Segmentation of iodine brachytherapy implants in fluoroscopy

Purpose

In prostate brachytherapy, intraoperative dosimetry would allow for evaluation of the implant quality while the patient is still in treatment position. Such a mechanism, however, requires 3-D visualization of the deposited seeds relative to the prostate. It follows that accurate and robust seed segmentation is of critical importance in achieving intraoperative dosimetry.

Methods

Implanted iodine brachytherapy seeds are segmented via a region-based implicit active contour model. Overlapping seed groups are then resolved using a template-based declustering technique.

Results

Ground truth seed coordinates were obtained through manual segmentation. A total of 57 clinical C-arm images from 10 patients were used to validate the proposed algorithm. This resulted in two failed images and a 96.0% automatic detection rate with a corresponding 2.2% false-positive rate in the remaining 55 images. The mean centroid error between the manual and automatic segmentations was 1.2 pixels.

Conclusions

Robust and accurate iodine seed segmentation can be achieved through the proposed segmentation workflow.     

Prostate segmentation in transrectal ultrasound using magnetic resonance imaging priors

Purpose

In the current standard of care, real-time transrectal ultrasound (TRUS) is commonly used for prostate brachytherapy guidance. As TRUS provides limited soft tissue contrast, segmenting the prostate gland in TRUS images is often challenging and subject to inter-observer and intra-observer variability, especially at the base and apex where the gland boundary is hard to define. Magnetic resonance imaging (MRI) has higher soft tissue contrast allowing the prostate to be contoured easily. In this paper, we aim to show that prostate segmentation in TRUS images informed by MRI priors can improve on prostate segmentation that relies only on TRUS images.

Methods

First, we compare the TRUS-based prostate segmentation used in the treatment of 598 patients with a high-quality MRI prostate atlas and observe inconsistencies at the apex and base. Second, motivated by this finding, we propose an alternative TRUS segmentation technique that is fully automatic and uses MRI priors. The algorithm uses a convolutional neural network to segment the prostate in TRUS images at mid-gland, where the gland boundary can be clearly seen. It then reconstructs the gland boundary at the apex and base with the aid of a statistical shape model built from an MRI atlas of 78 patients.

Results

Compared to the clinical TRUS segmentation, our method achieves similar mid-gland segmentation results in the 598-patient database. For the seven patients who had both TRUS and MRI, our method achieved more accurate segmentation of the base and apex with the MRI segmentation used as ground truth.

Conclusion

Our results suggest that utilizing MRI priors in TRUS prostate segmentation could potentially improve the performance at base and apex.

     

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.     

A technique for semiautomatic segmentation of echogenic structures in 3D ultrasound,applied to infant hip dysplasia

Purpose

Automatic segmentation of anatomical structures and lesions from medical ultrasound images is a formidable challenge in medical imaging due to image noise, blur and artifacts. In this paper we present a segmentation technique with features highly suited to use in noisy 3D ultrasound volumes and demonstrate its use in modeling bone, specifically the acetabulum in infant hips. Quantification of the acetabular shape is crucial in diagnosing developmental dysplasia of the hip (DDH), a common condition associated with hip dislocation and premature osteoarthritis if not treated. The well-established Graf technique for DDH diagnosis has been criticized for high inter-observer and inter-scan variability. In our earlier work we have introduced a more reliable instability metric based on 3D ultrasound data. Visualizing and interpreting the acetabular shape from noisy 3D ultrasound volumes has been one of the major roadblocks in using 3D ultrasound as diagnostic tool for DDH. For this study we developed a semiautomated segmentation technique to rapidly generate 3D acetabular surface models and classified the acetabulum based on acetabular contact angle (ACA) derived from the models. We tested the feasibility and reliability of the technique compared with manual segmentation.

Methods

The proposed segmentation algorithm is based on graph search. We formulate segmentation of the acetabulum as an optimal path finding problem on an undirected weighted graph. Slice contours are defined as the optimal path passing through a set of user-defined seed points in the graph, and it can be found using dynamic programming techniques (in this case Dijkstra’s algorithm). Slice contours are then interpolated over the 3D volume to generate the surface model. A three-dimensional ACA was calculated using normal vectors of the surface model.

Results

The algorithm was tested over an extensive dataset of 51 infant ultrasound hip volumes obtained from 42 subjects with normal to dysplastic hips. The contours generated by the segmentation algorithm closely matched with those obtained from manual segmentation. The average RMS errors between the semiautomated and manual segmentation for the 51 volumes were 0.28 mm/1.1 voxel (with 2 node points) and 0.24 mm/0.9 voxel (with 3 node points). The semiautomatic algorithm gave visually acceptable results on images with moderate levels of noise and was able to trace the boundary of the acetabulum even in the presence of significant shadowing. Semiautomatic contouring was also faster than manual segmentation at 37 versus 56 s per scan. It also improved the repeatability of the ACA calculation with inter-observer and intra-observer variability of \(1.4 \pm 0.9\) degree and \(1.4 \pm 1.0\) degree.

Conclusion

The semiautomatic segmentation technique proposed in this work offers a fast and reliable method to delineate the contours of the acetabulum from 3D ultrasound volumes of the hip. Since the technique does not rely upon contour evolution, it is less susceptible than other methods to the frequent missing or incomplete boundaries and noise artifacts common in ultrasound images. ACA derived from the segmented 3D surface was able to accurately classify the acetabulum under the categories normal, borderline and dysplastic. The semiautomatic technique makes it easier to segment the volume and reduces the inter-observer and intra-observer variation in ACA calculation compared with manual segmentation. The method can be applied to any structure with an echogenic boundary on ultrasound (such as a ventricle, blood vessel, organ or tumor), or even to structures with a bright border on computed tomography or magnetic resonance imaging.

     

Automatic initialization of an active shape model of the prostate

In this work is reported a new method for automatic segmentation of the boundary of the prostate, in transurethral ultrasound images. The scheme is based on a robust automatic initialization of an active shape model (ASM) of the prostate, which is subsequently fitted to the boundary of the gland. The initialization of the ASM is based on pixel classification to estimate the prostate region in an ultrasound image, followed by automatic adjustment – using a multipopulation genetic algorithm (MPGA) – of the initial pose of the ASM to the binary image produced by the classifier. The initial pose is next adjusted to the gray level ultrasound image, using the MPGA. After automatic initialization, the ASM is adjusted to the gray level ultrasound image to produce the final prostate contour. The method provides fast and robust segmentation of the prostate boundary. Validation results on 22 ultrasound images are reported with 1.74 mm of mean boundary error and an estimated processing time of 66 s per image. Our automatic initialization method can be applied with the ASMs of different organs in various imaging modalities.     

Muscles of mastication model-based MR image segmentation

Objective The muscles of mastication play a major role in the orodigestive system as the principal motive force for the mandible. An algorithm for segmenting these muscles from magnetic resonance (MR) images was developed and tested. Materials and methods Anatomical information about the muscles of mastication in MR images is used to obtain the spatial relationships relating the muscle region of interest (ROI) and head ROI. A model-based technique that involves the spatial relationships between head and muscle ROIs as well as muscle templates is developed. In the segmentation stage, the muscle ROI is derived from the model. Within the muscle ROI, anisotropic diffusion is applied to smooth the texture, followed by thresholding to exclude bone and fat. The muscle template and morphological operators are employed to obtain an initial estimate of the muscle boundary, which then serves as the input contour to the gradient vector flow snake that iterates to the final segmentation. Results The method was applied to segmentation of the masseter, lateral pterygoid and medial pterygoid in 75 images. The overlap indices (κ) achieved are 91.4, 92.1 and 91.2%, respectively. Conclusion A model-based method for segmenting the muscles of mastication from MR images was developed and tested. The results show good agreement between manual and automatic segmentations.     

Combining a deformable model and a probabilistic framework for an automatic 3D segmentation of prostate on MRI

Purpose  Accurate localization and contouring of prostate are crucial issues in prostate cancer diagnosis and/or therapies. Although several semi-automatic and automatic segmentation methods have been proposed, manual expert correction remains necessary. We introduce a new method for automatic 3D segmentation of the prostate gland from magnetic resonance imaging (MRI) scans. Methods  A statistical shape model was used as an a priori knowledge, and gray levels distribution was modeled by fitting histogram modes with a Gaussian mixture. Markov fields were used to introduce contextual information regarding voxels’ neighborhoods. Final labeling optimization is based on Bayesian a posteriori classification, estimated with the iterative conditional mode algorithm. Results  We compared the accuracy of this method, free from any manual correction, with contours outlined by an expert radiologist. In 12 cases, including prostates with cancer and benign prostatic hypertrophy, the mean Hausdorff distance and overlap ratio were 9.94 mm and 0.83, respectively. Conclusion  This new automatic prostate MRI segmentation method produces satisfactory results, even at prostate’s base and apex. The method is computationally feasible and efficient.     

Intraoperative segmentation of iodine and palladium radioactive sources in C-arm images

Purpose

   Dynamic dosimetry is becoming the standard to evaluate the quality of radioactive implants during brachytherapy. For this, it is essential to obtain a 3D visualization of the implanted seeds and their relative position to the prostate. A method was developed to obtain a robust and precise segmentation of seeds in C-arm images, and this approach was tested using clinical datasets.

Method

   A region-based implicit active contour approach was used to delineate implanted seeds. Then, a template-based matching was employed to segment iodine implants whereas a K-means algorithm is implemented to resolve palladium seed clusters. To validate the method, 55 C-arm images from 10 patients were used for the segmentation of iodine sources, whereas 225 C-arm images from 16 patients were used for the palladium case.

Results

   Compared to manual ground truth segmentation of 6,002 iodine seeds and 15,354 palladium seeds, 98.7 % of iodine sources were automatically detected and declustered showing a false-positive rate of only 1.7 %. A total of 98.7 % of palladium sources were automatically detected and declustered with a false-positive rate of only 2.0 %.

Conclusion

   An automated segmentation method was developed that is able to perform the identification and annotation processes of seeds on par with a human expert. This method was shown to be robust and suitable for integration in the dynamic dosimetry workflow of prostate brachytherapy interventions.     

Phase Grouping-Based Needle Segmentation in 3-D Trans-rectal Ultrasound-Guided Prostate Trans-perineal Therapy

A robust and efficient needle segmentation method used to localize and track the needle in 3-D trans-rectal ultrasound (TRUS)-guided prostate therapy is proposed. The algorithmic procedure begins by cropping the 3-D US image containing a needle; then all voxels in the cropped 3-D image are grouped into different line support regions (LSRs) based on the outer product of the adjacent voxels' gradient vector. Two different needle axis extraction methods in the candidate LSR are presented: least-squares fitting and 3-D randomized Hough transform. Subsequent local optimization refines the position of the needle axis. Finally, the needle endpoint is localized by finding an intensity drop along the needle axis. The proposed methods were validated with 3-D TRUS tissue-mimicking agar phantom images, chicken breast phantom images and patient images obtained during prostate cryotherapy. The results of the in vivo test indicate that our method can localize the needle accurately and robustly with a needle endpoint localization accuracy <1.43 mm and detection accuracy >84%, which are favorable for 3-D TRUS-guided prostate trans-perineal therapy.     

Fully Automatic Plaque Segmentation in 3-D Carotid Ultrasound Images

Automatic segmentation of the carotid plaques from ultrasound images has been shown to be an important task for monitoring progression and regression of carotid atherosclerosis. Considering the complex structure and heterogeneity of plaques, a fully automatic segmentation method based on media-adventitia and lumen-intima boundary priors is proposed. This method combines image intensity with structure information in both initialization and a level-set evolution process. Algorithm accuracy was examined on the common carotid artery part of 26 3-D carotid ultrasound images (34 plaques ranging in volume from 2.5 to 456 mm³) by comparing the results of our algorithm with manual segmentations of two experts. Evaluation results indicated that the algorithm yielded total plaque volume (TPV) differences of −5.3 ± 12.7 and −8.5 ± 13.8 mm³ and absolute TPV differences of 9.9 ± 9.5 and 11.8 ± 11.1 mm³. Moreover, high correlation coefficients in generating TPV (0.993 and 0.992) between algorithm results and both sets of manual results were obtained. The automatic method provides a reliable way to segment carotid plaque in 3-D ultrasound images and can be used in clinical practice to estimate plaque measurements for management of carotid atherosclerosis.     

Accuracy evaluation of initialization-free registration for intraoperative 3D-navigation

Purpose An initialization-free approach for perioperative registration in functional endoscopic sinus surgery (FESS) is sought. The quality of surgical navigation relies on registration accuracy of preoperative images to the patient. Although landmark-based registration is fast, it is prone to human operator errors. This study evaluates the accuracy of two well-known methods for segmentation of the occipital bone from CT-images for use in surgical 3D-navigation. Method The occipital bone was segmented for registration without pre-defined correspondences, with the iterative closest point algorithm (ICP). The thresholding plus marching cubes segmentation (TMCS), and the deformable model segmentation (DMS) were compared quantitatively by overlaying the areas of the segmentations in cross-sectional slices, and visually by displaying the pointwise distances between the segmentations in a three-dimensional distance map relative to an expert manual segmentation, taken as a “ground truth”. Results Excellent correspondence between the two methods was achieved; the results showed, however, that the TMCS is closer to the “ground truth”. This is due to the sub-voxel accuracy of the marching cubes algorithm by definition, and the sensitivity of the DMS method to the choice of parameters. The DMS approach, as a gradient-based method, is insensitive to the thresholding initialization. For noisy images and soft tissue delineation a gradient-based method, like the deformable model, performs better. Both methods correspond within minute differences less than 4%. Conclusion These results will allow further minimization of human interaction in the planning phase for intraoperative 3D-navigation, by allowing to automatically create surface patches for registration purposes, ultimately allowing to build an initialization-free, fully automatic registration procedure for navigated Ear-, Nose-, Throat- (ENT) surgery.     

经直肠多模态超声影像评分系统诊断前列腺癌的临床研究

目的建立前列腺癌多模态超声影像评分系统,并评价该评分系统对前列腺癌的诊断价值。 方法选取2016年5月至2017年12月在解放军总医院行超声引导下穿刺活检和（或）手术切除的86例可疑前列腺癌患者,术前对前列腺行经直肠常规超声、剪切波弹性成像、超声造影检查,分析三种模态超声影像特征,并与手术或穿刺病理进行对照。总结前列腺癌经直肠多模态超声影像特征,建立评分系统,并评价该系统对前列腺癌的诊断价值。 结果前列腺癌常规超声表现为低回声、边界不清、形态不规则、内外腺分界不清、包膜侵犯、血流信号丰富且为中心血流;剪切波弹性成像表现为非对称分布,前列腺癌病灶平均弹性模量高于良性病灶［（94.7±44.2）kPa vs（60.8±26.0）kPa］,差异有统计学意义（t=-3.578,P=0.001）;超声造影表现为快速高增强,分布不均匀（低增强区伴点状血管结构,点状、片状或结节状高增强）,内外腺分界不清,包膜或直肠壁侵犯。常规超声、超声造影、弹性成像有1项阳性即诊断为前列腺癌,其敏感度、阴性预测值和准确性分别为98.0%、96.7%和89.5%;三者均为阳性诊断为前列腺癌,其特异度和阳性预测值分别为97.3%和97.1%。 结论经直肠多模态超声影像评分系统可提高超声对前列腺癌的诊断价值。     

A supervised learning framework of statistical shape and probability priors for automatic prostate segmentation in ultrasound images

Prostate segmentation aids in prostate volume estimation, multi-modal image registration, and to create patient specific anatomical models for surgical planning and image guided biopsies. However, manual segmentation is time consuming and suffers from inter-and intra-observer variabilities. Low contrast images of trans rectal ultrasound and presence of imaging artifacts like speckle, micro-calcifications, and shadow regions hinder computer aided automatic or semi-automatic prostate segmentation. In this paper, we propose a prostate segmentation approach based on building multiple mean parametric models derived from principal component analysis of shape and posterior probabilities in a multi-resolution framework. The model parameters are then modified with the prior knowledge of the optimization space to achieve optimal prostate segmentation. In contrast to traditional statistical models of shape and intensity priors, we use posterior probabilities of the prostate region determined from random forest classification to build our appearance model, initialize and propagate our model. Furthermore, multiple mean models derived from spectral clustering of combined shape and appearance parameters are applied in parallel to improve segmentation accuracies. The proposed method achieves mean Dice similarity coefficient value of 0.91 ± 0.09 for 126 images containing 40 images from the apex, 40 images from the base and 46 images from central regions in a leave-one-patient-out validation framework. The mean segmentation time of the procedure is 0.67 ± 0.02 s.     

Development and Preliminary Evaluation of an Anthropomorphic Trans-rectal Ultrasound Prostate Brachytherapy Training Phantom

The quality of the trans-rectal ultrasound (TRUS) image, and thus seed placement during the prostate brachytherapy (PBT) procedure, relies on the user's technical and clinical competency. Simulation-based medical education can provide a structured approach for the acquisition of clinical competencies, but the efficacy of the training relies on the fidelity of the training simulators. In this work, the design, development and preliminary evaluation of an anthropomorphic training phantom for TRUS PBT is described. TRUS clinical patient data informed the design of 3-D printed moulds to fabricate prostate targets. Tissue-mimicking materials were included that had the sonographic characteristics of the prostate and overlying tissues, as well as the clinically relevant physical response, to provide haptic feedback to the user. Through an iterative design process, prototypes were constructed. These prototypes were quantitatively evaluated using a specification list and evaluated by an experienced clinical brachytherapy oncologist; their feedback was implemented, and the results of this evaluation are presented.     

区域生长法结合多竞争最小二乘拟合算法去除乳腺X线摄影图像中胸大肌影

目的 评价区域生长法结合多竞争最小二乘拟合算法去除数字乳腺X线摄影（MG）图像中胸大肌影的价值。方法 分层抽样法随机抽取244例MG数据,对图像进行轮廓选择、增强数据特征、胸大肌边界轮廓粗定位和去噪处理;结合最小二乘法改进区域生长法,拟合胸大肌的边界轮廓函数,使用最优轮廓函数制作胸大肌掩膜图,计算预测图与人工勾画图交并比（IOU）及像素精度（PA）,评价其去除MG图像中的胸大肌影的价值。结果 基于上述方法所获胸大肌轮廓较为平滑,较少漏分割或过度分割,结果误差较小;还原胸大肌边界轮廓与手动分割结果非常接近,平均IOU为（89.76±4.28）%,平均PA为（89.98±3.91）%。结论 结合区域生长法与多竞争最小二乘拟合算法可用于去除MG图像中的胸大肌影。     

Automatic Shape-Based Level Set Segmentation for Needle Tracking in 3-D TRUS-Guided Prostate Brachytherapy

Prostate brachytherapy is an effective treatment for early prostate cancer. The success depends critically on the correct needle implant positions. We have devised an automatic shape-based level set segmentation tool for needle tracking in 3-D transrectal ultrasound (TRUS) images, which uses the shape information and level set technique to localize the needle position and estimate the endpoint of needle in real-time. The 3-D TRUS images used in the evaluation of our tools were obtained using a 2-D TRUS transducer from Ultrasonix (Richmond, BC, Canada) and a computer-controlled stepper motor system from Thorlabs (Newton, NJ, USA). The accuracy and feedback mechanism had been validated using prostate phantoms and compared with 3-D positions of these needles derived from experts' readings. The experts' segmentation of needles from 3-D computed tomography images was the ground truth in this study. The difference between automatic and expert segmentations are within 0.1 mm for 17 of 19 implanted needles. The mean errors of automatic segmentations by comparing with the ground truth are within 0.25 mm. Our automated method allows real-time TRUS-based needle placement difference within one pixel compared with manual expert segementation.     

Multiresolution texture based adaptive clustering algorithm for breast lesion segmentation

Objective: A specific algorithm is presented for the automatic extraction of breast tumors in ultrasonic imaging. Method: The algorithm involves two-dimensional adaptive K-means clustering of the gray scale and textural feature images. The segmentation problem is formulated as a maximum a posteriori (MAP) estimation problem. The MAP estimation is achieved using Besag's iterated conditional modes algorithm for the minimization of an energy function. This function has three components: the first constrains the region to be close to the data; the second imposes spatial continuity; and the third takes into consideration the texture of the various regions. A multiresolution implementation of the algorithm is performed using a wavelets basis. Results: Experiments were carried out on synthetic images and on in vivo breast ultrasound images. Various parameters involved in the algorithm are discussed to evaluate the robustness and accuracy of the segmentation method. Conclusion: Including textural features in the segmentation of ultrasonic data improves the robustness of the algorithm and makes the segmentation result less parameter dependent.     

Spectrum-analysis and neural networks for imaging to detect and treat prostate cancer

Conventional B-mode ultrasound currently is the standard means of imaging the prostate for guiding prostate biopsies and planning brachytherapy to treat prostate cancer. Yet B-mode images do not adequately display cancerous lesions of the prostate. Ultrasonic tissue-type imaging based on spectrum analysis of radiofrequency (rf) echo signals has shown promise for overcoming the limitations of B-mode imaging for visualizing prostate tumors. This method of tissue-type imaging utilizes nonlinear classifiers, such as neural networks, to classify tissue based on values of spectral parameter and clinical variables. Two- and three-dimensional images based on these methods demonstrate potential for guiding prostate biopsies and targeting radiotherapy of prostate cancer. Two-dimensional images are being generated in real time in ultrasound scanners used for real-time biopsy guidance and have been incorporated into commercial dosimetry software used for brachytherapy planning. Three-dimensional renderings show promise for depicting locations and volumes of cancer foci for disease evaluation to assist staging and treatment planning, and potentially for registration or fusion with CT images for targeting external-beam radiotherapy.     

Characterization of a sequential pipeline approach to automatic tissue segmentation from brain MR Images

Objective Quantitative analysis of gray matter and white matter in brain magnetic resonance imaging (MRI) is valuable for neuroradiology and clinical practice. Submission of large collections of MRI scans to pipeline processing is increasingly important. We characterized this process and suggest several improvements. Materials and methods To investigate tissue segmentation from brain MR images through a sequential approach, a pipeline that consecutively executes denoising, skull/scalp removal, intensity inhomogeneity correction and intensity-based classification was developed. The denoising phase employs a 3D-extension of the Bayes–Shrink method. The inhomogeneity is corrected by an improvement of the Dawant et al.’s method with automatic generation of reference points. The N3 method has also been evaluated. Subsequently the brain tissue is segmented into cerebrospinal fluid, gray matter and white matter by a generalized Otsu thresholding technique. Intensive comparisons with other sequential or iterative methods have been carried out using simulated and real images. Results The sequential approach with judicious selection on the algorithm selection in each stage is not only advantageous in speed, but also can attain at least as accurate segmentation as iterative methods under a variety of noise or inhomogeneity levels. Conclusion A sequential approach to tissue segmentation, which consecutively executes the wavelet shrinkage denoising, scalp/skull removal, inhomogeneity correction and intensity-based classification was developed to automatically segment the brain tissue into CSF, GM and WM from brain MR images. This approach is advantageous in several common applications, compared with other pipeline methods.