contour model in a polar coordinate system that is tailored to the application. The algorithm initially approximates the prostate boundary in two stages. First a primary contour is detected using an elliptical model, followed by a primary contour optimization using an area-weighted mean-difference binary flow geometric snake model. The algorithm was assessed by comparing the computer-derived contours with contours produced manually by three sonographers. The proposed method has application in radiation therapy planning and delivery, as well as in automated volume measurements for ultrasonic diagnosis. The average root mean square discrepancy between computed and manual outlines is less than the inter-observer variability. Furthermore, 76% of the computer-outlined contour is less than 1 sigma manual outline variance away from "true" boundary of prostate. We conclude that the methods developed herein possess acceptable agreement with manually contoured prostate boundaries and that they are potentially valuable tools for radiotherapy treatment planning and verification.

Prostate segmentation algorithm using dyadic wavelet transform and discrete dynamic contour

Knowing the location and the volume of the prostate is important for ultrasound-guided prostate brachytherapy, a commonly used prostate cancer treatment method. The prostate boundary must be segmented before a dose plan can be obtained. However, manual segmentation is arduous and time consuming. This paper introduces a semi-automatic segmentation algorithm based on the dyadic wavelet transform (DWT) and the discrete dynamic contour (DDC). A spline interpolation method is used to determine the initial contour based on four user-defined initial points. The DDC model then refines the initial contour based on the approximate coefficients and the wavelet coefficients generated using the DWT. The DDC model is executed under two settings. The coefficients used in these two settings are derived using smoothing functions with different sizes. A selection rule is used to choose the best contour based on the contours produced in these two settings. The accuracy of the final contour produced by the proposed algorithm is evaluated by comparing it with the manual contour outlined by an expert observer. A total of 114 2D TRUS images taken for six different patients scheduled for brachytherapy were segmented using the proposed algorithm. The average difference between the contour segmented using the proposed algorithm and the manually outlined contour is less than 3 pixels.

Retroacetabular osteolysis: when to operate?

Polyethylene liner exchange for retroacetabular osteolysis should be done before the shell becomes loose. The purpose of this study was to determine the radiographic quantity of osteolysis that will predict impending loosening of the cementless shell. Between 1992 and 2002, 46 cementless shells were revised at our institution for aseptic osteolysis. Radiographs and a computer-assisted technique were used to quantify osteolysis. Implant stability was confirmed intraoperatively. Of 26 stable and 20 loose shells, the average area of osteolysis on anteroposterior radiographs showed no significant difference, whereas lateral radiographs showed a difference. The percentage of shell circumference with associated osteolysis seen on anteroposterior and lateral radiographs showed a significant difference. Diagnostic criterion of 50% shell circumference associated with osteolysis on lateral films has a sensitivity of 0.84 and a specificity of 0.54, and on anteroposterior views, a sensitivity of 1.0 and a specificity 0.27 for predicting shell loosening. Percent of shell circumference with surrounding osteolysis seems to be more predictive of loosening than the area of osteolysis. When 50% of the shell circumference has osteolysis evident on anteroposterior or lateral radiographs, but preferably anteroposterior radiographs, liner exchange should be considered so that the exchange procedure is still possible, rather than allowing the osteolysis to increase and compromise shell fixation.

Template-based finite-element mesh generation from medical images

The finite-element (FE) method is commonly used in biomedical engineering to simulate the behaviour of biological structures because of its ability to model complex shapes in a subject-specific manner. However, generating FE meshes from medical images remains a bottleneck. We present a template-based technique for semi-automatically generating FE meshes which is applicable to prospective studies of individual patients in which FE meshes must be generated from scans of the same structure taken at different points in time to study the effects of disease progression/regression. In this "template-based" meshing approach, the baseline FE (tetrahedral) volume mesh is first manually aligned with the follow-up images. The triangulated surface of the mesh is then automatically deformed to fit the imaged organ boundary. The deformed surface nodes are then smoothed using a Laplacian smoothing algorithm to correct triangle (surface nodes) distortion and thus preserve triangle quality. Finally, the internal mesh nodes are smoothed to correct distorted tetrahedral elements and thus preserve tetrahedral element quality. This template-based approach is shown to be as accurate and precise as the previous technique used by our group, while preserving element quality and volume.

Segmentation of abdominal ultrasound images of the prostate using a priori information and an adapted noise filter

This article discusses a method for the automatic segmentation of trans-abdominal ultrasound images of the prostate. Segmentation begins with the application of a filter to enhance the contours without modifying the image information. It combines adaptive morphological filtering and median filtering to detect the noise-containing regions and smooth them. A heuristic optimization algorithm searches for the contour initialized from a prostate model. The performance of the algorithm was tested by comparing the resulting contours with those obtained by manual segmentation. The average distance between the contours was 2.5 mm and the average coverage index was 93%.

Image-based cardiac gating for three-dimensional intravascular ultrasound imaging

Three-dimensional (3-D) intravascular ultrasound (US), or IVUS, provides valuable insight into the tissue characteristics of the coronary wall and plaque composition. However, artefacts due to cardiac motion and vessel wall pulsation limit the accuracy and variability of coronary lumen and plaque volume measurement in 3-D IVUS images. ECG-gated image acquisition can reduce these artefacts but it requires recording the ECG signal and may increase image acquisition time. The goal of our study was to reconstruct a 3-D IVUS image with negligible cardiac motion and vessel pulsation artefacts, by developing an image-based gating method to track 2-D IVUS images over the cardiac cycle. Our approach involved selecting 2-D IVUS images belonging to the same cardiac phase from an asynchronously-acquired series, by tracking the changing lumen contour over the cardiac cycle. The algorithm was tested with IVUS images of a custom-built coronary vessel phantom and with patient images. The artefact reduction achieved using the image-gating approach was > 86% in the in vitro images and > 80% in the in vivo images in our study. Our study shows that image-based gating of IVUS images provides a useful method for accurate reconstruction of 3-D IVUS images with reduced cardiac motion artefact.

Software for interactive segmentation of the carotid artery from 3D black blood magnetic resonance images

A semiautomatic algorithm for segmenting organ surfaces from 3D medical images is presented in this work. The algorithm is based on a deformable model, and allows the user to initialize the model by combining and molding primitive shapes such as cylinders and spheres to form an initial approximate model of the organ surface. The initial model is automatically deformed to better fit organ boundaries. The algorithm was applied to segment the carotid bifurcation from 3D black blood magnetic resonance (MR) images of 5 subjects. The algorithm-segmented surfaces were compared to surfaces segmented manually by an experienced user. On average, approximately 3 min were required to segment an image using the algorithm, whereas 1h was required for manual segmentation. The average distance between corresponding points on the manually and algorithm-segmented surfaces was 0.37 mm, whereas the average maximum distance was 2.03 mm. Moreover, algorithm-segmented surfaces exhibited less intra-operator variability than those segmented manually.

Watershed segmentation for breast tumor in 2-D sonography

Automatic contouring for breast tumors using medical ultrasound (US) imaging may assist physicians without relevant experience, in making correct diagnoses. This study integrates the advantages of neural network (NN) classification and morphological watershed segmentation to extract precise contours of breast tumors from US images. Textural analysis is employed to yield inputs to the NN to classify ultrasonic images. Autocovariance coefficients specify texture features to classify breasts imaged by US using a self-organizing map (SOM). After the texture features in sonography have been classified, an adaptive preprocessing procedure is selected by SOM output. Finally, watershed transformation automatically determines the contours of the tumor. In this study, the proposed method was trained and tested using images from 60 patients. The results of computer simulations reveal that the proposed method always identified similar contours and regions-of-interest (ROIs) to those obtained by manual contouring (by an experienced physician) of the breast tumor in ultrasonic images. As US imaging becomes more widespread, a functional automatic contouring method is essential and its clinical application is becoming urgent. Such a method provides robust and fast automatic contouring of US images. This study is not to emphasize that the automatic contouring technique is superior to the one undertaken manually. Both automatic and manual contours did not, after all, necessarily result in the same factual pathologic border. In computer-aided diagnosis (CAD) applications, automatic segmentation can save much of the time required to sketch a precise contour, with very high stability.

Robot-assisted 3D-TRUS guided prostate brachytherapy: System integration and validation

Current transperineal prostate brachytherapy uses transrectal ultrasound (TRUS) guidance and a template at a fixed position to guide needles along parallel trajectories. However, pubic arch interference (PAI) with the implant path obstructs part of the prostate from being targeted by the brachytherapy needles along parallel trajectories. To solve the PAI problem, some investigators have explored other insertion trajectories than parallel, i.e., oblique. However, parallel trajectory constraints in current brachytherapy procedure do not allow oblique insertion. In this paper, we describe a robot-assisted, three-dimensional (3D) TRUS guided approach to solve this problem. Our prototype consists of a commercial robot, and a 3D TRUS imaging system including an ultrasound machine, image acquisition apparatus and 3D TRUS image reconstruction, and display software. In our approach, we use the robot as a movable needle guide, i.e., the robot positions the needle before insertion, but the physician inserts the needle into the patient's prostate. In a later phase of our work, we will include robot insertion. By unifying the robot, ultrasound transducer, and the 3D TRUS image coordinate systems, the position of the template hole can be accurately related to 3D TRUS image coordinate system, allowing accurate and consistent insertion of the needle via the template hole into the targeted position in the prostate. The unification of the various coordinate systems includes two steps, i.e., 3D image calibration and robot calibration. Our testing of the system showed that the needle placement accuracy of the robot system at the "patient's" skin position was 0.15 mm+/-0.06 mm, and the mean needle angulation error was 0.07 degrees. The fiducial localization error (FLE) in localizing the intersections of the nylon strings for image calibration was 0.13 mm, and the FLE in localizing the divots for robot calibration was 0.37 mm. The fiducial registration error for image calibration was 0.12 mm and 0.52 mm for robot calibration. The target registration error for image calibration was 0.23 mm, and 0.68 mm for robot calibration. Evaluation of the complete system showed that needles can be used to target positions in agar phantoms with a mean error of 0.79 mm+/-0.32 mm.

Testing and optimization of a semiautomatic prostate boundary segmentation algorithm using virtual operators

Image analysis tasks such as size measurement and landmark-based registration require the user to select control points in an image. The output of such algorithms depends on the choice of control points. Since the choice of points varies from one user to the next, the requirement for user input introduces variability into the output of the algorithm. In order to test and/or optimize such algorithms, it is necessary to assess the multiplicity of outputs generated by the algorithm in response to a large set of inputs; however, the input of data requires substantial time and effort from multiple users. In this paper we describe a method to automate the testing and optimization of algorithms using "virtual operators," which consist of a set of spatial distributions describing how actual users select control points in an image. In order to construct the virtual operator, multiple users must repeatedly select control points in the image on which testing is to be performed. Once virtual operators are generated, control points for initializing the algorithm can be generated from them using a random number generator. Although an initial investment of time is required from the users in order to construct the virtual operator, testing and optimization of the algorithm can be done without further user interaction. We illustrate the construction and use of virtual operators by testing and optimizing our prostate boundary segmentation algorithm. The algorithm requires the user to select four control points on the prostate as input.

Prostate boundary segmentation from 3D ultrasound images

Segmenting, or outlining the prostate boundary is an important task in the management of patients with prostate cancer. In this paper, an algorithm is described for semiautomatic segmentation of the prostate from 3D ultrasound images. The algorithm uses model-based initialization and mesh refinement using an efficient deformable model. Initialization requires the user to select only six points from which the outline of the prostate is estimated using shape information. The estimated outline is then automatically deformed to better fit the prostate boundary. An editing tool allows the user to edit the boundary in problematic regions and then deform the model again to improve the final results. The algorithm requires less than 1 min on a Pentium III 400 MHz PC. The accuracy of the algorithm was assessed by comparing the algorithm results, obtained from both local and global analysis, to the manual segmentations on six prostates. The local difference was mapped on the surface of the algorithm boundary to produce a visual representation. Global error analysis showed that the average difference between manual and algorithm boundaries was -0.20 +/- 0.28 mm, the average absolute difference was 1.19 +/- 0.14 mm, the average maximum difference was 7.01 +/- 1.04 mm, and the average volume difference was 7.16% +/- 3.45%. Variability in manual and algorithm segmentation was also assessed: Visual representations of local variability were generated by mapping variability on the segmentation mesh. The mean variability in manual segmentation was 0.98 mm and in algorithm segmentation was 0.63 mm and the differences of about 51.5% of the points comprising the average algorithm boundary are insignificant (P < or = 0.01) to the manual average boundary.

Prostate boundary detection from ultrasonographic images

OBJECTIVE

Prostate diseases are very common in adult and elderly men, and prostate boundary detection from ultrasonographic images plays a key role in prostate disease diagnosis and treatment. However, because of the poor quality of ultrasonographic images, prostate boundary detection still remains a challenging task. Currently, this task is performed manually, which is arduous and heavily user dependent. To improve the efficiency by automating the boundary detection process, numerous methods have been proposed. We present a review of these methods, aiming to find a good solution that could efficiently detect the prostate boundary on ultrasonographic images.

METHODS

A full description of various methods is beyond the scope of this article; instead, we focus on providing an introduction to the different methods with a discussion of their advantages and disadvantages. Moreover, verification methods for estimating the accuracies of the algorithms reported in the literature are discussed as well.

RESULTS

From the investigation, we summarize several key issues that might be confronted and project possible future research.

CONCLUSIONS

Those model-based methods that minimize user involvement but allow for interactive guidance of experts will likely be most immediately successful.

Semiautomatic three-dimensional segmentation of the prostate using two-dimensional ultrasound images

In this paper, we report on two methods for semiautomatic three-dimensional (3-D) prostate boundary segmentation using 2-D ultrasound images. For each method, a 3-D ultrasound prostate image was sliced into the series of contiguous 2-D images, either in a parallel manner, with a uniform slice spacing of 1 mm, or in a rotational manner, about an axis approximately through the center of the prostate, with a uniform angular spacing of 5 degrees. The segmentation process was initiated by manually placing four points on the boundary of a selected slice, from which an initial prostate boundary was determined. This initial boundary was refined using the Discrete Dynamic Contour until it fit the actual prostate boundary. The remaining slices were then segmented by iteratively propagating this result to an adjacent slice and repeating the refinement, pausing the process when necessary to manually edit the boundary. The two methods were tested with six 3-D prostate images. The results showed that the parallel and rotational methods had mean editing rates of 20% and 14%, and mean (mean absolute) volume errors of -5.4% (6.5%) and -1.7% (3.1%), respectively. Based on these results, as well as the relative difficulty in editing, we conclude that the rotational segmentation method is superior.

Theoretical and experimental quantification of carotid plaque volume measurements made by three-dimensional ultrasound using test phantoms

An accurate technique that exhibits low variability has practical importance for the quantification of carotid plaque volume. Such a technique is necessary to monitor plaque progression or regression that may result in response to nonsurgical therapy. In this study, we investigate the accuracy and variability of plaque volume measurement by three-dimensional ultrasound using vascular plaque phantoms over a range of 68.2 mm3 to 285.5 mm3. The agar plaques maintained a consistent cylindrical geometry with variations in the height, length, and echogenicity. The volume of each plaque was determined by water displacement. The three-dimensional (3D) ultrasound (US) images were acquired with a mechanical scanning system which creates a 3D US Cartesian volume, that was manipulated and viewed in any orientation, from a collection of conventional parallel two-dimensional (2D) US images. The plaque volumes were measured by serial 2D manual planimtery. The mean accuracy in plaque volume measurement was 3.1+/-0.9%. Variability in plaque volume measurement was calculated to be 4.0+/-1.0% and 5.1+/-1.4% for intraobserver and interobserver measurements, respectively. We have also developed a theoretical description for the variance in measurement of plaque volume using manual planimetry. Root-mean-square difference between experimentally and theoretically determined values of plaque volume fractional variance was 9%.

Three-dimensional ultrasound imaging

Ultrasound is an inexpensive and widely used imaging modality for the diagnosis and staging of a number of diseases. In the past two decades, it has benefited from major advances in technology and has become an indispensable imaging modality, due to its flexibility and non-invasive character. In the last decade, research investigators and commercial companies have further advanced ultrasound imaging with the development of 3D ultrasound. This new imaging approach is rapidly achieving widespread use with numerous applications. The major reason for the increase in the use of 3D ultrasound is related to the limitations of 2D viewing of 3D anatomy, using conventional ultrasound. This occurs because: (a) Conventional ultrasound images are 2D, yet the anatomy is 3D, hence the diagnostician must integrate multiple images in his mind. This practice is inefficient, and may lead to variability and incorrect diagnoses. (b) The 2D ultrasound image represents a thin plane at some arbitrary angle in the body. It is difficult to localize the image plane and reproduce it at a later time for follow-up studies. In this review article we describe how 3D ultrasound imaging overcomes these limitations. Specifically, we describe the developments of a number of 3D ultrasound imaging systems using mechanical, free-hand and 2D array scanning techniques. Reconstruction and viewing methods of the 3D images are described with specific examples. Since 3D ultrasound is used to quantify the volume of organs and pathology, the sources of errors in the reconstruction techniques as well as formulae relating design specification to geometric errors are provided. Finally, methods to measure organ volume from the 3D ultrasound images and sources of errors are described.