Prostate boundary segmentation from 2D ultrasound images

Autonomous Prostate Segmentation in 2D B-Mode Ultrasound Images

Prostate brachytherapy is a treatment for prostate cancer; during the planning of the procedure, ultrasound images of the prostate are taken. The prostate must be segmented out in each of the ultrasound images, and to assist with the procedure, an autonomous prostate segmentation algorithm is proposed. The prostate contouring system presented here is based on a novel superpixel algorithm, whereby pixels in the ultrasound image are grouped into superpixel regions that are optimized based on statistical similarity measures, so that the various structures within the ultrasound image can be differentiated. An active shape prostate contour model is developed and then used to delineate the prostate within the image based on the superpixel regions. Before segmentation, this contour model was fit to a series of point-based clinician-segmented prostate contours exported from conventional prostate brachytherapy planning software to develop a statistical model of the shape of the prostate. The algorithm was evaluated on nine sets of in vivo prostate ultrasound images and compared with manually segmented contours from a clinician, where the algorithm had an average volume difference of 4.49 mL or 10.89%.

Estimation of the Prostate Volume from Abdominal Ultrasound Images by Image-Patch Voting

Estimation of the prostate volume with ultrasound offers many advantages such as portability, low cost, harmlessness, and suitability for real-time operation. Abdominal Ultrasound (AUS) is a practical procedure that deserves more attention in automated prostate-volume-estimation studies. As the experts usually consider automatic end-to-end volume-estimation procedures as non-transparent and uninterpretable systems, we proposed an expert-in-the-loop automatic system that follows the classical prostate-volume-estimation procedures. Our system directly estimates the diameter parameters of the standard ellipsoid formula to produce the prostate volume. To obtain the diameters, our system detects four diameter endpoints from the transverse and two diameter endpoints from the sagittal AUS images as defined by the classical procedure. These endpoints are estimated using a new image-patch voting method to address characteristic problems of AUS images. We formed a novel prostate AUS data set from 305 patients with both transverse and sagittal planes. The data set includes MRI images for 75 of these patients. At least one expert manually marked all the data. Extensive experiments performed on this data set showed that the proposed system results ranged among experts’ volume estimations, and our system can be used in clinical practice.

GENERALIZABLE MULTI-SITE TRAINING AND TESTING OF DEEP NEURAL NETWORKS USING IMAGE NORMALIZATION

The ability of medical image analysis deep learning algorithms to generalize across multiple sites is critical for clinical adoption of these methods. Medical imging data, especially MRI, can have highly variable intensity characteristics across different individuals, scanners, and sites. However, it is not practical to train algorithms with data from all imaging equipment sources at all possible sites. Intensity normalization methods offer a potential solution for working with multi-site data. We evaluate five different image normalization methods on training a deep neural network to segment the prostate gland in MRI. Using 600 MRI prostate gland segmentations from two different sites, our results show that both intra-site and inter-site evaluation is critical for assessing the robustness of trained models and that training with single-site data produces models that fail to fully generalize across testing data from sites not included in the training.

Association of multiparametric MRI quantitative imaging features with prostate cancer gene expression in MRI-targeted prostate biopsies

Standard clinicopathological variables are inadequate for optimal management of prostate cancer patients. While genomic classifiers have improved patient risk classification, the multifocality and heterogeneity of prostate cancer can confound pre-treatment assessment. The objective was to investigate the association of multiparametric (mp)MRI quantitative features with prostate cancer risk gene expression profiles in mpMRI-guided biopsies tissues.Global gene expression profiles were generated from 17 mpMRI-directed diagnostic prostate biopsies using an Affimetrix platform. Spatially distinct imaging areas ('habitats') were identified on MRI/3D-Ultrasound fusion. Radiomic features were extracted from biopsy regions and normal appearing tissues. We correlated 49 radiomic features with three clinically available gene signatures associated with adverse outcome. The signatures contain genes that are over-expressed in aggressive prostate cancers and genes that are under-expressed in aggressive prostate cancers. There were significant correlations between these genes and quantitative imaging features, indicating the presence of prostate cancer prognostic signal in the radiomic features. Strong associations were also found between the radiomic features and significantly expressed genes. Gene ontology analysis identified specific radiomic features associated with immune/inflammatory response, metabolism, cell and biological adhesion. To our knowledge, this is the first study to correlate radiogenomic parameters with prostate cancer in men with MRI-guided biopsy.

Automated localization and segmentation techniques for B-mode ultrasound images: A review

B-mode ultrasound imaging is used extensively in medicine. Hence, there is a need to have efficient segmentation tools to aid in computer-aided diagnosis, image-guided interventions, and therapy. This paper presents a comprehensive review on automated localization and segmentation techniques for B-mode ultrasound images. The paper first describes the general characteristics of B-mode ultrasound images. Then insight on the localization and segmentation of tissues is provided, both in the case in which the organ/tissue localization provides the final segmentation and in the case in which a two-step segmentation process is needed, due to the desired boundaries being too fine to locate from within the entire ultrasound frame. Subsequenly, examples of some main techniques found in literature are shown, including but not limited to shape priors, superpixel and classification, local pixel statistics, active contours, edge-tracking, dynamic programming, and data mining. Ten selected applications (abdomen/kidney, breast, cardiology, thyroid, liver, vascular, musculoskeletal, obstetrics, gynecology, prostate) are then investigated in depth, and the performances of a few specific applications are compared. In conclusion, future perspectives for B-mode based segmentation, such as the integration of RF information, the employment of higher frequency probes when possible, the focus on completely automatic algorithms, and the increase in available data are discussed.

Towards ultrasound-guided adaptive radiotherapy for cervical cancer: Evaluation of Elekta's semiautomated uterine segmentation method on 3D ultrasound images

PURPOSE

3D ultrasound (US) images of the uterus may be used to adapt radiotherapy (RT) for cervical cancer patients based on changes in daily anatomy. This requires accurate on-line segmentation of the uterus. The aim of this work was to assess the accuracy of Elekta's "Assisted Gyne Segmentation" (AGS) algorithm in semi-automatically segmenting the uterus on 3D transabdominal ultrasound images by comparison with manual contours.

MATERIALS & METHODS

Nine patients receiving RT for cervical cancer were imaged with the 3D Clarity® transabdominal probe at RT planning, and 1 to 7 times during treatment. Image quality was rated from unusable (0)-excellent (3). Four experts segmented the uterus (defined as the uterine body and cervix) manually and using AGS on images with a ranking > 0. Pairwise analysis between manual contours was evaluated to determine interobserver variability. The accuracy of the AGS method was assessed by measuring its agreement with manual contours via pairwise analysis.

RESULTS

35/44 images acquired (79.5%) received a ranking > 0. For the manual contour variation, the median [interquartile range (IQR)] distance between centroids (DC) was 5.41 [5.0] mm, the Dice similarity coefficient (DSC) was 0.78 [0.11], the mean surface-to-surface distance (MSSD) was 3.20 [1.8] mm, and the uniform margin of 95% (UM95) was 4.04 [5.8] mm. There was no correlation between image quality and manual contour agreement. AGS failed to give a result in 19.3% of cases. For the remaining cases, the level of agreement between AGS contours and manual contours depended on image quality. There were no significant differences between the AGS segmentations and the manual segmentations on the images that received a quality rating of 3. However, the AGS algorithm had significantly worse agreement with manual contours on images with quality ratings of 1 and 2 compared with the corresponding interobserver manual variation. The overall median [IQR] DC, DSC, MSSD, and UM95 between AGS and manual contours was 5.48 [5.45] mm, 0.77 [0.14], 3.62 [2.7] mm, and 5.19 [8.1] mm, respectively.

CONCLUSIONS

The AGS tool was able to represent uterine shape of cervical cancer patients in agreement with manual contouring in cases where the image quality was excellent, but not in cases where image quality was degraded by common artifacts such as shadowing and signal attenuation. The AGS tool should be used with caution for adaptive RT purposes, as it is not reliable in accurately segmenting the uterus on 'good' or 'poor' quality images. The interobserver agreement between manual contours of the uterus drawn on 3D US was consistent with results of similar studies performed on CT and MRI images.

Learning Non-rigid Deformations for Robust, Constrained Point-based Registration in Image-Guided MR-TRUS Prostate Intervention

Accurate and robust non-rigid registration of pre-procedure magnetic resonance (MR) imaging to intra-procedure trans-rectal ultrasound (TRUS) is critical for image-guided biopsies of prostate cancer. Prostate cancer is one of the most prevalent forms of cancer and the second leading cause of cancer-related death in men in the United States. TRUS-guided biopsy is the current clinical standard for prostate cancer diagnosis and assessment. State-of-the-art, clinical MR-TRUS image fusion relies upon semi-automated segmentations of the prostate in both the MR and the TRUS images to perform non-rigid surface-based registration of the gland. Segmentation of the prostate in TRUS imaging is itself a challenging task and prone to high variability. These segmentation errors can lead to poor registration and subsequently poor localization of biopsy targets, which may result in false-negative cancer detection. In this paper, we present a non-rigid surface registration approach to MR-TRUS fusion based on a statistical deformation model (SDM) of intra-procedural deformations derived from clinical training data. Synthetic validation experiments quantifying registration volume of interest overlaps of the PI-RADS parcellation standard and tests using clinical landmark data demonstrate that our use of an SDM for registration, with median target registration error of 2.98 mm, is significantly more accurate than the current clinical method. Furthermore, we show that the low-dimensional SDM registration results are robust to segmentation errors that are not uncommon in clinical TRUS data.

Segmentation of prostate from ultrasound images using level sets on active band and intensity variation across edges

PURPOSE

In this paper, the authors propose a novel efficient method to segment ultrasound images of the prostate with weak boundaries. Segmentation of the prostate from ultrasound images with weak boundaries widely exists in clinical applications. One of the most typical examples is the diagnosis and treatment of prostate cancer. Accurate segmentation of the prostate boundaries from ultrasound images plays an important role in many prostate-related applications such as the accurate placement of the biopsy needles, the assignment of the appropriate therapy in cancer treatment, and the measurement of the prostate volume.

METHODS

Ultrasound images of the prostate are usually corrupted with intensity inhomogeneities, weak boundaries, and unwanted edges, which make the segmentation of the prostate an inherently difficult task. Regarding to these difficulties, the authors introduce an active band term and an edge descriptor term in the modified level set energy functional. The active band term is to deal with intensity inhomogeneities and the edge descriptor term is to capture the weak boundaries or to rule out unwanted boundaries. The level set function of the proposed model is updated in a band region around the zero level set which the authors call it an active band. The active band restricts the authors' method to utilize the local image information in a banded region around the prostate contour. Compared to traditional level set methods, the average intensities inside∖outside the zero level set are only computed in this banded region. Thus, only pixels in the active band have influence on the evolution of the level set. For weak boundaries, they are hard to be distinguished by human eyes, but in local patches in the band region around prostate boundaries, they are easier to be detected. The authors incorporate an edge descriptor to calculate the total intensity variation in a local patch paralleled to the normal direction of the zero level set, which can detect weak boundaries and avoid unwanted edges in the ultrasound images.

RESULTS

The efficiency of the proposed model is demonstrated by experiments on real 3D volume images and 2D ultrasound images and comparisons with other approaches. Validation results on real 3D TRUS prostate images show that the authors' model can obtain a Dice similarity coefficient (DSC) of 94.03% ± 1.50% and a sensitivity of 93.16% ± 2.30%. Experiments on 100 typical 2D ultrasound images show that the authors' method can obtain a sensitivity of 94.87% ± 1.85% and a DSC of 95.82% ± 2.23%. A reproducibility experiment is done to evaluate the robustness of the proposed model.

CONCLUSIONS

As far as the authors know, prostate segmentation from ultrasound images with weak boundaries and unwanted edges is a difficult task. A novel method using level sets with active band and the intensity variation across edges is proposed in this paper. Extensive experimental results demonstrate that the proposed method is more efficient and accurate.

Prostate cancer radiomics and the promise of radiogenomics

Prostate cancer exhibits intra-tumoral heterogeneity that we hypothesize to be the leading confounding factor contributing to the underperformance of the current pre-treatment clinical-pathological and genomic assessment. These limitations impose an urgent need to develop better computational tools to identify men with low risk of prostate cancer versus others that may be at risk for developing metastatic cancer. The patient stratification will directly translate to patient treatments, wherein decisions regarding active surveillance or intensified therapy are made. Multiparametric MRI (mpMRI) provides the platform to investigate tumor heterogeneity by mapping the individual tumor habitats. We hypothesize that quantitative assessment (radiomics) of these habitats results in distinct combinations of descriptors that reveal regions with different physiologies and phenotypes. Radiogenomics, a discipline connecting tumor morphology described by radiomic and its genome described by the genomic data, has the potential to derive "radio phenotypes" that both correlate to and complement existing validated genomic risk stratification biomarkers. In this article we first describe the radiomic pipeline, tailored for analysis of prostate mpMRI, and in the process we introduce our particular implementations of radiomics modules. We also summarize the efforts in the radiomics field related to prostate cancer diagnosis and assessment of aggressiveness. Finally, we describe our results from radiogenomic analysis, based on mpMRI-Ultrasound (MRI-US) biopsies and discuss the potential of future applications of this technique. The mpMRI radiomics data indicate that the platform would significantly improve the biopsy targeting of prostate habitats through better recognition of indolent versus aggressive disease, thereby facilitating a more personalized approach to prostate cancer management. The expectation to non-invasively identify habitats with high probability of housing aggressive cancers would result in directed biopsies that are more informative and actionable. Conversely, providing evidence for lack of disease would reduce the incidence of non-informative biopsies. In radiotherapy of prostate cancer, dose escalation has been shown to reduce biochemical failure. Dose escalation only to determinate prostate habitats has the potential to improve tumor control with less toxicity than when the entire prostate is dose escalated.

Evaluation of uterine ultrasound imaging in cervical radiotherapy; a comparison of autoscan and conventional probe

OBJECTIVE

In cervical radiotherapy, it is essential that the uterine position is correctly determined prior to treatment delivery. The aim of this study was to evaluate an autoscan ultrasound (A-US) probe, a motorized transducer creating three-dimensional (3D) images by sweeping, by comparing it with a conventional ultrasound (C-US) probe, where manual scanning is required to acquire 3D images.

METHODS

Nine healthy volunteers were scanned by seven operators, using the Clarity(®) system (Elekta, Stockholm, Sweden). In total, 72 scans, 36 scans from the C-US and 36 scans from the A-US probes, were acquired. Two observers delineated the uterine structure, using the software-assisted segmentation in the Clarity workstation. The data of uterine volume, uterine centre of mass (COM) and maximum uterine lengths, in three orthogonal directions, were analyzed.

RESULTS

In 53% of the C-US scans, the whole uterus was captured, compared with 89% using the A-US. F-test on 36 scans demonstrated statistically significant differences in interobserver COM standard deviation (SD) when comparing the C-US with the A-US probe for the inferior-superior (p < 0.006), left-right (p < 0.012) and anteroposterior directions (p < 0.001). The median of the interobserver COM distance (Euclidean distance for 36 scans) was reduced from 8.5 (C-US) to 6.0 mm (A-US). An F-test on the 36 scans showed strong significant differences (p < 0.001) in the SD of the Euclidean interobserver distance when comparing the C-US with the A-US scans. The average Dice coefficient when comparing the two observers was 0.67 (C-US) and 0.75 (A-US). The predictive interval demonstrated better interobserver delineation concordance using the A-US probe.

CONCLUSION

The A-US probe imaging might be a better choice of image-guided radiotherapy system for correcting for daily uterine positional changes in cervical radiotherapy.

ADVANCES IN KNOWLEDGE

Using a novel A-US probe might reduce the uncertainty in interoperator variability during ultrasound scanning.

Fully automatic prostate segmentation from transrectal ultrasound images based on radial bas-relief initialization and slice-based propagation

Prostate segmentation from transrectal ultrasound (TRUS) images plays an important role in the diagnosis and treatment planning of prostate cancer. In this paper, a fully automatic slice-based segmentation method was developed to segment TRUS prostate images. The initial prostate contour was determined using a novel method based on the radial bas-relief (RBR) method, and a false edge removal algorithm proposed here in. 2D slice-based propagation was used in which the contour on each image slice was deformed using a level-set evolution model, which was driven by edge-based and region-based energy fields generated by dyadic wavelet transform. The optimized contour on an image slice propagated to the adjacent slice, and subsequently deformed using the level-set model. The propagation continued until all image slices were segmented. To determine the initial slice where the propagation began, the initial prostate contour was deformed individually on each transverse image. A method was developed to self-assess the accuracy of the deformed contour based on the average image intensity inside and outside of the contour. The transverse image on which highest accuracy was attained was chosen to be the initial slice for the propagation process. Evaluation was performed for 336 transverse images from 15 prostates that include images acquired at mid-gland, base and apex regions of the prostates. The average mean absolute difference (MAD) between algorithm and manual segmentations was 0.79±0.26mm, which is comparable to results produced by previously published semi-automatic segmentation methods. Statistical evaluation shows that accurate segmentation was not only obtained at the mid-gland, but also at the base and apex regions.

3D Transrectal Ultrasound (TRUS) Prostate Segmentation Based on Optimal Feature Learning Framework

We propose a 3D prostate segmentation method for transrectal ultrasound (TRUS) images, which is based on patch-based feature learning framework. Patient-specific anatomical features are extracted from aligned training images and adopted as signatures for each voxel. The most robust and informative features are identified by the feature selection process to train the kernel support vector machine (KSVM). The well-trained SVM was used to localize the prostate of the new patient. Our segmentation technique was validated with a clinical study of 10 patients. The accuracy of our approach was assessed using the manual segmentations (gold standard). The mean volume Dice overlap coefficient was 89.7%. In this study, we have developed a new prostate segmentation approach based on the optimal feature learning framework, demonstrated its clinical feasibility, and validated its accuracy with manual segmentations.

LEARNING NONRIGID DEFORMATIONS FOR CONSTRAINED POINT-BASED REGISTRATION FOR IMAGE-GUIDED MR-TRUS PROSTATE INTERVENTION

This paper presents and validates a low-dimensional nonrigid registration method for fusing magnetic resonance imaging (MRI) and trans-rectal ultrasound (TRUS) in image-guided prostate biopsy. Prostate cancer is one of the most prevalent forms of cancer and the second leading cause of cancer-related death in men in the United States. Conventional clinical practice uses TRUS to guide prostate biopsies when there is a suspicion of cancer. Pre-procedural MRI information can reveal lesions and may be fused with intra-procedure TRUS imaging to provide patient-specific, localization of lesions for targeting. The state-of-the-art MRI-TRUS nonrigid image fusion process relies upon semi-automated segmentation of the prostate in both the MRI and TRUS images. In this paper, we develop a fast, automated nonrigid registration approach to MRI-TRUS fusion based on a statistical deformation model of intra-procedural deformations derived from a clinical sample.

Three-dimensional prostate segmentation using level set with shape constraint based on rotational slices for 3D end-firing TRUS guided biopsy

PURPOSE

Prostate segmentation is an important step in the planning and treatment of 3D end-firing transrectal ultrasound (TRUS) guided prostate biopsy. In order to improve the accuracy and efficiency of prostate segmentation in 3D TRUS images, an improved level set method is incorporated into a rotational-slice-based 3D prostate segmentation to decrease the accumulated segmentation errors produced by the slice-by-slice segmentation method.

METHODS

A 3D image is first resliced into 2D slices in a rotational manner in both the clockwise and counterclockwise directions. All slices intersect approximately along the rotational scanning axis and have an equal angular spacing. Six to eight boundary points are selected to initialize a level set function to extract the prostate contour within the first slice. The segmented contour is then propagated to the adjacent slice and is used as the initial contour for segmentation. This process is repeated until all slices are segmented. A modified distance regularization level set method is used to segment the prostate in all resliced 2D slices. In addition, shape-constraint and local-region-based energies are imposed to discourage the evolved level set function to leak in regions with weak edges or without edges. An anchor point based energy is used to promote the level set function to pass through the initial selected boundary points. The algorithm's performance was evaluated using distance- and volume-based metrics (sensitivity (Se), Dice similarity coefficient (DSC), mean absolute surface distance (MAD), maximum absolute surface distance (MAXD), and volume difference) by comparison with expert delineations.

RESULTS

The validation results using thirty 3D patient images showed that the authors' method can obtain a DSC of 93.1% ± 1.6%, a sensitivity of 93.0% ± 2.0%, a MAD of 1.18 ± 0.36 mm, a MAXD of 3.44 ± 0.8 mm, and a volume difference of 2.6 ± 1.9 cm(3) for the entire prostate. A reproducibility experiment demonstrated that the proposed method yielded low intraobserver and interobserver variability in terms of DSC. The mean segmentation time of the authors' method for all patient 3D TRUS images was 55 ± 3.5 s, in addition to 30 ± 5 s for initialization.

CONCLUSIONS

To address the challenges involved with slice-based 3D prostate segmentation, a level set based method is proposed in this paper. This method is especially developed for a 3D end-firing TRUS guided prostate biopsy system. The extensive experimental results demonstrate that the proposed method is accurate, robust, and computationally efficient.

Automated skin segmentation in ultrasonic evaluation of skin toxicity in breast cancer radiotherapy

Skin toxicity is the most common side effect of breast cancer radiotherapy and impairs the quality of life of many breast cancer survivors. We, along with other researchers, have recently found quantitative ultrasound to be effective as a skin toxicity assessment tool. Although more reliable than standard clinical evaluations (visual observation and palpation), the current procedure for ultrasound-based skin toxicity measurements requires manual delineation of the skin layers (i.e., epidermis-dermis and dermis-hypodermis interfaces) on each ultrasound B-mode image. Manual skin segmentation is time consuming and subjective. Moreover, radiation-induced skin injury may decrease image contrast between the dermis and hypodermis, which increases the difficulty of delineation. Therefore, we have developed an automatic skin segmentation tool (ASST) based on the active contour model with two significant modifications: (i) The proposed algorithm introduces a novel dual-curve scheme for the double skin layer extraction, as opposed to the original single active contour method. (ii) The proposed algorithm is based on a geometric contour framework as opposed to the previous parametric algorithm. This ASST algorithm was tested on a breast cancer image database of 730 ultrasound breast images (73 ultrasound studies of 23 patients). We compared skin segmentation results obtained with the ASST with manual contours performed by two physicians. The average percentage differences in skin thickness between the ASST measurement and that of each physician were less than 5% (4.8 ± 17.8% and -3.8 ± 21.1%, respectively). In summary, we have developed an automatic skin segmentation method that ensures objective assessment of radiation-induced changes in skin thickness. Our ultrasound technology offers a unique opportunity to quantify tissue injury in a more meaningful and reproducible manner than the subjective assessments currently employed in the clinic.

Review: the physiological and computational approaches for atherosclerosis treatment

The cardiovascular disease has long been an issue that causes severe loss in population, especially those conditions associated with arterial malfunction, being attributable to atherosclerosis and subsequent thrombotic formation. This article reviews the physiological mechanisms that underline the transition from plaque formation in atherosclerotic process to platelet aggregation and eventually thrombosis. The physiological and computational approaches, such as percutaneous coronary intervention and stent design modeling, to detect, evaluate and mitigate this malicious progression were also discussed.

Quantitative mapping of tumor vascularity using volumetric contrast-enhanced ultrasound

OBJECTIVE

The goal of this research project was to develop a volumetric strategy for real-time monitoring and characterization of tumor blood flow using microbubble contrast agents and ultrasound (US) imaging.

MATERIALS AND METHODS

Volumetric contrast-enhanced US (VCEUS) imaging was implemented on a SONIX RP US system (Ultrasonix Medical Corp, Richmond, BC) equipped with a broadband 4DL14-5/38 probe. Using a microbubble-sensitive harmonic imaging mode (transducer transmits at 5 MHz and receives at 10 MHz), acquisition of postscan-converted VCEUS data was achieved at a volume rate of 1 Hz. After microbubble infusion, custom data processing software was used to derive microbubble time-intensity curve-specific parameters, namely, blood volume (IPK), transit time (T1/2PK), flow rate (SPK), and tumor perfusion (AUC).

RESULTS

Using a preclinical breast cancer animal model, it is shown that millimeter-sized deviations in transducer positioning can have profound implications on US-based blood flow estimators, with errors ranging from 6.4% to 40.3% and dependent on both degree of misalignment (offset) and particular blood flow estimator. These errors indicate that VCEUS imaging should be considered in tumor analyses, because they incorporate the entire mass and not just a representative planar cross-section. After administration of an antiangiogenic therapeutic drug (bevacizumab), tumor growth was significantly retarded compared with control tumors (P > 0.03) and reflects observed changes in VCEUS-based blood flow measurements. Analysis of immunohistologic data revealed no differences in intratumoral necrosis levels (P = 0.70), but a significant difference was found when comparing microvessel density counts in control with therapy group tumors (P = 0.05).

CONCLUSIONS

VCEUS imaging was shown to be a promising modality for monitoring changes in tumor blood flow. Preliminary experimental results are encouraging, and this imaging modality may prove clinically feasible for detecting and monitoring the early antitumor effects in response to cancer drug therapy.

Bladder segmentation in MRI images using active region growing model

Prostate segmentation in MRI may be difficult at the interface with the bladder where the contrast is poor. Coupled-models that segment simultaneously both organs with non-overlapping constraints offer a good solution. As a pre-segmentation of the structures of interest is required, we propose in this paper a fast deformable model to segment the bladder. The combination of inflation and internal forces, locally adapted according to the gray levels, allow to deform the mesh toward the boundaries while overcoming the leakage issues that can occur at weak edges. The algorithm, evaluated on 33 MRI volumes from 5 different devices, has shown good performance providing a smooth and accurate surface.

3D Prostate Segmentation of Ultrasound Images Combining Longitudinal Image Registration and Machine Learning

We developed a three-dimensional (3D) segmentation method for transrectal ultrasound (TRUS) images, which is based on longitudinal image registration and machine learning. Using longitudinal images of each individual patient, we register previously acquired images to the new images of the same subject. Three orthogonal Gabor filter banks were used to extract texture features from each registered image. Patient-specific Gabor features from the registered images are used to train kernel support vector machines (KSVMs) and then to segment the newly acquired prostate image. The segmentation method was tested in TRUS data from five patients. The average surface distance between our and manual segmentation is 1.18 ± 0.31 mm, indicating that our automatic segmentation method based on longitudinal image registration is feasible for segmenting the prostate in TRUS images.

Fast plaque burden assessment of the femoral artery using 3D black-blood MRI and automated segmentation

PURPOSE

Vessel wall imaging techniques have been introduced to assess the burden of peripheral arterial disease (PAD) in terms of vessel wall thickness, area or volume. Recent advances in a 3D black-blood MRI sequence known as the 3D motion-sensitized driven equilibrium (MSDE) prepared rapid gradient echo sequence (3D MERGE) have allowed the acquisition of vessel wall images with up to 50 cm coverage, facilitating noninvasive and detailed assessment of PAD. This work introduces an algorithm that combines 2D slice-based segmentation and 3D user editing to allow for efficient plaque burden analysis of the femoral artery images acquired using 3D MERGE.

METHODS

The 2D slice-based segmentation approach is based on propagating segmentation results of contiguous 2D slices. The 3D image volume was then reformatted using the curved planar reformation (CPR) technique. User editing of the segmented contours was performed on the CPR views taken at different angles. The method was evaluated on six femoral artery images. Vessel wall thickness and area obtained before and after editing on the CPR views were assessed by comparison with manual segmentation. Difference between semiautomatically and manually segmented contours were compared with the difference of the corresponding measurements between two repeated manual segmentations.

RESULTS

The root-mean-square (RMS) errors of the mean wall thickness (t(mean)) and the wall area (WA) of the edited contours were 0.35 mm and 7.1 mm(2), respectively, which are close to the RMS difference between two repeated manual segmentations (RMSE: 0.33 mm in t(mean), 6.6 mm(2) in WA). The time required for the entire semiautomated segmentation process was only 1%-2% of the time required for manual segmentation.

CONCLUSIONS

The difference between the boundaries generated by the proposed algorithm and the manually segmented boundary is close to the difference between repeated manual segmentations. The proposed method provides accurate plaque burden measurements, while considerably reducing the analysis time compared to manual review.

EFFICIENT 3D PROSTATE SURFACE DETECTION FOR ULTRASOUND GUIDED ROBOTIC BIOPSY

Prostate surface detection from ultrasound images plays a key role in our recently developed ultrasound guided robotic biopsy system. However, due to the low contrast, speckle noise and shadowing in ultrasound images, this still remains a difficult task. In the current system, a 3D prostate surface is reconstructed from a sequence of 2D outlines, which are performed manually. This is arduous and the results depend heavily on the user's expertise. This paper presents a new practical method, called Evolving Bubbles, based on the level set method to semi-automatically detect the prostate surface from transrectal ultrasound (TRUS) images. To produce good results, a few initial bubbles are simply specified by the user from five particular slices based on the prostate shape. When the initial bubbles evolve along their normal directions, they expand, shrink, merge and split, and finally are attracted to the desired prostate surface. Meanwhile, to remedy the boundary leaking problem caused by gaps or weak boundaries, domain specific knowledge of the prostate and statistical information are incorporated into the Evolving Bubbles. We apply the bubbles model to eight 3D and four stacks of 2D TRUS images and the results show its effectiveness.

Clinical application of a 3D ultrasound-guided prostate biopsy system

OBJECTIVES

Prostate biopsy (Bx) has for 3 decades been performed in a systematic, but blind fashion using 2D ultrasound (US). Herein is described the initial clinical evaluation of a 3D Bx tracking and targeting device (Artemis; Eigen, Grass Valley, CA). Our main objective was to test accuracy of the new 3D method in men undergoing first and follow-up Bx to rule out prostate cancer (CaP).

MATERIALS AND METHODS

Patients in the study were men ages 35-87 years (66.1 ± 9.9), scheduled for Bx to rule out CaP, who entered into an IRB-approved protocol. A total of 218 subjects underwent conventional trans-rectal US (TRUS); the tracking system was then attached to the US probe; the prostate was scanned and a 3D reconstruction was created. All Bx sites were visualized in 3D and tracked electronically. In 11 men, a pilot study was conducted to test ability of the device to return a Bx to an original site. In 47 men, multi-parametric 3 Tesla MRI, incorporating T2-weighted images, dynamic contrast enhancement, and diffusion-weighted imaging, was performed in advance of the TRUS, allowing the stored MRI images to be fused with real-time US during biopsy. Lesions on MRI were delineated by a radiologist, assigned a grade of CaP suspicion, and fused into TRUS for biopsy targeting.

RESULTS

3D Bx tracking was completed successfully in 180/218 patients, with a success rate approaching 95% among the last 50 men. Average time for Bx with the Artemis device was 15 minutes with an additional 5 minutes for MRI fusion and Bx targeting. In the tracking study, an ability to return to prior Bx sites (n=32) within 1.2 ± 1.1 mm SD was demonstrated and was independent of prostate volume or location of Bx site. In the MRI fusion study, when suspicious lesions were targeted, a 33% Bx-positivity rate was found compared with a 7% positivity rate for systematic, nontargeted Bx (19/57 cores vs. 9/124 cores, P=0.03).

CONCLUSION

Use of 3D tracking and image fusion has the potential to transform MRI into a clinical tool to aid biopsy and improve current methods for diagnosis and follow-up of CaP.

Automatic 3D Segmentation of Ultrasound Images Using Atlas Registration and Statistical Texture Prior

We are developing a molecular image-directed, 3D ultrasound-guided, targeted biopsy system for improved detection of prostate cancer. In this paper, we propose an automatic 3D segmentation method for transrectal ultrasound (TRUS) images, which is based on multi-atlas registration and statistical texture prior. The atlas database includes registered TRUS images from previous patients and their segmented prostate surfaces. Three orthogonal Gabor filter banks are used to extract texture features from each image in the database. Patient-specific Gabor features from the atlas database are used to train kernel support vector machines (KSVMs) and then to segment the prostate image from a new patient. The segmentation method was tested in TRUS data from 5 patients. The average surface distance between our method and manual segmentation is 1.61 ± 0.35 mm, indicating that the atlas-based automatic segmentation method works well and could be used for 3D ultrasound-guided prostate biopsy.

Adaptively learning local shape statistics for prostate segmentation in ultrasound

Automatic segmentation of the prostate from 2-D transrectal ultrasound (TRUS) is a highly desired tool in many clinical applications. However, it is a very challenging task, especially for segmenting the base and apex of the prostate due to the large shape variations in those areas compared to the midgland, which leads many existing segmentation methods to fail. To address the problem, this paper presents a novel TRUS video segmentation algorithm using both global population-based and patient-specific local shape statistics as shape constraint. By adaptively learning shape statistics in a local neighborhood during the segmentation process, the algorithm can effectively capture the patient-specific shape statistics and quickly adapt to the local shape changes in the base and apex areas. The learned shape statistics is then used as the shape constraint in a deformable model for TRUS video segmentation. The proposed method can robustly segment the entire gland of the prostate with significantly improved performance in the base and apex regions, compared to other previously reported methods. Our method was evaluated using 19 video sequences obtained from different patients and the average mean absolute distance error was 1.65 ± 0.47 mm.

Incremental shape statistics learning for prostate tracking in TRUS

Automatic delineation of the prostate boundary in transrectal ultrasound (TRUS) can play a key role in image-guided prostate intervention. However, it is a very challenging task for several reasons, especially due to the large variation of the prostate shape from the base to the apex. To deal with the problem, a new method for incrementally learning the patient-specific local shape statistics is proposed in this paper to help achieve robust and accurate boundary delineation over the entire prostate gland. The proposed method is fast and memory efficient in that new shapes can be merged into the shape statistics without recomputing using all the training shapes, which makes it suitable for use in real-time interventional applications. In our work, the learned shape statistics is incorporated into a modified sequential inference model for tracking the prostate boundary. Experimental results show that the proposed method is more robust and accurate than the active shape model using global population-based shape statistics in delineating the prostate boundary in TRUS.

A magnetic resonance spectroscopy driven initialization scheme for active shape model based prostate segmentation

Segmentation of the prostate boundary on clinical images is useful in a large number of applications including calculation of prostate volume pre- and post-treatment, to detect extra-capsular spread, and for creating patient-specific anatomical models. Manual segmentation of the prostate boundary is, however, time consuming and subject to inter- and intra-reader variability. T2-weighted (T2-w) magnetic resonance (MR) structural imaging (MRI) and MR spectroscopy (MRS) have recently emerged as promising modalities for detection of prostate cancer in vivo. MRS data consists of spectral signals measuring relative metabolic concentrations, and the metavoxels near the prostate have distinct spectral signals from metavoxels outside the prostate. Active Shape Models (ASM's) have become very popular segmentation methods for biomedical imagery. However, ASMs require careful initialization and are extremely sensitive to model initialization. The primary contribution of this paper is a scheme to automatically initialize an ASM for prostate segmentation on endorectal in vivo multi-protocol MRI via automated identification of MR spectra that lie within the prostate. A replicated clustering scheme is employed to distinguish prostatic from extra-prostatic MR spectra in the midgland. The spatial locations of the prostate spectra so identified are used as the initial ROI for a 2D ASM. The midgland initializations are used to define a ROI that is then scaled in 3D to cover the base and apex of the prostate. A multi-feature ASM employing statistical texture features is then used to drive the edge detection instead of just image intensity information alone. Quantitative comparison with another recent ASM initialization method by Cosio showed that our scheme resulted in a superior average segmentation performance on a total of 388 2D MRI sections obtained from 32 3D endorectal in vivo patient studies. Initialization of a 2D ASM via our MRS-based clustering scheme resulted in an average overlap accuracy (true positive ratio) of 0.60, while the scheme of Cosio yielded a corresponding average accuracy of 0.56 over 388 2D MR image sections. During an ASM segmentation, using no initialization resulted in an overlap of 0.53, using the Cosio based methodology resulted in an overlap of 0.60, and using the MRS-based methodology resulted in an overlap of 0.67, with a paired Student's t-test indicating statistical significance to a high degree for all results. We also show that the final ASM segmentation result is highly correlated (as high as 0.90) to the initialization scheme.

Semi-automatic segmentation for prostate interventions

In this paper we report and characterize a semi-automatic prostate segmentation method for prostate brachytherapy. Based on anatomical evidence and requirements of the treatment procedure, a warped and tapered ellipsoid was found suitable as the a-priori 3D shape of the prostate. By transforming the acquired endorectal transverse images of the prostate into ellipses, the shape fitting problem was cast into a convex problem which can be solved efficiently. The average whole gland error between non-overlapping volumes created from manual and semi-automatic contours from 21 patients was 6.63 ± 0.9%. For use in brachytherapy treatment planning, the resulting contours were modified, if deemed necessary, by radiation oncologists prior to treatment. The average whole gland volume error between the volumes computed from semi-automatic contours and those computed from modified contours, from 40 patients, was 5.82 ± 4.15%. The amount of bias in the physicians' delineations when given an initial semi-automatic contour was measured by comparing the volume error between 10 prostate volumes computed from manual contours with those of modified contours. This error was found to be 7.25 ± 0.39% for the whole gland. Automatic contouring reduced subjectivity, as evidenced by a decrease in segmentation inter- and intra-observer variability from 4.65% and 5.95% for manual segmentation to 3.04% and 3.48% for semi-automatic segmentation, respectively. We characterized the performance of the method relative to the reference obtained from manual segmentation by using a novel approach that divides the prostate region into nine sectors. We analyzed each sector independently as the requirements for segmentation accuracy depend on which region of the prostate is considered. The measured segmentation time is 14 ± 1s with an additional 32 ± 14s for initialization. By assuming 1-3 min for modification of the contours, if necessary, a total segmentation time of less than 4 min is required, with no additional time required prior to treatment planning. This compares favorably to the 5-15 min manual segmentation time required for experienced individuals. The method is currently used at the British Columbia Cancer Agency (BCCA) Vancouver Cancer Centre as part of the standard treatment routine in low dose rate prostate brachytherapy and is found to be a fast, consistent and accurate tool for the delineation of the prostate gland in ultrasound images.

Measuring flow-mediated dilation through transverse and longitudinal imaging: comparison and validation of methods

Three-dimensional ultrasound images (3DUS), having two spatial and one temporal dimension, were taken of the brachial artery during baseline conditions, in the transverse and longitudinal planes. The transverse images were analyzed by three different techniques used to quantify flow-mediated dilation (FMD): (1) measuring vessel area manually (TIMA), (2) measuring vessel area semi-automatically (TISA) and (3) measuring vessel diameter (TID). The inter- and intra-observer variability and transducer repositioning variability of each method were compared to each other and to the variability of measurements taken using the traditional method of measuring vessel FMD through measuring vessel diameter on longitudinal images (LID). The percent coefficient-of-variation describing the inter-observer variability (COV(inter)) was similar for the methods, indicating that each method was equally reproducible by the different observers. The percent coefficient-of-variation describing the intra-observer variability (COV(intra)) and the smallest detectable percent change in diameter (Δd(intra)) for each method indicated that TID was the most precise at measuring vessel diameter, and could measure the smallest changes in diameter between successive measurements (COV(intra) = 0.31%, Δd(intra) = 0.87%). LID performed the poorest (COV(intra) = 0.57%, Δd(intra) = 1.59%). The percent coefficient-of-variation describing transducer repositioning (COV(rep)) and the smallest detectable percent change in FMD over time (ΔFMD) for each method indicated that TIMA was the most reproducible method (COV(rep) = 2.35%, ΔFMD = 6.52%) closely followed by TISA. TID performed the poorest (COV(rep) = 5.37%, ΔFMD = 14.89%). TIMA and TISA were found not to be statistically different so we suggest TISA as the method of choice to maximize reproducibility between measurements over time, as it is faster and simpler to perform. In each experiment it was clear that transverse imaging introduced equal or less variability into diameter measurements as compared to longitudinal imaging and we suggest this imaging plane be used in all assessments of FMD.

Highly sensitive computer aided diagnosis system for breast tumor based on color Doppler flow images

A computer-aided diagnosis (CAD) system for breast tumor based on color Doppler flow images is proposed. Our system consists of automatic segmentation, feature extraction, and classification of breast tumors. First, the B-mode grayscale image containing anatomical information was separated from a color Doppler flow image (CDFI). Second, the boundary of the breast tumor was automatically defined in the B-mode image and then morphologic and gray features were extracted. Third, an optimal feature vector was created using K-means cluster algorithm. Then a back-propagation (BP) artificial neural network (ANN) was used to classify breast tumors as benign, malignant or uncertain. Finally, the blood flow feature was extracted selectively from the CDFI, and was used to classify the uncertain tumor as benign or malignant. Experiments on 500 cases show that the proposed system yields an accuracy of 100% for the malignant and 80.8% for the benign classification. Comparing with other systems, the advantage of our system is that it has a much lower percentage of malignant tumor misdiagnosis.

An intraoperative 3D ultrasound system for tumor margin determination in breast cancer surgery

PURPOSE

The purpose of this study was to analyze the clinical utility of a portable three-dimensional ultrasound (3DUS) system to be used for surgical guidance of lumpectomy surgeries. In 11%-60% of lumpectomy surgeries, a second surgery is required to fully resect the tumor. Previous studies have used 3DUS as a guidance tool with the hope of more accuracy in resecting the entire tumor during the first surgery. However, they utilized larger systems, which are not easily integrated into the operating room.

METHODS

The portable 3DUS scanning system we developed consisted of a motorized "tilt" scanner coupled to a Terason t3000 portable ultrasound machine (Terason Ultrasound, Burlington, MA). The 3DUS system was evaluated by measuring agar "tumor" phantoms of known volumes and acquiring and segmenting images from nine patients undergoing lumpectomy.

RESULTS

Experiments on simulated agar tumor phantoms have shown that our device could be used to measure objects with smooth, well-defined boundaries of known volume with an error of 3%. It was possible to view and segment estimated tumor margins from the clinical images in three dimensions. Correspondence between measurements obtained in the laboratory and the operating room varied with tumor geometry and the degree of spiculation in the ultrasound image. The measured values obtained by the system did not correspond closely with those obtained using histology. However, a more accurate histological measurement using 3D histology may provide a better basis for comparison.

CONCLUSIONS

The results of imaging simulated agar tumor phantoms indicate the system's consistency in measuring objects of known volume and geometry. The system could be used for segmenting the approximate boundary of lumpectomy patients' breast tumors relative to inserted guide wires. The potential advantages of this system are a reduction in the number of re-excision surgeries required and a reduction in the operative time with the patient under anesthesia.

Determination of breast cancer response to bevacizumab therapy using contrast-enhanced ultrasound and artificial neural networks

OBJECTIVE

The purpose of this study was to evaluate contrast-enhanced ultrasound and neural network data classification for determining the breast cancer response to bevacizumab therapy in a murine model.

METHODS

An ultrasound scanner operating in the harmonic mode was used to measure ultrasound contrast agent (UCA) time-intensity curves in vivo. Twenty-five nude athymic mice with orthotopic breast cancers received a 30-microL tail vein bolus of a perflutren microsphere UCA, and baseline tumor imaging was performed using microbubble destruction-replenishment techniques. Subsequently, 15 animals received a 0.2-mg injection of bevacizumab, whereas 10 control animals received an equivalent dose of saline. Animals were reimaged on days 1, 2, 3, and 6 before euthanasia. Histologic assessment of excised tumor sections was performed. Time-intensity curve analysis for a given region of interest was conducted using customized software. Tumor perfusion metrics on days 1, 2, 3, and 6 were modeled using neural network data classification schemes (60% learning and 40% testing) to predict the breast cancer response to therapy.

RESULTS

The breast cancer response to a single dose of bevacizumab in a murine model was immediate and transient. Permutations of input to the neural network data classification scheme revealed that tumor perfusion data within 3 days of bevacizumab dosing was sufficient to minimize the prediction error to 10%, whereas measurements of physical tumor size alone did not appear adequate to assess the therapeutic response.

CONCLUSIONS

Contrast-enhanced ultrasound may be a useful tool for determining the response to bevacizumab therapy and monitoring the subsequent restoration of blood flow to breast cancer.

Discrete deformable model guided by partial active shape model for TRUS image segmentation

Automatic prostate segmentation in transrectal ultrasound (TRUS) images is highly desired in many clinical applications. However, robust and automated prostate segmentation is challenging due to the low SNR in TRUS and the missing boundaries in shadow areas caused by calcifications or hyperdense prostate tissues. This paper presents a novel method of utilizing a priori shapes estimated from partial contours for segmenting the prostate. The proposed method is able to automatically extract prostate boundary from 2-D TRUS images without user interaction for shape correction in shadow areas. During the segmentation process, missing boundaries in shadow areas are estimated by using a partial active shape model, which takes partial contours as input but returns a complete shape estimation. With this shape guidance, an optimal search is performed by a discrete deformable model to minimize an energy functional for image segmentation, which is achieved efficiently by using dynamic programming. The segmentation of an image is executed in a multiresolution fashion from coarse to fine for robustness and computational efficiency. Promising segmentation results were demonstrated on 301 TRUS images grabbed from 19 patients with the average mean absolute distance error of 2.01 mm +/- 1.02 mm.

Fully automated common carotid artery and internal jugular vein identification and tracking using B-mode ultrasound

We describe a fully automated ultrasound analysis system that tracks and identifies the common carotid artery (CCA) and the internal jugular vein (IJV). Our goal is to prevent inadvertent damage to the CCA when targeting the IJV for catheterization. The automated system starts by identifying and fitting ellipses to all the regions that look like major arteries or veins throughout each B-mode ultrasound image frame. The spokes ellipse algorithm described in this paper tracks these putative vessels and calculates their characteristics, which are then weighted and summed to identify the vessels. The optimum subset of characteristics and their weights were determined from a training set of 38 subjects, whose necks were scanned with a portable 10 MHz ultrasound system at 10 frames per second. Stepwise linear discriminant analysis (LDA) narrowed the characteristics to the five that best distinguish between the CCA and IJV. A paired version of Fisher's LDA was used to calculate the weights for each of the five parameters. Leave-one-out validation studies showed that the system could track and identify the CCA and IJV with 100% accuracy in this dataset.

Mechanically assisted 3D ultrasound guided prostate biopsy system

There are currently limitations associated with the prostate biopsy procedure, which is the most commonly used method for a definitive diagnosis of prostate cancer. With the use of two-dimensional (2D) transrectal ultrasound (TRUS) for needle-guidance in this procedure, the physician has restricted anatomical reference points for guiding the needle to target sites. Further, any motion of the physician's hand during the procedure may cause the prostate to move or deform to a prohibitive extent. These variations make it difficult to establish a consistent reference frame for guiding a needle. We have developed a 3D navigation system for prostate biopsy, which addresses these shortcomings. This system is composed of a 3D US imaging subsystem and a passive mechanical arm to minimize prostate motion. To validate our prototype, a series of experiments were performed on prostate phantoms. The 3D scan of the string phantom produced minimal geometric distortions, and the geometric error of the 3D imaging subsystem was 0.37 mm. The accuracy of 3D prostate segmentation was determined by comparing the known volume in a certified phantom to a reconstructed volume generated by our system and was shown to estimate the volume with less then 5% error. Biopsy needle guidance accuracy tests in agar prostate phantoms showed that the mean error was 2.1 mm and the 3D location of the biopsy core was recorded with a mean error of 1.8 mm. In this paper, we describe the mechanical design and validation of the prototype system using an in vitro prostate phantom. Preliminary results from an ongoing clinical trial show that prostate motion is small with an in-plane displacement of less than 1 mm during the biopsy procedure.

Design and evaluation of a 3D transrectal ultrasound prostate biopsy system

Biopsy of the prostate using ultrasound guidance is the clinical gold standard for diagnosis of prostate adenocarcinoma. The current prostate biopsy procedure is limited to using 2D transrectal ultrasound (TRUS) images to target biopsy sites and record biopsy core locations for postbiopsy confirmation. Localization of the 2D image in its actual 3D position is ambiguous and limits procedural accuracy and reproducibility. We have developed a 3D TRUS prostate biopsy system that provides 3D intrabiopsy information for needle guidance and biopsy location recording. The system conforms to the workflow and imaging technology of the current biopsy procedure, making it easier for clinical integration. In this paper, we describe the system design and validate the system accuracy by performing mock biopsies on US/CT multimodal patient-specific prostate phantoms. Our biopsy system generated 3D patient-specific models of the prostate with volume errors less than 3.5% and mean boundary errors of less than 1 mm. Using the 3D biopsy system, needles were guided to within 2.3 +/- 1.0 mm of 3D targets and with a high probability of biopsying clinically significant tumors. The positions of the actual biopsy sites were accurately localized to within 1.5 +/- 0.8 mm.

Quantification of carotid vessel wall and plaque thickness change using 3D ultrasound images

Quantitative measurements of carotid plaque burden progression or regression are important in monitoring patients and in evaluation of new treatment options. 3D ultrasound (US) has been used to monitor the progression or regression of carotid artery plaques. This paper reports on the development and application of a method used to analyze changes in carotid plaque morphology from 3D US. The technique used is evaluated using manual segmentations of the arterial wall and lumen from 3D US images acquired in two imaging sessions. To reduce the effect of segmentation variability, segmentation was performed five times each for the wall and lumen. The mean wall and lumen surfaces, computed from this set of five segmentations, were matched on a point-by-point basis, and the distance between each pair of corresponding points served as an estimate of the combined thickness of the plaque, intima, and media (vessel-wall-plus-plaque thickness or VWT). The VWT maps associated with the first and the second US images were compared and the differences of VWT were obtained at each vertex. The 3D VWT and VWT-Change maps may provide important information for evaluating the location of plaque progression in relation to the localized disturbances of flow pattern, such as oscillatory shear, and regression in response to medical treatments.

Adaptation of a 3D prostate cancer atlas for transrectal ultrasound guided target-specific biopsy

Due to lack of imaging modalities to identify prostate cancer in vivo, current TRUS guided prostate biopsies are taken randomly. Consequently, many important cancers are missed during initial biopsies. The purpose of this study was to determine the potential clinical utility of a high-speed registration algorithm for a 3D prostate cancer atlas. This 3D prostate cancer atlas provides voxel-level likelihood of cancer and optimized biopsy locations on a template space (Zhan et al 2007). The atlas was constructed from 158 expert annotated, 3D reconstructed radical prostatectomy specimens outlined for cancers (Shen et al 2004). For successful clinical implementation, the prostate atlas needs to be registered to each patient's TRUS image with high registration accuracy in a time-efficient manner. This is implemented in a two-step procedure, the segmentation of the prostate gland from a patient's TRUS image followed by the registration of the prostate atlas. We have developed a fast registration algorithm suitable for clinical applications of this prostate cancer atlas. The registration algorithm was implemented on a graphical processing unit (GPU) to meet the critical processing speed requirements for atlas guided biopsy. A color overlay of the atlas superposed on the TRUS image was presented to help pick statistically likely regions known to harbor cancer. We validated our fast registration algorithm using computer simulations of two optimized 7- and 12-core biopsy protocols to maximize the overall detection rate. Using a GPU, patient's TRUS image segmentation and atlas registration took less than 12 s. The prostate cancer atlas guided 7- and 12-core biopsy protocols had cancer detection rates of 84.81% and 89.87% respectively when validated on the same set of data. Whereas the sextant biopsy approach without the utility of 3D cancer atlas detected only 70.5% of the cancers using the same histology data. We estimate 10-20% increase in prostate cancer detection rates when TRUS guided biopsies are assisted by the 3D prostate cancer atlas compared to the current standard of care. The fast registration algorithm we have developed can easily be adapted for clinical applications for the improved diagnosis of prostate cancer.

Level set segmentation of bovine corpora lutea in ex situ ovarian ultrasound images

BACKGROUND

The objective of this study was to investigate the viability of level set image segmentation methods for the detection of corpora lutea (corpus luteum, CL) boundaries in ultrasonographic ovarian images. It was hypothesized that bovine CL boundaries could be located within 1-2 mm by a level set image segmentation methodology.

METHODS

Level set methods embed a 2D contour in a 3D surface and evolve that surface over time according to an image-dependent speed function. A speed function suitable for segmentation of CL's in ovarian ultrasound images was developed. An initial contour was manually placed and contour evolution was allowed to proceed until the rate of change of the area was sufficiently small. The method was tested on ovarian ultrasonographic images (n = 8) obtained ex situ. A expert in ovarian ultrasound interpretation delineated CL boundaries manually to serve as a "ground truth". Accuracy of the level set segmentation algorithm was determined by comparing semi-automatically determined contours with ground truth contours using the mean absolute difference (MAD), root mean squared difference (RMSD), Hausdorff distance (HD), sensitivity, and specificity metrics.

RESULTS AND DISCUSSION

The mean MAD was 0.87 mm (sigma = 0.36 mm), RMSD was 1.1 mm (sigma = 0.47 mm), and HD was 3.4 mm (sigma = 2.0 mm) indicating that, on average, boundaries were accurate within 1-2 mm, however, deviations in excess of 3 mm from the ground truth were observed indicating under- or over-expansion of the contour. Mean sensitivity and specificity were 0.814 (sigma = 0.171) and 0.990 (sigma = 0.00786), respectively, indicating that CLs were consistently undersegmented but rarely did the contour interior include pixels that were judged by the human expert not to be part of the CL. It was observed that in localities where gradient magnitudes within the CL were strong due to high contrast speckle, contour expansion stopped too early.

CONCLUSION

The hypothesis that level set segmentation can be accurate to within 1-2 mm on average was supported, although there can be some greater deviation. The method was robust to boundary leakage as evidenced by the high specificity. It was concluded that the technique is promising and that a suitable data set of human ovarian images should be obtained to conduct further studies.

Application of reinforcement learning for segmentation of transrectal ultrasound images

Background

Among different medical image modalities, ultrasound imaging has a very widespread clinical use. But, due to some factors, such as poor image contrast, noise and missing or diffuse boundaries, the ultrasound images are inherently difficult to segment. An important application is estimation of the location and volume of the prostate in transrectal ultrasound (TRUS) images. For this purpose, manual segmentation is a tedious and time consuming procedure.

Methods

We introduce a new method for the segmentation of the prostate in transrectal ultrasound images, using a reinforcement learning scheme. This algorithm is used to find the appropriate local values for sub-images and to extract the prostate. It contains an offline stage, where the reinforcement learning agent uses some images and manually segmented versions of these images to learn from. The reinforcement agent is provided with reward/punishment, determined objectively to explore/exploit the solution space. After this stage, the agent has acquired knowledge stored in the Q-matrix. The agent can then use this knowledge for new input images to extract a coarse version of the prostate.

Results

We have carried out experiments to segment TRUS images. The results demonstrate the potential of this approach in the field of medical image segmentation.

Conclusion

By using the proposed method, we can find the appropriate local values and segment the prostate. This approach can be used for segmentation tasks containing one object of interest. To improve this prototype, more investigations are needed.