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 segmentation from 2D ultrasound images

Outlining, or segmenting, the prostate is a very important task in the assignment of appropriate therapy and dose for cancer treatment; however, manual outlining is tedious and time-consuming. In this paper, an algorithm is described for semiautomatic segmentation of the prostate from 2D ultrasound images. The algorithm uses model-based initialization and the efficient discrete dynamic contour. Initialization requires the user to select only four points from which the outline of the prostate is estimated using cubic interpolation functions and shape information. The estimated contour is then deformed automatically to better fit the image. The algorithm can easily segment a wide range of prostate images, and contour editing tools are included to handle more difficult cases. The performance of the algorithm with a single user was compared to manual outlining by a single expert observer. The average distance between semiautomatically and manually outlined boundaries was found to be less than 5 pixels (0.63 mm), and the accuracy and sensitivity to area measurements were both over 90%.     

Computer-assisted analysis of transrectal ultrasound images

We have developed a microcomputer based system with an application specific software package which permits the direct digitization and analysis of transrectal ultrasound (TRUS) images. The system is highly flexible and enables access to a wide range of image analysis tools through relatively simple software modifications, which cannot be implemented using a standard ultrasound instrument. We have demonstrated the capability of the system by an analysis of a number of morphometric parameters and by a correlation of these measurements with the presence of prostatic cancer. We found that the measurement of the ratio of the anterior-posterior axis to transverse axis and the presumed circular area ratio (PCAR) were significant predictors of prostatic cancer. The sensitivity of the PCAR measurement was 93%, the specificity was 50%, the positive predictive value was 57%, and the negative predictive value was 91%. The high negative predictive values of these parameters may provide objective criteria to allow for selective biopsy of patients. This system provides researchers with an efficient, economical, and flexible method to aid in the analysis of TRUS images in a quantitative manner.     

A clinical evaluation of contrast-detail analysis for ultrasound images

We report on the reproducibility of human observers' vanishing detection thresholds for visual targets in contrast-detail (C/D) analysis of ultrasound B-mode images. The images used in this study contain visual targets which are circular cross sections of constant-contrast conical structures in the C/D phantom. The vanishing threshold diameters for these targets vary as a function of the perceived size of the imaged target, target-to-background contrast, image noise content, and reproducibility of the decision levels of human observers for repeated observations. Our study indicates that the determination of absolute vanishing threshold diameter values for several targets of different contrast by human observers yields a high degree of error that is not predicted by existing theoretical assumptions based on a static threshold detector. We find that systematic error is introduced by the observers during the course of the experiment and that the levels of sensitivity of the observers differ widely at all times, and increase the amount of total observer error. These results suggest that, due to the large total observer error, C/D analysis may be impractical in a clinical environment, unless there is access to a team of observers specifically and extensively trained in this task. We suggest that a computer-based observer may be more reliable for the objective performance of contrast-detail analysis as a method for evaluating ultrasound image quality and comparison of imaging systems.     

Shape symmetry analysis of breast tumors on ultrasound images

Shape characteristics of malignant and benign breast tumors are significantly different. In this paper, the reflective symmetry of breast tumor shapes on ultrasound images was investigated. A new reflective symmetry measure (RSML) derived from multiscale local area integral invariant was proposed to quantify the shape symmetry of breast tumor, which could be computed directly from the binary mask image without the shape parameterization in terms of arc length. The performance of several symmetry measures for differentiating malignant and benign breast tumors at varying scales was evaluated and compared by receiver operating characteristic (ROC) analysis. RSML with Gaussian kernel at scale 0.04 (related to the maximal diameter) achieved the highest area under the ROC curve (0.85) on the image data of 168 tumors (104 benign and 64 malignant). The experimental results showed that the reflective symmetry of breast tumor shape was capable of providing potential diagnostic information, which could be characterized quantitatively by RSML with the appropriate scale parameter.     

Gallbladder shape extraction from ultrasound images using active contour models

Gallbladder function is routinely assessed using ultrasonographic (USG) examinations. In clinical practice, doctors very often analyse the gallbladder shape when diagnosing selected disorders, e.g. if there are turns or folds of the gallbladder, so extracting its shape from USG images using supporting software can simplify a diagnosis that is often difficult to make. The paper describes two active contour models: the edge-based model and the region-based model making use of a morphological approach, both designed for extracting the gallbladder shape from USG images. The active contour models were applied to USG images without lesions and to those showing specific disease units, namely, anatomical changes like folds and turns of the gallbladder as well as polyps and gallstones. This paper also presents modifications of the edge-based model, such as the method for removing self-crossings and loops or the method of dampening the inflation force which moves nodes if they approach the edge being determined. The user is also able to add a fragment of the approximated edge beyond which neither active contour model will move if this edge is incomplete in the USG image. The modifications of the edge-based model presented here allow more precise results to be obtained when extracting the shape of the gallbladder from USG images than if the morphological model is used.     

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.     

Wavelet based compression of medical ultrasound images using vector quantization

In this paper, an efficient technique for compression of medical ultrasound (US) images is proposed. The technique is based on wavelet transform of the original image combined with vector quantization (VQ) of high-energy subbands using the LBG algorithm. First, we analyse the statistical behaviour of wavelet coefficients in US images across various subbands and scales. The analysis show that most of the image energy is concentrated in one of the detail subband, either in the vertical detail subband (most of the time) or in the horizontal subband. The other two subbands at each decomposition level contribute negligibly to the total image energy. Then, by exploiting this statistical analysis, a low-complexity image coder is designed, which applies VQ only to the highest energy subband while discarding the other detail subbands at each level of decomposition. The coder is tested on a series of abdominal and uterus greyscale US images. The experimental results indicate that the proposed method clearly outperforms the JPEG2000 (Joint Photographers Expert Group) encoder both qualitatively and quantitatively. For example, without using any entropy coder, the proposed method yields a peak signal to noise ratio gain of 0.2 dB to 1.2 dB over JPEG2000 on medical US images.     

基于多特征融合跟踪的微小肺结节识别算法

如何在海量的肺部高分辨率CT(HRCT)序列图片中准确识别微小结节(直径为5～10 mm)一直是肺结节计算机辅助检测(CAD)系统的研究重点和难点。本文提出了一种新的微小肺结节识别算法——多特征融合跟踪算法。该算法在处理一个HRCT序列图片时,首先结合大津法和形态学方法获取每一张CT图的肺实质,再通过基于灰度阈值和改进的模板匹配算法提取感兴趣区域(ROI),接着计算ROI的多个有效特征,然后在整个HRCT序列图片中进行ROI的多特征跟踪和融合,最后根据分类规则识别并标出候选肺结节。实验证明,该算法能准确地检测出微小肺结节,且假阳率较低。     

Technical note: check software for use with trans-rectal ultrasound guided I-125 seed prostate implants

In-house software has been developed to enable the dose distribution of a commercial treatment planning system to be verified prior to permanent trans-rectal ultrasound guided I-125 seed implantation of the prostate. Printouts enabling the required loading pattern to be communicated to other staff groups are also generated. This software can be obtained via the authors and the AAPM software exchange (URL: http://aapm.org/medphys/resources/software/index.htm).     

Processing technique for ultrasound images

Ultrasound images are sometimes difficult to reproduce repeatedly and perfectly when operating a complicated instrument, especially in regard to the amplifier gain. Thus the logarithm-differential processing (l.d.p.) method described here is aimed at an improvement in the uniformity of the clinical information. This paper discusses the use of the time gain control method and the role of a physical model of tissue, for example a parallel interface model, which has been used for the derivation of acoustical parameters from an echo signal. The l.d.p. method has the following advantages: (i) each point in the image corresponds with the local acoustical parameters of the tissue; (ii) the image will be insensitive to the variations in the gain of the amplifier; and (iii) the l.d.p. method is very easy to operate as a real-time system. A set of six clinical photographs is presented showing that a 20 dB variation in the gain of the amplifier may seriously affect the images. However, the processed images are insensitive to the value of amplifier gain.     

Prostate cancer screening

Prostate cancer is a slowly progressing but potentially lethal disease. In order to cure it we must detect it while it remains organ confined. Because of the slow course of the disease, prostate cancer screening trials take a long time to show any benefit and in that time the measurement and interpretation of prostate specific antigen (PSA) concentrations have changed, and biopsy and treatment protocols have also developed. Nevertheless, measuring PSA in the blood remains the main tool we have at hand and improvements have been made but not fully utilised. Improvements in the specificity of PSA include age-related PSA reference limits, free to total PSA ratio and PSA dynamics such as doubling time. Improvements in sensitivity have progressed to defining that we should focus on the 50% of men with PSA concentrations above their population median, as men with PSA below the median are very unlikely to develop or suffer from prostate cancer. Like any medical procedure, men should be informed of the risks and benefits but this should ideally be done in a manner that encourages informed choice based on their own understanding and feelings, rather than informed compliance based on the views of others.     

Prostate cancer]

Carcinoma of the prostate constitutes a major and escalating international health problem. In many developed countries prostate cancer is the most commonly diagnosed malignancy in men, and seems to overtake lung cancer as major cause of cancer mortality. In Japan mortality of the prostate cancer is relatively low, but future incidence and mortality of the prostate cancer will be dramatically increased. Risk factors of the prostate cancer were well known as Western-type lifestyle and diet. Carcinoma of the prostate are detected early by prostatic specific antigen and systematic trans-rectal ultrasonography guided prostatic needle biopsy. Once prostate cancer has been diagnosed in a patient, histologically graded, and staged as accurately as possible, clinicians are duty bound to offer the best advice about treatment options, even though the risks and benefits of competing therapies. Radical prostatectomy and radiation therapy are known as treatment of localized prostate cancer, antiandrogen therapy is known as treatment of advanced prostate cancer. Alternative approaches utilizing, for example microable inhibitors, inhibitor of growth factors and gene therapy also hold exciting promise.     

Automatic needle segmentation in three-dimensional ultrasound images using two orthogonal two-dimensional image projections

In this paper, we describe an algorithm to segment a needle from a three-dimensional (3D) ultrasound image by using two orthogonal two-dimensional (2D) image projections. Not only is the needle more conspicuous in a projected (volume-rendered) image, but its direction in 3D lies in the plane defined by the projection direction and the needle direction in the projected 2D image. Hence, using two such projections, the 3D vector describing the needle direction lies along the intersection of the two corresponding planes. Thus, the task of 3D needle segmentation is reduced to two 2D needle segmentations. For improved accuracy and robustness, we use orthogonal projection directions (both orthogonal to a given a priori estimate of the needle direction), and use volume cropping and Gaussian transfer functions to remove complex background from the 2D projection images. To evaluate our algorithm, we tested it with 3D ultrasound images of agar and turkey breast phantoms. Using a 500 MHz personal computer equipped with a commercial volume-rendering card, we found that our 3D needle segmentation algorithm performed in near real time (about 10 fps) with a root-mean-square accuracy in needle length and endpoint coordinates of better than 0.8 mm, and about 0.5 mm on average, for needles lengths in the 3D image from 4.0 mm to 36.7 mm.     

Detection of breast lesion regions in ultrasound images using wavelets and order statistics

Accurate detection and segmentation of suspicious regions within the complex and irregular tissues of the breast, as depicted with ultrasonic B scans, typically require human analysis and decision making. Tissue characterization methods for classifying suspicious regions often depend on identifying and then accurately segmenting these regions. Motivated by an ultimate goal to automate this critical identification and segmentation step for tissue characterization problems, this work examines ultrasonic signal characteristics between various regions of breast tissue broadly classified as normal tissue and breast lesions. This paper introduces a nonparametric model based on order statistics (OS) estimated from multiresolution (MR) decompositions of energy-normalized subregions. Experimental results demonstrate the classification performance of the OS-based features extracted from the tumor and normal tissue regions in multiple scans from 84 patients, which resulted in a total of 204 tumor regions (from 43 malignant and 161 benign) and 816 normal tissue regions. Performance results indicate that OS-based features achieved an area under the receiver-operator characteristic curve of 91% in the discrimination between breast lesions and surrounding normal tissues.     

Prostate brachytherapy seed identification on post-implant TRUS images

TRUS is a conceptually appealing alternative to CT-based dosimetry, offering the substantial practical advantage of being readily available intraoperatively. To test the feasibility and reliability of seed identification on post-implant TRUS using standard two-dimensional images, ten patients treated with I-125 or Pd-103 brachytherapy were studied. A set of transverse images (6 MHz) were taken immediately following completion of the implant procedure. Original thermal images were sent to four physicians and the sources were identified independently by placing marks on a cellophane overlay, with grids to match the axial TRUS images. The number and type of seed implanted were not revealed to the investigators. Instead, they were instructed to mark the positions of what they would consider, with reasonable certainty, to be seeds. The overlays were then manually compared for source identification and agreement between observers regarding each alleged source. The actual number of implanted seeds ranged from 44 to 108 (median: 60). In contrast, the mean number of seeds allegedly identified per patients ranged from 26 to 82 (median: 43). The average percent of the seeds allegedly identified per patient ranged from 51% to 83% (mean: 74%). The four physician investigators--KW, JS, BH, and GM--identified an alleged median of 90%, 44%, 63%, and 91% of the total seeds, respectively. There were five instances in which investigators alleged more seeds than were actually implanted. The consistency of seed identification among the investigators was evaluated by noting how many investigators identified each bright spot on the images. The percent of bright spots identified by all four investigators ranged from 8% to 33% (median: 20%). Despite considerable interest among some of our clinical and commercial colleagues in developing TRUS-based intraoperative post-implant dosimetry, the use of TRUS-based seed identification for post-implant dosimetry should be viewed with skepticism.