Edge-guided boundary delineation in prostate ultrasound images.

Accurate detection of prostate boundaries is required in many diagnostic and treatment procedures for prostate disease. In this paper, a new paradigm for guided edge delineation is described, which involves presenting automatically detected prostate edges as a visual guide to the observer, followed by manual editing. This approach enables robust delineation of the prostate boundaries, making it suitable for routine clinical use. The edge-detection algorithm is comprised of three stages. An algorithm called sticks is used to enhance contrast and at the same time reduce speckle in the transrectal ultrasound prostate image. The resulting image is further smoothed using an anisotropic diffusion filter. In the third stage, some basic prior knowledge of the prostate, such as shape and echo pattern, is used to detect the most probable edges describing the prostate. Finally, patient-specific anatomic information is integrated during manual linking of the detected edges. The algorithm was tested on 125 images from 16 patients. The performance of the algorithm was statistically evaluated by employing five expert observers. Based on this study, we found that consistency in prostate delineation increases when automatically detected edges are used as visual guide during outlining, while the accuracy of the detected edges was found to be at least as good as those of the human observers. The use of edge guidance for boundary delineation can also be extended to other applications in medical imaging where poor contrast in the images and the complexity in the anatomy limit the clinical usability of fully automatic edge-detection techniques.

Pubic arch detection in transrectal ultrasound guided prostate cancer therapy.

New biopsy techniques, increased life expectancy, and prostate-specific antigen (PSA) screening have contributed to an increase in the reported incidence of prostate cancer. Among several treatment options available to the patients, transperineal prostate brachytherapy has emerged as a medically successful, cost-effective outpatient procedure for treating localized prostate cancer. Transperineal prostate brachytherapy employs transrectal ultrasound (TRUS) as the primary imaging modality to accurately preplan and subsequently execute the placement of radioactive seeds into the prostate. Under TRUS guidance, a needle (preloaded with radioactive seeds) is inserted through a template guide, through the perineum and into a predetermined prostate target. The pubic arch, formed by the central union of pelvic bones, is a potential barrier to the passage of these needles in the prostate. A critical aspect, therefore, in the planning and execution of the brachytherapy procedure is the accurate assessment of pubic arch interference (PAI) in relation to the prostate. Traditionally, the evaluation of PAI has involved computed tomography correlate scanning or crude subjective evaluations. In this paper, we describe a new method of assessing PAI by detecting the pubic arch via image processing on the TRUS images. The PAI detection (PAID) algorithm first uses a technique known as sticks to selectively enhance the contrast of linear features in ultrasound images. Next, the enhanced image is thresholded via percentile thresholding. Finally, we fit a parabola (a model for the pubic arch) recursively to the thresholded image. Our evaluation result from 15 cases indicates that the algorithm can successfully detect the pubic arch with 90% accuracy. Based on this study, we believe that detecting the pubic arch and assessing PAI can be done practically and more accurately in the clinical setting using TRUS rather than the current available methods.

A methodology for evaluation of boundary detection algorithms on medical images.

Image segmentation is the partition of an image into a set of nonoverlapping regions whose union is the entire image. The image is decomposed into meaningful parts which are uniform with respect to certain characteristics, such as gray level or texture. In this paper, we propose a methodology for evaluating medical image segmentation algorithms wherein the only information available is boundaries outlined by multiple expert observers. In this case, the results of the segmentation algorithm can be evaluated against the multiple observers' outlines. We have derived statistics to enable us to find whether the computer-generated boundaries agree with the observers' hand-outlined boundaries as much as the different observers agree with each other. We illustrate the use of this methodology by evaluating image segmentation algorithms on two different applications in ultrasound imaging. In the first application, we attempt to find the epicardial and endocardial boundaries from cardiac ultrasound images, and in the second application, our goal is to find the fetal skull and abdomen boundaries from prenatal ultrasound images.

Interactive automatic fetal head measurements from ultrasound images using multimedia computer technology.

We have developed a tool to automatically detect inner and outer skull boundaries of a fetal head in ultrasound images. These boundaries are used to measure biparietal diameter (BPD) and head circumference (HC). The algorithm is based on active contour models and takes 32 s on a Sun SparcStation 20/71. A high-performance desktop multimedia system called MediaStation 5000 (MS5000) is used as a model for our future ultrasound subsystem. On the MS5000, the optimized implementation of this algorithm takes 248 ms. The difference (between the computer-measured values on MS5000 and the gold standard) for BPD and HC was 1.43% (sigma = 1.00%) and 1.96% (sigma = 1.96%), respectively. According to our data analysis, no significant differences exist in the BPD and HC measurements made on the MS5000 and those measurements made on the Sun SparcStation 20/71. Reduction in the overall execution time from 32 s to 248 ms will help making this algorithm a practical ultrasound tool for sonographers.

A real-time scan conversion algorithm on commercially available microprocessors.

We have developed a new ultrasound scan conversion algorithm that can be executed very efficiently on modern microprocessors. Our algorithm is designed to handle the address calculations and input and output (I/O) data loading concurrently with the interpolation. The processing unit's computing power can be dedicated to performing pixel interpolations while the other operations are handled by an independent direct memory access (DMA) controller. By making intelligent use of the I/O transfer capabilities of the DMA controller, the algorithm avoids spending the processing unit's valuable computing cycles in address calculations and nonactive pixel blanking. Furthermore, the new approach speeds up the computation by utilizing the ability of superscalar and very long instruction word (VLIW) processors to perform multiple operations in parallel. Our scan conversion algorithm was implemented on a multimedia and imaging system based on the Texas Instruments TMS320C80 Multimedia Video Processor (MVP). Computing cycles are spent only on predeterminable nonzero output pixels. For example, an execution time of 11.4 ms was achieved when there are 101,829 nonzero output pixels. This algorithm demonstrates a substantial improvement over previous scan conversion algorithms, and its optimized implementation enables modern commercially available programmable processors to support scan conversion at video rates.

Automatic fetal head measurements from sonographic images.

RATIONALE AND OBJECTIVES: We designed an image processing technique to automatically measure the biparietal diameter (BPD) and head circumference (HC) from prenatal sonograms. We evaluated the performance of the algorithm by comparing the resulting measurements with those made by experienced sonographers. METHODS: Thirty-five digitized sonograms of the fetal head were obtained during routine imaging. The BPD and HC were automatically computed by detecting the inner and outer boundaries of the fetal skull using the computer vision technique known as the "active contour model." Six experienced sonographers also measured the BPD and HC on these images. RESULTS: The algorithm failed to locate the boundaries in two of the 35 cases. For the remaining cases, the mean absolute difference between the automated measurements and the average of the six observers was 1.4% for BPD and 2.9% for HC. The correlations were .999 for the BPD and .994 for the HC. The computer's measurements were no different from the six observers' measurements than the observers' measurements were from one another. CONCLUSION: The tested algorithm effectively and accurately measures BPD and HC automatically. We are currently in the process of integrating this algorithm into an ultrasound machine.

A multiple active contour model for cardiac boundary detection on echocardiographic sequences.

Tracing of left-ventricular epicardial and endocardial borders on echocardiographic sequences is essential for quantification of cardiac function. The authors designed a method based on an extension of active contour models to detect both epicardial and endocardial borders on short-axis cardiac sequences spanning the entire cardiac cycle. They validated the results by comparing the computer-generated boundaries to the boundaries manually outlined by four expert observers on 44 clinical data sets. The mean boundary distance between the computer-generated boundaries and the manually outlined boundaries was 2.80 mm (sigma=1.28 mm) for the epicardium and 3.61 (sigma=1.68 mm) for the endocardium. These distances were comparable to interobserver distances, which had a mean of 3.79 mm (sigma=1.53 mm) for epicardial borders and 2.67 mm (sigma=0.88 mm) for endocardial borders. The correlation coefficient between the areas enclosed by the computer-generated boundaries and the average manually outlined boundaries was 0.95 for epicardium and 0.91 for endocardium. The algorithm is fairly insensitive to the choice of the initial curve. Thus, the authors have developed an effective and robust algorithm to extract left-ventricular boundaries from echocardiographic sequences.