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.

     

Prostate multimodality image registration based on B-splines and quadrature local energy

Purpose  

Needle biopsy of the prostate is guided by Transrectal Ultrasound (TRUS) imaging. The TRUS images do not provide proper spatial localization of malignant tissues due to the poor sensitivity of TRUS to visualize early malignancy. Magnetic Resonance Imaging (MRI) has been shown to be sensitive for the detection of early stage malignancy, and therefore, a novel 2D deformable registration method that overlays pre-biopsy MRI onto TRUS images has been proposed.     

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.     

Role of transrectal ultrasound in the diagnosis of extracapsular prostate cancer

Introduction

Transrectal ultrasound (TRUS) has significantly improved the diagnostic rate, nevertheless, the correlation between findings on TRUS and clinically significant prostate cancer (PCa) is not completely understood. The purpose of this study was to evaluate the diagnostic accuracy and utility of preoperative TRUS in patients with PCa to define the sonographic signs of cohesion of the Denonvilliers’ fascia (DF) to prostate capsula (PC) to detect the local advancement of the disease.

Methods

Between April 2010 and May 2013, at our Department of Urology, the clinical anatomy of preoperative regions and excised specimens was reviewed macroscopically for 68 cases of radical retropubic prostatectomy for PCa and compared to ultrasound images obtained by TRUS.

Results

Pathological analysis detected on the surface of the prostate the DF fused with the PC at the midpoint of the prostatic posterior surface in 94 % of the cases, in 4 % the DF remained at a certain distance from PC in this region and in 1 case lateral pelvic fascia fused with PC and little adipose tissue was present between them (P < 0.005). The TRUS allowed a more precise result in terms of tumor extension to DF with a detection rate of 95 %. (P < 0.001).

Conclusion

In our opinion, it is very important to recognize preoperatively the possibility of cancer extracapsular extension to the DF and to the rectum wall, using a simple and low cost examination as TRUS. The knowledge of the fascial structures anatomy around the prostate is necessary to perform a nerve-sparing radical prostatectomy, avoiding excessive bleeding, iatrogenic positive surgical margin, and post-operative complications.     

Towards ultrasound probe positioning optimization during prostate needle biopsy using pressure feedback

Purpose

Accurate Transrectal Ultrasound (TRUS)-guided prostate needle biopsy requires registering preoperative 3D TRUS or MR image, in which tumors and other suspicious areas are visible, to intraoperative 2D TRUS images. Such image registration is time-consuming while its real-time implementation is yet to be developed. To bypass this registration step, robotic needle biopsy systems can be used to place the US probe at the same position relative to the prostate during the 3D and 2D image acquisition to ensure similar prostate deformation. To have such similar deformation, only visual feedback is not sufficient as such feedback can be used to only guarantee that the whole prostate is within the field of view irrespective of the probe’s orientation. As such, contact pressure feedback can be utilized to ensure consistent minimum contact between the probe and prostate.

Method

A robotic system is proposed where a TRUS probe with pressure sensor array is used. The contact pressure can be measured during imaging and used to provide feedback in conjunction with an optimization algorithm for consistent probe positioning. The robotic system is driven by the feedback to position the probe such that pressure pattern of the sensors during 2D image acquisition is similar to the pressure pattern during 3D image acquisition. The proposed method takes into account the patient’s body movement expected during image acquisition. In this study, an in silico phantom is used where the simulated contact pressure distribution required in the optimization algorithm is obtained using a prostate finite element model.

Result

Starting from an arbitrary position where the probe contacts the phantom, this position was varied systematically until a position corresponding to maximum pressure pattern similarity between contact pressure patterns corresponding to the 2D and 3D imaging was achieved successfully.

Conclusion

Results obtained from the in silico phantom study indicate that the proposed technique is capable of ensuring having only minimal relative prostate deformation between preoperative image acquisition and intraoperative imaging used for guiding needle biopsy, paving the way for faster and more accurate registration.     

Deep dense multi-path neural network for prostate segmentation in magnetic resonance imaging

Purpose

We propose an approach of 3D convolutional neural network to segment the prostate in MR images.

Methods

A 3D deep dense multi-path convolutional neural network that follows the framework of the encoder–decoder design is proposed. The encoder is built based upon densely connected layers that learn the high-level feature representation of the prostate. The decoder interprets the features and predicts the whole prostate volume by utilizing a residual layout and grouped convolution. A set of sub-volumes of MR images, centered at the prostate, is generated and fed into the proposed network for training purpose. The performance of the proposed network is compared to previously reported approaches.

Results

Two independent datasets were employed to assess the proposed network. In quantitative evaluations, the proposed network achieved 95.11 and 89.01 Dice coefficients for the two datasets. The segmentation results were robust to variations in MR images. In comparison experiments, the segmentation performance of the proposed network was comparable to the previously reported approaches. In qualitative evaluations, the segmentation results by the proposed network were well matched to the ground truth provided by human experts.

Conclusions

The proposed network is capable of segmenting the prostate in an accurate and robust manner. This approach can be applied to other types of medical images.

     

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.     

Liver segmentation for contrast-enhanced MR images using partitioned probabilistic model

Purpose  

Liver volume segmentation is important in computer assisted diagnosis and therapy planning of liver tumors. Manual segmentation is time-consuming, tedious and error prone, so automated methods are needed. Automatic segmentation of MR images is more challenging than for CT images, so a robust system was developed.     

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.     

3D prostate model formation from non-parallel 2D ultrasound biopsy images

Biopsy of the prostate using 2D transrectal ultrasound (TRUS) guidance is the current gold standard for diagnosis of prostate cancer; however, the current procedure is limited by using 2D biopsy tools to target 3D biopsy locations. We propose a technique for patient-specific 3D prostate model reconstruction from a sparse collection of non-parallel 2D TRUS biopsy images. Our method conforms to the restrictions of current TRUS biopsy equipment and could be efficiently incorporated into current clinical biopsy procedures for needle guidance without the need for expensive hardware additions. In this paper, the model reconstruction technique is evaluated using simulated biopsy images from 3D TRUS prostate images of 10 biopsy patients. All reconstructed models are compared to their corresponding 3D manually segmented prostate models for evaluation of prostate volume accuracy and surface errors (both regional and global). The number of 2D TRUS biopsy images used for prostate modeling was varied to determine the optimal number of images necessary for accurate prostate surface estimation.     

Automatic cardiac ventricle segmentation in MR images: a validation study

Purpose  

Segmenting the cardiac ventricles in magnetic resonance (MR) images is required for cardiac function assessment. Numerous segmentation methods have been developed and applied to MR ventriculography. Quantitative validation of these segmentation methods with ground truth is needed prior to clinical use, but requires manual delineation of hundreds of images. We applied a well-established method to this problem and rigorously validated the results.     

A cost-sensitive extension of AdaBoost with markov random field priors for automated segmentation of breast tumors in ultrasonic images

Purpose  

A cost-sensitive extension of AdaBoost based on Markov random field (MRF) priors was developed to train an ensemble segmentation process which can avoid irregular shape, isolated points and holes, leading to lower error rate. The method was applied to breast tumor segmentation in ultrasonic images.     

Expert-driven label fusion in multi-atlas-based segmentation of the prostate using weighted atlases

Purpose

Automated segmentation is required for radiotherapy treatment planning, and multi-atlas methods are frequently used for this purpose. The combination of multiple intermediate results from multi-atlas segmentation into a single segmentation map can be achieved by label fusion. A method that includes expert knowledge in the label fusion phase of multi-atlas-based segmentation was developed. The method was tested by application to prostate segmentation, and the accuracy was compared to standard techniques.

Methods

The selective and iterative method for performance level estimation (SIMPLE) algorithm for label fusion was modified with a weight map given by an expert that indicates the importance of each region in the evaluation of segmentation results. Voxel-based weights specified by an expert when performing the label fusion step in atlas-based segmentation were introduced into the modified SIMPLE algorithm. These weights incorporate expert knowledge on accuracy requirements in different regions of a segmentation. Using this knowledge, segmentation accuracy in regions known to be important can be improved by sacrificing segmentation accuracy in less important regions. Contextual information such as the presence of vulnerable tissue is then used in the segmentation process. This method using weight maps to fine-tune the result of multi-atlas-based segmentation was tested using a set of 146 atlas images consisting of an MR image of the lower abdomen and a prostate segmentation. Each image served as a target in a set of leave-one-out experiments. These experiments were repeated for a weight map derived from the clinical practice in our hospital.

Results

The segmentation accuracy increased 6 % in regions that border vulnerable tissue using expert-specified voxel-based weight maps. This was achieved at the cost of a 4 % decrease in accuracy in less clinically relevant regions.

Conclusion

The inclusion of expert knowledge in a multi-atlas-based segmentation procedure was shown to be feasible for prostate segmentation. This method allows an expert to ensure that automatic segmentation is most accurate in critical regions. This improved local accuracy can increase the practical value of automatic segmentation.     

A partial augmented reality system with live ultrasound and registered preoperative MRI for guiding robot-assisted radical prostatectomy

We propose an image guidance system for robot assisted laparoscopic radical prostatectomy (RALRP). A virtual 3D reconstruction of the surgery scene is displayed underneath the endoscope’s feed on the surgeon’s console. This scene consists of an annotated preoperative Magnetic Resonance Image (MRI) registered to intraoperative 3D Trans-rectal Ultrasound (TRUS) as well as real-time sagittal 2D TRUS images of the prostate, 3D models of the prostate, the surgical instrument and the TRUS transducer. We display these components with accurate real-time coordinates with respect to the robot system. Since the scene is rendered from the viewpoint of the endoscope, given correct parameters of the camera, an augmented scene can be overlaid on the video output. The surgeon can rotate the ultrasound transducer and determine the position of the projected axial plane in the MRI using one of the registered da Vinci instruments. This system was tested in the laboratory on custom-made agar prostate phantoms. We achieved an average total registration accuracy of 3.2  ±  1.3 mm. We also report on the successful application of this system in the operating room in 12 patients. The average registration error between the TRUS and the da Vinci system for the last 8 patients was 1.4  ±  0.3 mm and average target registration error of 2.1  ±  0.8 mm, resulting in an in vivo overall robot system to MRI mean registration error of 3.5 mm or less, which is consistent with our laboratory studies.     

Automatic 3D segmentation of individual facial muscles using unlabeled prior information

Purpose  

Segmentation of facial soft tissues is required for surgical planning and evaluation, but this is laborious using manual methods and has been difficult to achieve with digital segmentation methods. A new automatic 3D segmentation method for facial soft tissues in magnetic resonance imaging (MRI) images was designed, implemented, and tested.     

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.     

Transrectal ultrasound in patients with hematospermia

Introduction

To illustrate the lesions detected with transrectal ultrasound (TRUS) in patients with hematospermia.

Material and methods

This study included 74 male patients (25–73 years old) affected by hematospermia. Clinical history was obtained and all patients underwent rectal examination as well as TRUS examination in both axial and coronal planes to evaluate the prostate, ejaculatory ducts and seminal vesicles. Biopsy was performed in 10 patients.

Results

Abnormalities were detected in 59 patients. Calculi (n = 20) were seen within the prostate, seminal vesicles and along the course of the ejaculatory ducts. Chronic prostatitis (n = 14) appeared as hyperechoic and hypoechoic areas within the prostate with capsule thickening suggesting seminal vesiculitis (n = 8). Granulomatous prostatitis (n = 3) appeared as hyperechoic and calcified areas scattered within the prostate and the seminal vesicles. Hypoechoic focal lesions and heterogeneous texture were seen in prostate cancer (n = 5). Utricular cysts (n = 3) appeared as small midline lesions, and Mullerian duct cysts (n = 8) appeared as larger midline cysts protruding above the prostate. Ejaculatory duct cysts (n = 4) appeared as thick walled cystic lesions along the course of the ejaculatory duct. Seminal vesicle cysts were detected in 2 patients.

Conclusion

Our conclusion is that TRUS is a safe, non-invasive technique which can be used to detect lesions of the prostate, seminal vesicles and the ejaculatory ducts in patients with hematospermia.     

Endocardial boundary extraction in left ventricular echocardiographic images using fast and adaptive B-spline snake algorithm

Purpose  

A fast and robust algorithm was developed for automatic segmentation of the left ventricular endocardial boundary in echocardiographic images. The method was applied to calculate left ventricular volume and ejection fraction estimation.     

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.