Prostate Contours Research Articles

Deep Learning-Based Registration of MR and Treatment Planning Ultrasound Images for HDR Prostate Brachytherapy

Propagation of contours from high-quality magnetic resonance (MR) images to treatment planning ultrasound (US) images with severe needle artifacts is a challenging task, which can greatly aid the organ or intraprostatic lesion contouring in high dose rate (HDR) prostate brachytherapy. In this study, a deep learning approach was developed to automatize this registration procedure for HDR brachytherapy practice.With the approval from the institutional review board, the MR and US images with manual prostate contours were collected from our clinical database and processed to construct the deep learning dataset. A deep learning framework based on the weakly-supervised strategy was proposed for the registration of prostate MR images and US images after the needle insertion, which consisted of two segmentation networks and a deformable registration network. Specifically, two 3D V-Net was trained for the prostate segmentation on the MR and US images separately, to generate the weak supervision labels automatically for the registration network training. Besides the image pair, the corresponding prostate probability maps from the segmentation were further fed to the registration network to improve the registration accuracy, and the deformation matrix was the output. A random augmentation method was designed to alleviate the map overfitting problem during the network training. The overlap between the deformed and fixed prostate contours was analyzed to evaluate the registration accuracy.Clinical data from 121, 104 and 63 patient cases were collected and utilized for the MR and US image segmentation networks, and the registration network learning, respectively. The mean DSC, center-of-mass (COM) distance, Hausdorff distance (HD) and averaged symmetric surface distance (ASSD) results for the registration of prostate contours were 0.87 ± 0.05, 1.70 ± 0.89 mm, 7.21 ± 2.07 mm, 1.61 ± 0.64 mm, respectively. By providing the prostate probability map from the segmentation to the registration network, as well as applying the random map augmentation method, the evaluation results of the four metrics were all improved, such as an increase of DSC from 0.83 ± 0.08 to 0.86 ± 0.06 and from 0.86 ± 0.06 to 0.87 ± 0.05, respectively.This study first worked on the deep learning-based registration about the treatment planning US image for HDR prostate brachytherapy. A novel segmentation-based registration framework was proposed for this multi-modality registration problem, which not only largely saved the labor work on the data preparation, but also improved the registration accuracy. The evaluation results showed the potential of this approach in HDR brachytherapy to automatize current clinical procedures.

Deep-Learning-Based Multi-Organ Auto-Segmentation on 3D Transrectal Ultrasound for Ultrasound-Guided Prostate Brachytherapy

Ultrasound (US) imaging has been widely used in image-guided prostate brachytherapy. Current prostate brachytherapy uses transrectal US (TRUS) images for implant guidance, where contours of prostate and organs-at risk are necessary for treatment planning and dose evaluation. This work aims to develop a deep learning-based method for pelvic multi-organ TRUS segmentation to improve TRUS-guided prostate brachytherapy.We developed an anchor-free mask convolutional neural network (CNN) that consist of three subnetworks, i.e., a backbone, a fully convolutional one-state object detector (FCOS) head, and a mask head. The backbone extracts multi-level and multi-scale features from US image. The FOCS head utilizes these features to detect the location of volume-of-interest (VOI) of each organ. In contrast to previous mask regional CNN (Mask R-CNN) method, which perform detection and segmentation within several pre-defined potential VOIs (called as anchors), FCOS head is anchor-free, which can capture spatial correlation of multi-organs due to whole image input. Mask head performs segmentation on each detected VOI, where a spatial attention strategy is integrated into mask head that helps to focus on informative features that can well-represent the organ boundary and suppress noise introduced by previous subnetwork and by arrival TRUS image itself. For evaluation, we retrospectively investigated 80 prostate cancer patients by a five-fold cross-validation. Prostate, bladder, rectum and urethra were segmented and compared with manual contours using Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and mean surface distance (MSD).For all patients, the DSC, HD95 and MSD were 0.93 ± 0.03, 2.28 ± 0.64 mm and 0.57 ± 0.20 mm for prostate; 0.75 ± 0.12, 2.58 ± 0.7 mm and 1.26 ± 0.23 mm for bladder; 0.90 ± 0.07, 1.65 ± 0.52 mm and 0.34 ± 0.16 mm for rectum; and 0.86 ± 0.07, 1.85 ± 1.71 mm and 0.44 ± 0.32mm for urethra. The proposed method outperforms two state-of-art methods (U-Net and Mask R-CNN) with better agreement with physicians' manual contours and less mis-identified speckles.We proposed an automatic deep learning-based pelvic multi-organ segmentation on 3D TRUS images for TRUS-guided prostate brachytherapy. The proposed method could provide fast and accurate multi-organ segmentations for prostate, bladder, rectum and urethra, and outperformed two competing methods. This deep-learning-based multi-organ auto-segmentation may play an important role in future clinical practice to improve auto-planning and auto-evaluation during TRUS-guided prostate brachytherapy.

Comparing Deep Learning Based Prostate Delineation With Manual Contouring From Multiple Experts

Accurate contouring of the target is very important in radiation therapy treatment planning. Unlike most other cancers where the radiation target occupies a small area of an organ, prostate cancer treatment involves the irradiation of the entire prostate. This study evaluates the quality of prostate contours generated from a deep learning segmentation (DLSEG) model.A total of 23 prostate cancer patients who did not underwent prostatectomy was randomly selected. The original contours used clinically was carefully quality checked and revised when necessary by one expert radiation oncologist (RO) and regarded as the ground truth (GT). Two additional ROs were invited to perform manual contouring of the prostate from scratch. Auto contours (labelled as AI) generated by a research version of DLSEG was then compared with those from manual delineations. A paired t-test was employed for statistical comparison. A comparative geometric analysis of the manual and automatic delineations was performed to quantify the multi-observer delineation variability, including dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and mean surface distance (MSD).Using GT contour as reference, the contours from three additional RO achieved an average of 0.81 ± 0.04 for DSC, 0.60 ± 0.16cm and 0.21 ± 0.05cm for HD95 and MSD, respectively. In contrast, AI contours achieved an average of 0.83 ± 0.05 for DSC, 0.60 ± 0.18cm and 0.21 ± 0.07 cm for HD95 and MSD, respectively. No statistical difference was found for the delineation accuracy between the three observers (P > 0.05). AI contours were considered to have similar performance to the three human experts with all geometric metrics (P > 0.05).The DLSEG model for prostate contouring tested demonstrates similar performance in terms of accuracy compared with expert ROs.

Real-Time Motion Tracking Based on Orthogonal Cine MRI During MR-Guided Radiation Therapy for Prostate Cancer

In contrast to radiographic imaging with implanted radio-opaque fiducials, the high soft tissue contrast and noninvasive nature of MRI are advantageous for real-time motion tracking of prostate motion. The purpose of this study is to investigate the feasibility of tracking the intrafraction prostate motion using an intensity-based template registration technique between real-time 2D cine and 3D MRI acquired during MR-guided Adaptative Radiation Therapy (MRgART).The motion tracking algorithm includes two steps: (1) creating a template by rigidly registering a set of cine images with a 3D reference MRI, and (2) tracking the target motion by registering incoming (i.e., real-time) cine with the template with a known relationship to the 3D volume. The daily 3D T2 MRI and 2D T2/T1 bFFE real-time cine MRI acquired on a 1.5T MR-Linac during MRgART for 6 prostate cancer patients were selected to test the algorithm limits. The cine images were acquired with a temporal resolution of 0.2 s for a total duration of 9-11 minutes interleaved between coronal and sagittal orientations. A 2D template image set was generated in the coronal and sagittal planes using the cine data acquired during the first 20 s registered to the 3D volume using in-plane rigid-body image registration based on a region of interest defined by the prostate contour on 3D T2 MRI. Motion tracking of the prostate was performed by registering the rest of the 2D cine series with the corresponding template. Manually delineated contours on sampled cine frames were used as the ground truth. Tracking accuracy was defined as the standard deviation of the error (SDE) between the center of mass (CM) of the ground-truth and tracked motions in 1 min. Prostate drift was evaluated by tracking the CM shift with the algorithm every 8-9 s for 9-11 min.The prostate tracking algorithm was qualitatively validated by visual assessment of 6 prostate cases. Overall, the tracking was found robust to implant-induced image artefacts in two cases, large change in bladder size in one case, and body motion in one other case. The tracking algorithm was also validated quantitatively on 2 cases for which ground truth contours were available and reliable. Mean SDE for the two cases was 0.45, 0.32, and 0.31 mm in superior-inferior, left-right, and anterior-posterior directions, respectively. A continuous motion drift of the prostate was observed over a 600 s period for one of these two cases and was accurately tracked by the technique.We have demonstrated the feasibility to track prostate motion based on real-time orthogonal cine MRI without implanting fiducials. With further investigation on more patients and following careful workflow, the real-time motion tracking technique may be implemented in MRgART to manage intrafraction motion.H. Jassar: None. A. Tai: None. X. Chen: None. T. Keiper: None. E.S. Paulson: Research Grant; Siemens Healthineers, Elekta Instruments AB.F. Lathuiliere: None. S. Bériault: None. D. Cooper: None. F. Hebert: None. L. Savard: None. S. Cloake: None. W.A. Hall: Research Grant; Elekta, National Cancer Institute, American Cancer Society. C.A. Lawton: None. A. Li: Research Grant; Elekta AB, Accuray Inc, Siemens Healthineers, Manteia Med. Honoraria; Elekta AB, Accuray Inc. Patent/License Fees/Copyright; Manteia Med.

Geometrical imaging accuracy, image quality and plan quality for prostate cancer treatments on a 1.5 T MRLinac in patients with a unilateral hip implant

Purpose. To assess the feasibility of prostate cancer radiotherapy for patients with a hip implant on an 1.5 T MRI-Linac (MRL) in terms of geometrical image accuracy, image quality, and plan quality. Methods. Pretreatment MRI images on a 1.5 T MRL and 3 T MRI consisting of a T2-weighted 3D delineation scan and main magnetic field homogeneity (B 0) scan were performed in six patients with a unilateral hip implant. System specific geometrical errors due to gradient nonlinearity were determined for the MRL. Within the prostate and skin contour, B 0 inhomogeneity, gradient nonlinearity error and the total geometrical error (vector summation of the prior two) was determined. Image quality was determined by visually scoring the extent of implant-born image artifacts. A treatment planning study was performed on five patients to quantify the impact of the implant on plan quality, in which conventional MRL IMRT plans were created, as well as plans which avoid radiation through the left or right femur. Results. The total maximum geometrical error in the prostate was <1 mm and the skin contour <1.7 mm; in all cases the machine-specific gradient error was most dominant. The B 0 error for the MRlinac MRI could partly be predicted based on the pre-treatment 3 T scan. Image quality for all patients was sufficient at 1.5 T MRL. Plan comparison showed that, even with avoidance of the hips, in all cases sufficient target coverage could be obtained with similar D1cc and D5cc to rectum and bladder, while V28Gy was slightly poorer in only the rectum for femur avoidance. Conclusion. We showed that geometrical accuracy, image quality and plan quality for six prostate patients with a hip implant or hip fixation treated on a 1.5 T MRL did not show relevant deterioration for the used image settings, which allowed safe treatment.

How does CBCT reconstruction algorithm impact on deformably mapped targets and accumulated dose distributions?

PurposeWe performed quantitative analysis of differences in deformable image registration (DIR) and deformable dose accumulation (DDA) computed on CBCT datasets reconstructed using the standard (Feldkamp‐Davis‐Kress: FDK_CBCT) and a novel iterative (iterative_CBCT) CBCT reconstruction algorithms.MethodsBoth FDK_CBCT and iterative_CBCT images were reconstructed for 323 fractions of treatment for 10 prostate cancer patients. Planning CT images were deformably registered to each CBCT image data set. After daily dose distributions were computed, they were mapped to planning CT to obtain deformed doses. Dosimetric and image registration results based CBCT images reconstructed by two algorithms were compared at three levels: (A) voxel doses over entire dose calculation volume, (B) clinical constraint results on targets and sensitive structures, and (C) contours propagated to CBCT images using DIR results based on three algorithms (SmartAdapt, Velocity, and Elastix) were compared with manually delineated contours as ground truth.Results(A) Average daily dose differences and average normalized DDA differences between FDK_CBCT and iterative_CBCT were ≤1 cGy. Maximum daily point dose differences increased from 0.22 ± 0.06 Gy (before the deformable dose mapping operation) to 1.33 ± 0.38 Gy after the deformable dose mapping. Maximum differences of normalized DDA per fraction were up to 0.80 Gy (0.42 ± 0.19 Gy). (B) Differences in target minimum doses were up to 8.31 Gy (−0.62 ± 4.60 Gy) and differences in critical structure doses were 0.70 ± 1.49 Gy. (C) For mapped prostate contours based on iterative_CBCT (relative to standard FDK_CBCT), dice similarity coefficient increased by 0.10 ± 0.09 (p < 0.0001), mass center distances decreased by 2.5 ± 3.0 mm (p < 0.00005), and Hausdorff distances decreased by 3.3 ± 4.4 mm (p < 0.00015).ConclusionsThe new iterative CBCT reconstruction algorithm leads to different mapped volumes of interest, deformed and cumulative doses than results based on conventional FDK_CBCT.

Impact of the implementation of a Contouring Atlas on Therapeutic Radiographer inter-observer contour variation in prostate radiotherapy

Purpose: The clinical implementation of MR-guided adaptive radiotherapy requires fast, accurate delineation of target volumes and organs at risk (OAR's). It is important with the introduction of new online imaging strategies to mitigate the potential for contouring inaccuracies, as they could potentially result in treatment errors. To support the introduction of radiographer-led real-time MR-guided adaptive radiotherapy on the MR-Linac (MRL), an MR contouring atlas for prostate radiotherapy delineation guidance was developed. This tool was based on the ‘Male Pelvis Normal Tissue RTOG Consensus Contouring’ recommendations and local guidelines, and its impact on inter-observer variation was subsequently determined. Methods: Multi-disciplinary consensus on the contouring of the prostate, seminal vesicles and associated OAR's was obtained by developing a contouring guide (3 MRL radiographers, 2 clinical oncologists and 1 diagnostic radiographer). Contours were defined on T2-weighted three-dimensional turbo spin echo sequences, reconstructed axially (T2w 3D Tra) acquired on the MRL. To assess the guide's utility, 9 radiographers with varying MRL experience contoured 5 MRI scans in the Monaco treatment planning system, from 5 different patients (n= 25). Each radiographer contoured the prostate, seminal vesicles, bladder, and rectum on each data set before and after the introduction of the atlas. The ‘after’ contours were generated &gt;21 days following the ‘before’ contours to minimise the effects of repetition. In addition to DICE coefficients and descriptive statistics, inter-observer contour variations, time to contour and observer contouring confidence was determined prior to and following the introduction of the atlas utilising a 5-point Likert scale (observers score confidence 1 not confident to 5 extremely confident). Results: The contouring atlas has been agreed by the multidisciplinary team incorporating locally defined gold-standard contours and RTOG guidance. Five sets of images from 5 different patients have been acquired on the MRL (T2w 3D Tra) and to date the ‘before’ contours have been completed. Mean contouring time without the atlas for all contours was 54 minutes with the rectum and prostate contouring taking the greatest amount of time, a mean time of 15 minutes each. Contour confidence levels varied between participants greatly. Minimum contour variability between the observers was for the bladder contour, with the maximum range being 22.0cm3. This corresponded with the participants scoring the bladder contour with the higher confidence level rates (majority scoring ≥ 3). Prostate and rectum structures had the greatest contour variability between observers with the maximum range being 32.6cm3 and 36.1 cm3 respectively. Confidence levels also corresponded with this large variation with majority of observers scoring ≤ 2. The same radiographers will repeat the process with the aid of the contouring atlas. Conclusion: It is anticipated that the new atlas for contouring prostate and surrounding OAR anatomy during both online and offline radiotherapy planning scenarios will reduce inter-observer variability, uncertainty and the time needed to contour. This will be of particular benefit in future adapt to shape pathways.

MR to ultrasound image registration with segmentation‐based learning for HDR prostate brachytherapy

Propagation of contours from high-quality magnetic resonance (MR) images to treatment planning ultrasound (US) images with severe needle artifacts is a challenging task, which can greatly aid the organ contouring in high dose rate (HDR) prostate brachytherapy. In this study, a deep learning approach was developed to automatize this registration procedure for HDR brachytherapy practice. Because of the lack of training labels and difficulty of accurate registration from inferior image quality, a new segmentation-based registration framework was proposed for this multi-modality image registration problem. The framework consisted of two segmentation networks and a deformable registration network, based on the weakly -supervised registration strategy. Specifically, two 3D V-Nets were trained for the prostate segmentation on the MR and US images separately, to generate the weak supervision labels for the registration network training. Besides the image pair, the corresponding prostate probability maps from the segmentation were further fed to the registration network to predict the deformation matrix, and an augmentation method was designed to randomly scale the input and label probability maps during the registration network training. The overlap between the deformed and fixed prostate contours was analyzed to evaluate the registration accuracy. Three datasets were collected from our institution for the MR and US image segmentation networks, and the registration network learning, which contained 121, 104, and 63 patient cases, respectively. The mean Dice similarity coefficient (DSC) results of the two prostate segmentation networks are 0.86±0.05 and 0.90±0.03, for MR images and the US images after the needle insertion, respectively. The mean DSC, center-of-mass (COM) distance, Hausdorff distance (HD), and averaged symmetric surface distance (ASSD) results for the registration of manual prostate contours were 0.87±0.05, 1.70±0.89mm, 7.21±2.07mm, 1.61±0.64mm, respectively. By providing the prostate probability map from the segmentation to the registration network, as well as applying the random map augmentation method, the evaluation results of the four metrics were all improved, such as an increase in DSC from 0.83±0.08 to 0.86±0.06 and from 0.86±0.06 to 0.87±0.05, respectively. A novel segmentation-based registration framework was proposed to automatically register prostate MR images to the treatment planning US images with metal artifacts, which not only largely saved the labor work on the data preparation, but also improved the registration accuracy. The evaluation results showed the potential of this approach in HDR prostate brachytherapy practice.

Automated contour propagation of the prostate from pCT to CBCT images via deep unsupervised learning.

To develop and evaluate a deep unsupervised learning (DUL) framework based on a regional deformable model for automated prostate contour propagation from planning computed tomography (pCT) to cone-beam CT (CBCT). We introduce a DUL model to map the prostate contour from pCT to on-treatment CBCT. The DUL framework used a regional deformable model via narrow-band mapping to augment the conventional strategy. Two hundred and fifty-one anonymized CBCT images from prostate cancer patients were retrospectively selected and divided into three sets: 180 were used for training, 12 for validation, and 59 for testing. The testing dataset was divided into two groups. Group 1 contained 50 CBCT volumes, with one physician-generated prostate contour on CBCT image. Group 2 contained nine CBCT images, each including prostate contours delineated by four independent physicians and a consensus contour generated using the STAPLE method. Results were compared between the proposed DUL and physician-generated contours through the Dice similarity coefficients (DSCs), the Hausdorff distances, and the distances of the center-of-mass. The average DSCs between DUL-based prostate contours and reference contours for test data in group 1 and group 2 consensus were 0.83±0.04, and 0.85±0.04, respectively. Correspondingly, the mean center-of-mass distances were 3.52mm±1.15mm, and 2.98mm±1.42mm, respectively. This novel DUL technique can automatically propagate the contour of the prostate from pCT to CBCT. The proposed method shows that highly accurate contour propagation for CBCT-guided adaptive radiotherapy is achievable via the deep learning technique.

Multi-task edge-recalibrated network for male pelvic multi-organ segmentation on CT images

Automated male pelvic multi-organ segmentation on CT images is highly desired for applications, including radiotherapy planning. To further improve the performance and efficiency of existing automated segmentation methods, in this study, we propose a multi-task edge-recalibrated network (MTER-Net), which aims to overcome the challenges, including blurry boundaries, large inter-patient appearance variations, and low soft-tissue contrast. The proposed MTER-Net is equipped with the following novel components. (a) To exploit the saliency and stability of femoral heads, we employed a light-weight localization module to locate the target region and efficiently remove the complex background. (b) We add an edge stream to the regular segmentation stream to focus on processing the edge-related information, distinguish the organs with blurry boundaries, and then boost the overall segmentation performance. Between the regular segmentation stream and edge stream, we introduce an edge recalibration module at each resolution level to connect the intermediate layers and deliver the higher-level activations from the regular stream to the edge stream to denoise the irrelevant activations. (c) Finally, using a 3D Atrous Spatial Pyramid Pooling (ASPP) feature fusion module, we fuse the features at different scales in the regular stream and the predictions from the edge stream to form the final segmentation result. The proposed segmentation network was evaluated on 200 prostate cancer patient CT images with manually delineated contours of bladder, rectum, seminal vesicle, and prostate. The segmentation performance of the proposed method was quantitatively evaluated using three metrics including Dice similarity coefficient (DSC), average surface distance (ASD), and 95% surface distance (95SD). The proposed MTER-Net achieves average DSC of 86.35%, ASD of 1.09 mm, and 95SD of 3.53 mm on the four organs, which outperforms the state-of-the-art segmentation networks by a large margin. Specifically, the quantitative DSC evaluation results of the four organs are 96.49% (bladder), 86.39% (rectum), 76.38% (seminal vesicle), and 86.14% (prostate), respectively. In conclusion, we demonstrate that the proposed MTER-Net efficiently attains superior performance to state-of-the-art pelvic organ segmentation methods.

MRI prostate contouring is not impaired by the use of a radiotherapy image acquisition set-up. An intra- and inter-observer paired comparative analysis with diagnostic set-up images

PurposeThe use of MRI for radiotherapy planning purposes is growing but image acquisition using radiotherapy set-ups has impaired image quality. Whether differences in image acquisition set-up could modify organ contouring has not been evaluated. Therefore, we aimed to evaluate differences in contouring between paired of image sets that were acquired in the same scanning session using different parameters. Material and methodsTen patients underwent RT treatment planning with MRI co-registration. MRI was carried out using two different set-ups during the same session, MRI radiotherapy set-ups and MRI diagnostic set-ups. Prostates and rectums were retrospectively contoured in both image sets by 5 radiation oncologists and 4 radiologists. Intra-observer analysis was carried out comparing organ volumes, the Dice coefficient and hausdorff distance values between two contouring rounds. Inter-observer analysis was carried out by comparing individual contours to a generated STAPLE consensus contour, which is considered the gold standard reference. ResultsNo significant differences were observed between MRI acquisition set-ups. Significant differences were observed for the dice and hausdorff parameters, comparing individual contours to the STAPLE consensus contour, when analysing diagnostic images between rounds, although raw values were similar. ConclusionProstate and rectum contours did not differ significantly when using diagnostic or radiotherapy MRI acquisition set-ups.

Validation of the dosimetric and geometric accuracy of MR-only treatment planning solution for prostate cancer radiotherapy.

IntroductionThe aim was to validate the dosimetric and geometric accuracy of radiotherapy treatment plans for prostate cancer based on magnetic resonance (MR) imaging only and a solution based on computed tomography (CT) supported by MR imaging.Material and methodsWe used CT and MR images of ten prostate cancer patients implanted with three fiducial markers (FM) in the prostate gland. Rigid registration based on FM was performed to assess the fusion accuracy between MR and CT images. The differences between prostate contours (clinical target volume – CTV) on CT (CTVCT) and MR (CTVMR) images were scored using the Dice similarity coefficient and directly comparing the outlined volumes. The volumetric modulated arc therapy plans were designed and optimised on synthetic CT (sCT) to obtain the dose distribution for the MR-only solution. In the next step, the sCT images were replaced by conventional CT images and the plans were recalculated. The doses obtained on sCT and CT were compared by direct dose subtraction and the gamma method.ResultsThe averaged fiducial registration error was equal to 0.5 mm. All CTVCT volumes were significantly bigger than corresponding CTV delineated on MR images (p = 0.005). The direct dose comparison shows that for 97.1% of patients’ bodies, the differences were smaller than 0.1%. The average gamma passing rates were higher than 0.970.ConclusionsMR imaging allows for a more precise delineation of the prostate compared to CT imaging. The workflow of plan preparation based on MR and CT is burdened with an FM registration error that is eliminated by an MR-only solution with no compromise on dose distribution.

ProSegNet: A New Network of Prostate Segmentation Based on MR Images

Prostate cancer is the most common cancer in men after lung cancer. Generally, the segmentation of the prostate is the preprocessing work for the diagnosis of prostate cancer. Aiming at the variety of prostate and the similarity of visual characteristics between prostates and their surroundings, this paper proposes a new prostate segmentation network based on MR images, denoted as ProSegNet. ProSegNet consists of two parts: encoder and decoder. To improve the feature extraction capability of the encoder, we use dense blocks as the feature extraction unit, and at the same time introduce a cross-stage partial (CSP) structure to reduce the amount of calculation. In the design of the decoder structure, we integrated the spatial attention mechanism and the channel attention mechanism to enable it to focus on the important features while ignoring the invalid features. In addition, to segment the prostate more accurately, we add a prostate contour segmentation branch to the output of the segmentation network to learn the contour features of the prostate. Finally, to alleviate the problem of small intensity difference between the prostate and surrounding tissues, we designed a truncated intensity stretching image enhancement method. The performance of ProSegNet has been experimentally verified in the Promise12 and ProstateX datasets. On the Promise12 dataset, the dice similarity coefficient (DSC) and hausdorff (Haus) distance are 0.908 and 9.87 respectively. On the ProstateX dataset, the DSC and Haus reach the results of 0.892 and 10.45, respectively. Experimental results show that the ProSegNet can obtain a competitive performance.

Use of deformable image registration techniques to estimate dose to organs at risk following prostate external beam radiation therapy and high-dose-rate brachytherapy.

PurposeThe purpose of this investigation was to examine differences in estimates of accumulated rectal dose when using deformable image registration (DIR) compared with rigid image registration (RIR) methods, and parameter addition methods for combined transrectal ultrasound (TRUS)-based high-dose-rate brachytherapy (HDR-BT) and external beam radiation therapy (EBRT) treatments of prostate cancer.Material and methodsIn this retrospective study, data from 10 patients who had previously received HDR-BT in one 15 Gy fraction, followed by 46 Gy EBRT in twenty-three fractions were used. To estimate total combined dose to the rectum, dose accumulation using both DIR and RIR methods were compared with parameter addition methods, which assume the same region of rectal anatomy receives the maximum dose from both treatment modalities. For both rigid and deformable image registration techniques, the quality of image registration was evaluated through metrics, including mean distance to agreement and dice similarity coefficient of prostate contours. Total D1cc and D2cc for the rectum was calculated and compared using each method.ResultsThe parameter addition methods predicted the highest accumulated dose to the rectum. On average, the predicted D2cc dose was higher than that calculated by the DIR method by 6.59 Gy EQD2 (range, –3.03 to 13.68 Gy EQD2) for partial parameter addition (PPA), and 4.88 Gy EQD2 (range, –3.41 to 11.97 Gy EQD2) for the full parameter addition (FPA) methods. Similarly, RIR predicted higher average doses compared with DIR, with a difference of 3.46 Gy EQD2 (range, –5.50 to 7.90 Gy EQD2). The results showed a significant difference between DIR and parameter addition methods for dose estimation.ConclusionsThis retrospective study demonstrates significant differences in accumulated rectal dose prediction using different image registration methods. Each method has limitations in its application, and when used with real-time HDR-BT dose planning, awareness of these limitations is essential.

A prostate MRI segmentation method based on prior-shape-information combined with gradient and regional information

With the increasing and younger incidence of prostate cancer, the extraction of prostate contour from magnetic resonance imaging (MRI) plays an increasingly important role in clinical diagnosis and related medical research. In order to accurately segment the prostate region in MR images, we propose a level set segmentation model, which integrates the prior shape information of the prostate and the gradient information into the region-scalable fitting (RSF) model proposed by Li et al. to achieve high-precision segmentation of the prostate. In our model, we use the Gaussian probability model to establish the statistical learning of the prior shape, expressed as the external energy term of the evolution curve, and use the local grey information and the improved gradient information as the internal energy term to construct the final level set segmentation model. This method uses the information of the image itself to modify the evolution curve under the constraints of the prior shape, which can better deal with the small difference between the background and the target area in the medical image, and improve the accuracy and robustness of the segmentation. The final experimental results and analysis illustrate the feasibility of the method used in prostate MRI segmentation.

An unusual case of oedematous prostate volumetric changes observed over the course of radiotherapy on the MR linear accelerator

IntroductionThe integration of magnetic resonance (MR) imaging into radiotherapy through new technology, including the MR -linear accelerator (MRL), has allowed further advancements into image guided radiotherapy (IGRT). Better soft tissue visualisation has led to some unusual findings. Case and outcomesA patient with T1c N0 M0 prostate adenocarcinoma received 60Gy in 20# radiotherapy on the MRL. Radiotherapy planning (RTP) scans were completed on both CT and MR (using T2 and T1 weighted three-dimensional turbo spin echo sequences, reconstructed transaxially (TRA). The MR scans revealed atypical oedema in the right peripheral zone, visualised on T2-weighted (T2w) MR Images as an accumulation of high signal intensity fluid. Daily MRL treatment includes a (T2w 3D Tra) sequence with which oedematous changes could be monitored. The images demonstrated an increase in oedematous volume over fractions 1–10 causing the prostate contour variations from the initial planning scans. Despite the prostate volume variations PTV coverage was never breached and dose constraints were always met for both PTV and surrounding organs at risk (OAR's), excluding the need for oncologist input.A single Therapeutic Radiographer (RTT) experienced in MRL delivery, contoured the prostate and oedematous volumes on the radiotherapy plan (RTP) MR and all on-treatment MR images to assess change over the radiotherapy course. The initial volumes were 53.4 cm3 and 8.3 cm3 for the prostate plus oedema and oedema alone respectively. The most significant change was seen for both the prostate and oedema on fraction nine (68.0 cm3 and 10.1 cm3, respectively). Reductions were noted after this with final (fraction 20) volumes of 55.2 cm3 and 0.58 cm3 respectively. DiscussionThe ability to visualise prostatic oedema was new to the radiotherapy treatment team due to better soft tissue visualisation than standard radiotherapy. The results from contouring the prostate and oedema volumes confirmed radiographer observations and demonstrated how oedema impacted the overall prostate volume by quantifying the oedematous variations over time. The changes in oedema volume are presumed to be in response to radiotherapy. ConclusionFurther adaptive radiotherapy work-flow developments, utilising an “Adapt to Shape” model will allow real-time re-contouring of the prostate to ensure tumour control is not compromised. Further work investigating the frequency and impact of oedemotous changes to external beam prostate patients will help to inform practice.

Artificial intelligence-based radiotherapy machine parameter optimization using reinforcement learning.

To develop and evaluate a volumetric modulated arc therapy (VMAT) machine parameter optimization (MPO) approach based on deep-Q reinforcement learning (RL) capable of finding an optimal machine control policy using previous prostate cancer patient CT scans and contours, and applying the policy to new cases to rapidly produce deliverable VMAT plans in a simplified beam model. A convolutional deep-Q network was employed to control the dose rate and multileaf collimator of a C-arm linear accelerator model using the current dose distribution and machine parameter state as input. A Q-value was defined as the discounted cumulative cost based on dose objectives, and experience-replay RL was performed to determine a policy to minimize the Q-value. A two-dimensional network design was employed which optimized each opposing leaf pair independently while monitoring the corresponding dose plane blocked by those leaves. This RL approach was applied to CT and contours from 40 retrospective prostate cancer patients. The dataset was split into training (15 patients) and validation (5 patients) groups to optimize the network, and its performance was tested in an independent cohort of 20 patients by comparing RL-based dose distributions to conformal arcs and clinical intensity modulated radiotherapy (IMRT) delivering a prescription dose of 78Gy in 40 fractions. Mean±SD execution time of the RL VMAT optimization was 1.5±0.2s per slice. In the test cohort, mean±SD (P-value) planning target volume (PTV), bladder, and rectum dose were 80.5±2.0Gy (P<0.001), 44.2±14.6Gy (P<0.001), and 43.7±11.1Gy (P<0.001) for RL VMAT compared to 81.6±1.1Gy, 51.6±12.9Gy, and 36.0±12.3Gy for clinical IMRT. RL was applied to VMAT MPO using clinical patient contours without independently optimized treatment plans for training and achieved comparable target and normal tissue dose to clinical plans despite the application of a relatively simple network design originally developed for video-game control. These results suggest that extending a RL approach to a full three-dimensional beam model could enable rapid artificial intelligence-based optimization of deliverable treatment plans, reducing the time required for radiotherapy planning without requiring previous plans for training.

Prostate brachytherapy intraoperative dosimetry using a combination of radiographic seed localization with a C-arm and deformed ultrasound prostate contours

PurposeThe purpose of the study was to assess the feasibility of performing intraoperative dosimetry for permanent prostate brachytherapy by combining transrectal ultrasound (TRUS) and fluoroscopy/cone beam CT [CBCT] images and accounting for the effect of prostate deformation. Methods and Materials13 patients underwent TRUS and multiview two-dimensional fluoroscopic imaging partway through the implant, as well as repeat fluoroscopic imaging with the TRUS probe inserted and retracted, and finally three-dimensional CBCT imaging at the end of the implant. The locations of all the implanted seeds were obtained from the fluoroscopy/CBCT images and were registered to prostate contours delineated on the TRUS images based on a common subset of seeds identified on both image sets. Prostate contours were also deformed, using a finite-element model, to take into account the effect of the TRUS probe pressure. Prostate dosimetry parameters were obtained for fluoroscopic and CBCT-dosimetry approaches and compared with the standard-of-care Day-0 postimplant CT dosimetry. ResultsHigh linear correlation (R2 > 0.8) was observed in the measured values of prostate D90%, V100%, and V150%, between the two intraoperative dosimetry approaches. The prostate D90% and V100% obtained from intraoperative dosimetry methods were in agreement with the postimplant CT dosimetry. Only the prostate V150% was on average 4.1% (p-value <0.05) higher in the CBCT-dosimetry approach and 6.7% (p-value <0.05) higher in postimplant CT dosimetry compared with the fluoroscopic dosimetry approach. Deformation of the prostate by the ultrasound probe appeared to have a minimal effect on prostate dosimetry. ConclusionsThe results of this study have shown that both of the proposed dosimetric evaluation approaches have potential for real-time intraoperative dosimetry.

Graph-convolutional-network-based interactive prostate segmentation in MR images.

Accurate and robust segmentation of the prostate from magnetic resonance (MR) images is extensively applied in many clinical applications in prostate cancer diagnosis and treatment. The purpose of this study is the development of a robust interactive segmentation method for accurate segmentation of the prostate from MR images. We propose an interactive segmentation method based on a graph convolutional network (GCN) to refine the automatically segmented results. An atrous multiscale convolutional neural network (CNN) encoder is proposed to learn representative features to obtain accurate segmentations. Based on the multiscale feature, a GCN block is presented to predict the prostate contour in both automatic and interactive manners. To preserve the prostate boundary details and effectively train the GCN, a contour matching loss is proposed. The performance of the proposed algorithm was evaluated on 41 in-house MR subjects and 30 PROMISE12 test subjects. The proposed method yields mean Dice similarity coefficients of 93.8±1.2% and 94.4±1.0% on our in-house and PROMISE12 datasets, respectively. The experimental results show that the proposed method outperforms several state-of-the-art segmentation methods. The proposed interactive segmentation method based on the GCN can accurately segment the prostate from MR images. Our method has a variety of applications in prostate cancer imaging.

Sagittal alignment in an MR-TRUS fusion biopsy using only the prostate contour in the axial image

PurposeThis paper examines the feasibility of automated alignment in sagittal direction in MR-TRUS fusion biopsy of the prostate by comparing the prostate contour in axial images between different modalities. In the treatment of prostate cancer, an important factor affecting the prognosis of patients is focal therapy of cancer within the prostate. Therefore, MR-TRUS fusion biopsy of the prostate is attracting attention as one of the most effective localization techniques. Because the accuracy of this biopsy is highly dependent on the doctor performing it, automation should reduce variability in diagnostic performance.MethodThe MR image is scaled to the same scale as the TRUS image, and the contours of the prostate on the MR and TRUS images are compared in polar coordinates. In addition, this method makes it possible to perform a robust comparison against deformation by comparing specific angle ranges. It is also possible to improve the accuracy of error calculation by accumulating contour data.ResultThe axial image selected by the proposed method using the prostate contour obtained from the doctor-labeled segmentation image has an error of about 4 mm in the sagittal direction on average compared to the axial image selected by the doctor did. Furthermore, using the inaccurate prostate contours obtained by performing segmentation with U-Net only slightly reduced the accuracy. In addition, it was found that alignment accuracy is improved by using the angler weight.ConclusionIt has been shown that sagittal alignment can be performed with some degree of accuracy using only axial images. Also, the angular weight values used indicate that when comparing axial images, it may be an important factor in determining the same axial cross section to compare the parts that deform due to probe pressure.