Automatic Contour Refinement for Deep Learning Auto-segmentation of Complex Organs in MRI-guided Adaptive Radiation Therapy
Ontology highlight
ABSTRACT: Purpose
Fast and accurate auto-segmentation on daily images is essential for magnetic resonance imaging (MRI)–guided adaptive radiation therapy (ART). However, the state-of-the-art auto-segmentation based on deep learning still has limited success, particularly for complex structures in the abdomen. This study aimed to develop an automatic contour refinement (ACR) process to quickly correct for unacceptable auto-segmented contours. Methods and Materials
An improved level set–based active contour model (ACM) was implemented for the ACR process and was tested on the deep learning–based auto-segmentation of 80 abdominal MRI sets along with their ground truth contours. The performance of the ACR process was evaluated using 4 contour accuracy metrics: the Dice similarity coefficient (DSC), mean distance to agreement (MDA), surface DSC, and added path length (APL) on the auto-segmented contours of the small bowel, large bowel, combined bowels, pancreas, duodenum, and stomach. Results
A portion (3%-39%) of the corrected contours became practically acceptable per the American Association of Physicists in Medicine Task Group 132 (TG-132) recommendation (DSC >0.8 and MDA <3 mm). The best correction performance was seen in the combined bowels, where for the contours with major errors (initial DSC <0.5 or MDA >8 mm), the mean DSC increased from 0.34 to 0.59, the mean MDA decreased from 7.02 mm to 5.23 mm, and the APL reduced by almost 20 mm, whereas for the contours with minor errors, the mean DSC increased from 0.72 to 0.79, the mean MDA decreased from 3.35 mm to 3.29 mm, and more than one-third (39%) of the ACR contours became clinically acceptable. The execution time for the ACR process on one subregion was less than 2 seconds using an NVIDIA GTX 1060 GPU. Conclusions
The ACR process implemented based on the ACM was able to quickly correct for some inaccurate contours produced from MRI-based deep learning auto-segmentation of complex abdominal anatomy. The ACR method may be integrated into the auto-segmentation step to accelerate the process of MRI-guided ART.
SUBMITTER: Ding J
PROVIDER: S-EPMC9280040 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The accurate contour delineation of the target and/or organs at risk (OAR) is essential in treatment planning for image-guided radiation therapy (IGRT). Although many automatic contour delineation approaches have been proposed, few of them can fulfill the necessities of applications in terms of accuracy and efficiency. Moreover, clinicians would like to analyze the characteristics of regions of interests (ROI) and adjust contours manually during IGRT. Interactive tool for contour delineation is necessary in such cases. In this work, a novel approach of curve fitting for interactive contour delineation is proposed. It allows users to quickly improve contours by a simple mouse click. Initially, a region which contains interesting object is selected in the image, then the program can automatically select important control points from the region boundary, and the method of Hermite cubic curves is used to fit the control points. Hence, the optimized curve can be revised by moving its control points interactively. Meanwhile, several curve fitting methods are presented for the comparison. Finally, in order to improve the accuracy of contour delineation, the process of the curve refinement based on the maximum gradient magnitude is proposed. All the points on the curve are revised automatically towards the positions with maximum gradient magnitude. Experimental results show that Hermite cubic curves and the curve refinement based on the maximum gradient magnitude possess superior performance on the proposed platform in terms of accuracy, robustness, and time calculation. Experimental results of real medical images demonstrate the efficiency, accuracy, and robustness of the proposed process in clinical applications.
| S-EPMC5711244 | biostudies-literature
Project description:BACKGROUND:Structure delineation is a necessary, yet time-consuming manual procedure in radiotherapy. Recently, convolutional neural networks have been proposed to speed-up and automatise this procedure, obtaining promising results. With the advent of magnetic resonance imaging (MRI)-guided radiotherapy, MR-based segmentation is becoming increasingly relevant. However, the majority of the studies investigated automatic contouring based on computed tomography (CT). PURPOSE:In this study, we investigate the feasibility of clinical use of deep learning-based automatic OARs delineation on MRI. MATERIALS AND METHODS:We included 150 patients diagnosed with prostate cancer who underwent MR-only radiotherapy. A three-dimensional (3D) T1-weighted dual spoiled gradient-recalled echo sequence was acquired with 3T MRI for the generation of the synthetic-CT. The first 48 patients were included in a feasibility study training two 3D convolutional networks called DeepMedic and dense V-net (dV-net) to segment bladder, rectum and femurs. A research version of an atlas-based software was considered for comparison. Dice similarity coefficient, 95% Hausdorff distances (HD95), and mean distances were calculated against clinical delineations. For eight patients, an expert RTT scored the quality of the contouring for all the three methods. A choice among the three approaches was made, and the chosen approach was retrained on 97 patients and implemented for automatic use in the clinical workflow. For the successive 53 patients, Dice, HD95 and mean distances were calculated against the clinically used delineations. RESULTS:DeepMedic, dV-net and the atlas-based software generated contours in 60 s, 4 s and 10-15 min, respectively. Performances were higher for both the networks compared to the atlas-based software. The qualitative analysis demonstrated that delineation from DeepMedic required fewer adaptations, followed by dV-net and the atlas-based software. DeepMedic was clinically implemented. After retraining DeepMedic and testing on the successive patients, the performances slightly improved. CONCLUSION:High conformality for OARs delineation was achieved with two in-house trained networks, obtaining a significant speed-up of the delineation procedure. Comparison of different approaches has been performed leading to the succesful adoption of one of the neural networks, DeepMedic, in the clinical workflow. DeepMedic maintained in a clinical setting the accuracy obtained in the feasibility study.
| S-EPMC7216473 | biostudies-literature
Project description:PurposeThis study aimed to demonstrate the potential clinical applicability of an organ-contour-driven auto-matching algorithm in image-guided radiotherapy.MethodsThis study included eleven consecutive patients with cervical cancer who underwent radiotherapy in 23 or 25 fractions. Daily and reference magnetic resonance images were converted into mesh models. A weight-based algorithm was implemented to optimize the distance between the mesh model vertices and surface of the reference model during the positioning process. Within the cost function, weight parameters were employed to prioritize specific organs for positioning. In this study, three scenarios with different weight parameters were prepared. The optimal translation and rotation values for the cervix and uterus were determined based on the calculated translations alone or in combination with rotations, with a rotation limit of ±3°. Subsequently, the coverage probabilities of the following two planning target volumes (PTV), an isotropic 5 mm and anisotropic margins derived from a previous study, were evaluated.ResultsThe percentage of translations exceeding 10 mm varied from 9% to 18% depending on the scenario. For small PTV sizes, more than 80% of all fractions had a coverage of 80% or higher. In contrast, for large PTV sizes, more than 90% of all fractions had a coverage of 95% or higher. The difference between the median coverage with translational positioning alone and that with both translational and rotational positioning was 1% or less.ConclusionThis algorithm facilitates quantitative positioning by utilizing a cost function that prioritizes organs for positioning. Consequently, consistent displacement values were algorithmically generated. This study also revealed that the impact of rotational corrections, limited to ±3°, on PTV coverage was minimal.
| S-EPMC10795436 | biostudies-literature
Project description:External-beam radiotherapy followed by high dose rate (HDR) brachytherapy is the standard-of-care for treating gynecologic cancers. The enhanced soft-tissue contrast provided by magnetic resonance imaging (MRI) makes it a valuable imaging modality for diagnosing and treating these cancers. However, in contrast to computed tomography (CT) imaging, the appearance of the brachytherapy catheters, through which radiation sources are inserted to reach the cancerous tissue later on, is often variable across images. This paper reports, for the first time, a new deep-learning-based method for fully automatic segmentation of multiple closely spaced brachytherapy catheters in intraoperative MRI. Represented in the data are 50 gynecologic cancer patients treated by MRI-guided HDR brachytherapy. For each patient, a single intraoperative MRI was used. 826 catheters in the images were manually segmented by an expert radiation physicist who is also a trained radiation oncologist. The number of catheters in a patient ranged between 10 and 35. A deep 3D convolutional neural network (CNN) model was developed and trained. In order to make the learning process more robust, the network was trained 5 times, each time using a different combination of shown patients. Finally, each test case was processed by the five networks and the final segmentation was generated by voting on the obtained five candidate segmentations. 4-fold validation was executed and all the patients were segmented. An average distance error of 2.0??±??3.4?mm was achieved. False positive and false negative catheters were 6.7% and 1.5% respectively. Average Dice score was equal to 0.60??±??0.17. The algorithm is available for use in the open source software platform 3D Slicer allowing for wide scale testing and research discussion. In conclusion, to the best of our knowledge, fully automatic segmentation of multiple closely spaced catheters from intraoperative MR images was achieved for the first time in gynecological brachytherapy.
| S-EPMC6726393 | biostudies-literature
Project description:In this contribution, a semi-automatic segmentation algorithm for (medical) image analysis is presented. More precise, the approach belongs to the category of interactive contouring algorithms, which provide real-time feedback of the segmentation result. However, even with interactive real-time contouring approaches there are always cases where the user cannot find a satisfying segmentation, e.g. due to homogeneous appearances between the object and the background, or noise inside the object. For these difficult cases the algorithm still needs additional user support. However, this additional user support should be intuitive and rapid integrated into the segmentation process, without breaking the interactive real-time segmentation feedback. I propose a solution where the user can support the algorithm by an easy and fast placement of one or more seed points to guide the algorithm to a satisfying segmentation result also in difficult cases. These additional seed(s) restrict(s) the calculation of the segmentation for the algorithm, but at the same time, still enable to continue with the interactive real-time feedback segmentation. For a practical and genuine application in translational science, the approach has been tested on medical data from the clinical routine in 2D and 3D.
| S-EPMC4044619 | biostudies-other
Project description:Background and purposeMagnetic resonance (MR)-guided linear accelerator (MR-Linac) systems have changed radiotherapy workflows. The addition of daily online contour adaptation allows for higher precision treatment, but also increases the workload of those involved. We train radiation therapists (RTTs) to perform daily online contour adaptation for MR-Linac treatment of prostate cancer (PCa) patients. The purpose of this study was to evaluate these prostate contours by performing an interfraction and interobserver analysis.Materials and methodsClinical target volume (CTV) contours generated online by RTTs from 30 low-intermediate risk PCa patients, treated with 5x7.25 Gy, were used. Two physicians (Observers) judged the RTTs contours and performed adaptations when necessary. Interfraction relative volume differences between the first and the subsequent fractions were calculated for the RTTs, Observer 1, and Observer 2. Additionally, interobserver dice's similarity coefficient (DSC) for fraction 2-5 was calculated with the RTTs- and physician-adapted contours. Clinical acceptability of the RTTs contours was judged by a third observer.ResultsMean (SD) online contour adaptation time was 12.6 (±3.8) minutes and overall median (interquartile range [IQR]) relative volume difference was 9.3% (4.4-13.0). Adaptations by the observers were mostly performed at the apex and base of the prostate. Median (IQR) interobserver DSC between RTTs and Observer 1, RTTs and Observer 2, and Observer 1 and 2 was 0.99 (0.98-1.00), 1.00 (0.98-1.00), and 1.00 (0.99-1.00), respectively. Contours were acceptable for clinical use in 113 (94.2%) fractions. Dose-volume histogram (DVH) analysis showed significant CTV underdosage for one of the seven identified outliers.ConclusionDaily online contour adaptation by RTTs is clinically feasible for MR-Linac treatment of PCa.
| S-EPMC7822780 | biostudies-literature
Project description:Defining myocardial contours is often the most time-consuming portion of dynamic cardiac MRI image analysis. Displacement encoding with stimulated echoes (DENSE) is a quantitative MRI technique that encodes tissue displacement into the phase of the complex MRI images. Cine DENSE provides a time series of these images, thus facilitating the non-invasive study of myocardial kinematics. Epicardial and endocardial contours need to be defined at each frame on cine DENSE images for the quantification of regional displacement and strain as a function of time. This work presents a reliable and effective two-dimensional semi-automated segmentation technique that uses the encoded motion to project a manually-defined region of interest through time. Contours can then easily be extracted for each cardiac phase. This method boasts several advantages, including, (1) parameters are based on practical physiological limits, (2) contours are calculated for the first few cardiac phases, where it is difficult to visually distinguish blood from myocardium, and (3) the method is independent of the shape of the tissue delineated and can be applied to short- or long-axis views, and on arbitrary regions of interest. Motion-guided contours were compared to manual contours for six conventional and six slice-followed mid-ventricular short-axis cine DENSE datasets. Using an area measure of segmentation error, the accuracy of the segmentation algorithm was shown to be similar to inter-observer variability. In addition, a radial segmentation error metric was introduced for short-axis data. The average radial epicardial segmentation error was 0.36+/-0.08 and 0.40+/-0.10 pixels for slice-followed and conventional cine DENSE, respectively, and the average radial endocardial segmentation error was 0.46+/-0.12 and 0.46+/-0.16 pixels for slice following and conventional cine DENSE, respectively. Motion-guided segmentation employs the displacement-encoded phase shifts intrinsic to DENSE MRI to accurately propagate a single set of pre-defined contours throughout the remaining cardiac phases.
| S-EPMC2614556 | biostudies-literature
Project description:Purpose: To evaluate the accuracy of deep-learning-based auto-segmentation of the superior constrictor, middle constrictor, inferior constrictor, and larynx in comparison with a traditional multi-atlas-based method. Methods and Materials: One hundred and five computed tomography image datasets from 83 head and neck cancer patients were retrospectively collected and the superior constrictor, middle constrictor, inferior constrictor, and larynx were analyzed for deep-learning versus multi-atlas-based segmentation. Eighty-three computed tomography images (40 diagnostic computed tomography and 43 planning computed tomography) were used for training the convolutional neural network, and for atlas-based model training. The remaining 22 computed tomography datasets were used for validation of the atlas-based auto-segmentation versus deep-learning-based auto-segmentation contours, both of which were compared with the corresponding manual contours. Quantitative measures included Dice similarity coefficient, recall, precision, Hausdorff distance, 95th percentile of Hausdorff distance, and mean surface distance. Dosimetric differences between the auto-generated contours and manual contours were evaluated. Subjective evaluation was obtained from 3 clinical observers to blindly score the autosegmented structures based on the percentage of slices that require manual modification. Results: The deep-learning-based auto-segmentation versus atlas-based auto-segmentation results were compared for the superior constrictor, middle constrictor, inferior constrictor, and larynx. The mean Dice similarity coefficient values for the 4 structures were 0.67, 0.60, 0.65, and 0.84 for deep-learning-based auto-segmentation, whereas atlas-based auto-segmentation has Dice similarity coefficient results at 0.45, 0.36, 0.50, and 0.70, respectively. The mean 95th percentile of Hausdorff distance (cm) for the 4 structures were 0.41, 0.57, 0.59, and 0.54 for deep-learning-based auto-segmentation, but 0.78, 0.95, 0.96, and 1.23 for atlas-based auto-segmentation results, respectively. Similar mean dose differences were obtained from the 2 sets of autosegmented contours compared to manual contours. The dose-volume discrepancies and the average modification rates were higher with the atlas-based auto-segmentation contours. Conclusion: Swallowing-related structures are more accurately generated with DL-based versus atlas-based segmentation when compared with manual contours.
| S-EPMC9340321 | biostudies-literature
Project description:PURPOSE:Segmentation of cardiac medical images, an important step in measuring cardiac function, is usually performed either manually or semiautomatically. Fully automatic segmentation of the left ventricle (LV), the right ventricle (RV) as well as the myocardium of three-dimensional (3D) magnetic resonance (MR) images throughout the entire cardiac cycle (four-dimensional, 4D), remains challenging. This study proposes a deformable-based segmentation methodology for efficiently segmenting 4D (3D + t) cardiac MR images. METHODS:The proposed methodology first used the Hough transform and the local Gaussian distribution method (LGD) to segment the LV endocardial contours from cardiac MR images. Following this, a novel level set-based shape prior method was applied to generate the LV epicardial contours and the RV boundary. RESULTS:This automatic image segmentation approach has been applied to studies on 17 subjects. The results demonstrated that the proposed method was efficient compared to manual segmentation, achieving a segmentation accuracy with average Dice values of 88.62 ± 5.47%, 87.35 ± 7.26%, and 82.63 ± 6.22% for the LV endocardial, LV epicardial, and RV contours, respectively. CONCLUSIONS:We have presented a method for accurate LV and RV segmentation. Compared to three existing methods, the proposed method can successfully segment the LV and yield the highest Dice value. This makes it an option for clinical assessment of the volume, size, and thickness of the ventricles.
| S-EPMC6322927 | biostudies-literature
Project description:BackgroundSegmentation of medical image volumes is a time-consuming manual task. Automatic tools are often tailored toward specific patient cohorts, and it is unclear how they behave in other clinical settings.PurposeTo evaluate the performance of the open-source Multi-Planar U-Net (MPUnet), the validated Knee Imaging Quantification (KIQ) framework, and a state-of-the-art two-dimensional (2D) U-Net architecture on three clinical cohorts without extensive adaptation of the algorithms.Study typeRetrospective cohort study.SubjectsA total of 253 subjects (146 females, 107 males, ages 57 ± 12 years) from three knee osteoarthritis (OA) studies (Center for Clinical and Basic Research [CCBR], Osteoarthritis Initiative [OAI], and Prevention of OA in Overweight Females [PROOF]) with varying demographics and OA severity (64/37/24/53/2 scans of Kellgren and Lawrence [KL] grades 0-4).Field strength/sequence0.18 T, 1.0 T/1.5 T, and 3 T sagittal three-dimensional fast-spin echo T1w and dual-echo steady-state sequences.AssessmentAll models were fit without tuning to knee magnetic resonance imaging (MRI) scans with manual segmentations from three clinical cohorts. All models were evaluated across KL grades.Statistical testsSegmentation performance differences as measured by Dice coefficients were tested with paired, two-sided Wilcoxon signed-rank statistics with significance threshold α = 0.05.ResultsThe MPUnet performed superior or equal to KIQ and 2D U-Net on all compartments across three cohorts. Mean Dice overlap was significantly higher for MPUnet compared to KIQ and U-Net on CCBR ( 0.83±0.04 vs. 0.81±0.06 and 0.82±0.05 ), significantly higher than KIQ and U-Net OAI ( 0.86±0.03 vs. 0.84±0.04 and 0.85±0.03) , and not significantly different from KIQ while significantly higher than 2D U-Net on PROOF ( 0.78±0.07 vs. 0.77±0.07 , P=0.10 , and 0.73±0.07) . The MPUnet performed significantly better on N=22 KL grade 3 CCBR scans with 0.78±0.06 vs. 0.75±0.08 for KIQ and 0.76±0.06 for 2D U-Net.Data conclusionThe MPUnet matched or exceeded the performance of state-of-the-art knee MRI segmentation models across cohorts of variable sequences and patient demographics. The MPUnet required no manual tuning making it both accurate and easy-to-use.Level of evidence3 TECHNICAL EFFICACY: Stage 2.
| S-EPMC9106804 | biostudies-literature