Automatic segmentation of head and neck CT images for radiotherapy treatment planning using multiple atlases, statistical appearance models, and geodesic active contours.
Ontology highlight
ABSTRACT:
SUBMITTER: Fritscher KD
PROVIDER: S-EPMC4000401 | biostudies-other | 2014 May
REPOSITORIES: biostudies-other
Similar Datasets
Project description:Background and purposePeer-review of Target Volume (TV) and Organ at Risk (OAR) contours in radiotherapy planning are typically conducted visually; this can be time consuming and subject to interobserver variation. This study investigated automatic evaluation of contouring using conformity indices and supervised machine learning.MethodsA total of 393 contours from 253 Stereotactic Ablative Body Radiotherapy (SABR) benchmark cases (adrenal gland, liver, pelvic lymph node and spine), delineated by 132 clinicians from 25 centres, were visually evaluated for conformity against gold standard contours. Contours were scored as "pass" or "fail" on visual peer review and six Conformity Indices (CIs) were applied. CI values were mapped to pass/fail scores for each contour and used to train supervised machine learning models. A 5-fold cross validation method was employed to determine the predictive accuracies of each model.ResultsThe stomach structure produced models with the highest predictive accuracy overall (96% using Support Vector Machine and Ensemble models), whilst the liver GTV produced models with the lowest predictive accuracy (76% using Logistic Regression). Predictive accuracies across all models ranged from 68-96% (68-87% for TV and 71-96% for OARs).ConclusionsAlthough a final visual review by an experienced clinician is still required, the automatic contour evaluation method could reduce the time for benchmark case reviews by identifying gross contouring errors. This method could be successfully implemented to support departmental training and the continuous assessment of outlining for clinical staff in the peer-review process, to reduce interobserver variability in contouring and improve interpretation of radiological anatomy.
| S-EPMC7807884 | biostudies-literature
Project description:Treatment planning is time-consuming and the outcome depends on the person performing the optimization. A system that automates treatment planning could potentially reduce the manual time required for optimization and could also provide a method to reduce the variation between persons performing radiation dose planning (dosimetrist) and potentially improve the overall plan quality. This study evaluates the performance of the Auto-Planning module that has recently become clinically available in the Pinnacle3 radiation therapy treatment planning system. Twenty-six clinically delivered head and neck treatment plans were reoptimized with the Auto-Planning module. Comparison of the two types of treatment plans were performed using DVH metrics and a blinded clinical evaluation by two senior radiation oncologists using a scale from one to six. Both evaluations investigated dose coverage of target and dose to healthy tissues. Auto-Planning was able to produce clinically acceptable treatment plans in all 26 cases. Target coverages in the two types of plans were similar, but automatically generated plans had less irradiation of healthy tissue. In 94% of the evaluations, the autoplans scored at least as high as the previously delivered clinical plans. For all patients, the Auto-Planning tool produced clinically acceptable head and neck treatment plans without any manual intervention, except for the initial target and OAR delineations. The main benefit of the method is the likely improvement in the overall treatment quality since consistent, high-quality plans are generated which even can be further optimized, if necessary. This makes it possible for the dosimetrist to focus more time on difficult dose planning goals and to spend less time on the more tedious parts of the planning process.
| S-EPMC5690191 | biostudies-literature
Project description:Background and purposeReducing trismus in radiotherapy for head and neck cancer (HNC) is important. Automated deep learning (DL) segmentation and automated planning was used to introduce new and rarely segmented masticatory structures to study if trismus risk could be decreased.Materials and methodsAuto-segmentation was based on purpose-built DL, and automated planning used our in-house system, ECHO. Treatment plans for ten HNC patients, treated with 2 Gy × 35 fractions, were optimized (ECHO0). Six manually segmented OARs were replaced with DL auto-segmentations and the plans re-optimized (ECHO1). In a third set of plans, mean doses for auto-segmented ipsilateral masseter and medial pterygoid (MIMean, MPIMean), derived from a trismus risk model, were implemented as dose-volume objectives (ECHO2). Clinical dose-volume criteria were compared between the two scenarios (ECHO0 vs. ECHO1; ECHO1 vs. ECHO2; Wilcoxon signed-rank test; significance: p < 0.01).ResultsSmall systematic differences were observed between the doses to the six auto-segmented OARs and their manual counterparts (median: ECHO1 = 6.2 (range: 0.4, 21) Gy vs. ECHO0 = 6.6 (range: 0.3, 22) Gy; p = 0.007), and the ECHO1 plans provided improved normal tissue sparing across a larger dose-volume range. Only in the ECHO2 plans, all patients fulfilled both MIMean and MPIMean criteria. The population median MIMean and MPIMean were considerably lower than those suggested by the trismus model (ECHO0: MIMean = 13 Gy vs. ≤42 Gy; MPIMean = 29 Gy vs. ≤68 Gy).ConclusionsAutomated treatment planning can efficiently incorporate new structures from DL auto-segmentation, which results in trismus risk sparing without deteriorating treatment plan quality. Auto-planning and deep learning auto-segmentation together provide a powerful platform to further improve treatment planning.
| S-EPMC8552336 | biostudies-literature
Project description:PurposeDeep learning-based auto-segmented contour (DC) models require high quality data for their development, and previous studies have typically used prospectively produced contours, which can be resource intensive and time consuming to obtain. The aim of this study was to investigate the feasibility of using retrospective peer-reviewed radiotherapy planning contours in the training and evaluation of DC models for lung stereotactic ablative radiotherapy (SABR).MethodsUsing commercial deep learning-based auto-segmentation software, DC models for lung SABR organs at risk (OAR) and gross tumor volume (GTV) were trained using a deep convolutional neural network and a median of 105 contours per structure model obtained from 160 publicly available CT scans and 50 peer-reviewed SABR planning 4D-CT scans from center A. DCs were generated for 50 additional planning CT scans from center A and 50 from center B, and compared with the clinical contours (CC) using the Dice Similarity Coefficient (DSC) and 95% Hausdorff distance (HD).ResultsComparing DCs to CCs, the mean DSC and 95% HD were 0.93 and 2.85mm for aorta, 0.81 and 3.32mm for esophagus, 0.95 and 5.09mm for heart, 0.98 and 2.99mm for bilateral lung, 0.52 and 7.08mm for bilateral brachial plexus, 0.82 and 4.23mm for proximal bronchial tree, 0.90 and 1.62mm for spinal cord, 0.91 and 2.27mm for trachea, and 0.71 and 5.23mm for GTV. DC to CC comparisons of center A and center B were similar for all OAR structures.ConclusionsThe DCs developed with retrospective peer-reviewed treatment contours approximated CCs for the majority of OARs, including on an external dataset. DCs for structures with more variability tended to be less accurate and likely require using a larger number of training cases or novel training approaches to improve performance. Developing DC models from existing radiotherapy planning contours appears feasible and warrants further clinical workflow testing.
| S-EPMC8215371 | 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:Atlas-based autosegmentation is an established tool for segmenting structures for CT-planned head and neck radiotherapy. MRI is being increasingly integrated into the planning process. The aim of this study is to assess the feasibility of MRI-based, atlas-based autosegmentation for organs at risk (OAR) and lymph node levels, and to compare the segmentation accuracy with CT-based autosegmentation. Fourteen patients with locally advanced head and neck cancer in a prospective imaging study underwent a T1-weighted MRI and a PET-CT (with dedicated contrast-enhanced CT) in an immobilization mask. Organs at risk (orbits, parotids, brainstem, and spinal cord) and the left level II lymph node region were manually delineated on the CT and MRI separately. A 'leave one out' approach was used to automatically segment structures onto the remaining images separately for CT and MRI. Contour comparison was performed using multiple positional metrics: Dice index, mean distance to conformity (MDC), sensitivity index (Se Idx), and inclusion index (Incl Idx). Automatic segmentation using MRI of orbits, parotids, brainstem, and lymph node level was acceptable with a DICE coefficient of 0.73-0.91, MDC 2.0-5.1mm, Se Idx 0.64-0.93, Incl Idx 0.76-0.93. Segmentation of the spinal cord was poor (Dice coefficient 0.37). The process of automatic segmentation was significantly better on MRI compared to CT for orbits, parotid glands, brainstem, and left lymph node level II by multiple positional metrics; spinal cord segmentation based on MRI was inferior compared with CT. Accurate atlas-based automatic segmentation of OAR and lymph node levels is feasible using T1-MRI; segmentation of the spinal cord was found to be poor. Comparison with CT-based automatic segmentation suggests that the process is equally as, or more accurate, using MRI. These results support further translation of MRI-based segmentation methodology into clinicalpractice.
| S-EPMC5690045 | biostudies-literature
Project description:IntroductionOrgan-at-risk segmentation for head and neck cancer radiation therapy is a complex and time-consuming process (requiring up to 42 individual structure, and may delay start of treatment or even limit access to function-preserving care. Feasibility of using a deep learning (DL) based autosegmentation model to reduce contouring time without compromising contour accuracy is assessed through a blinded randomized trial of radiation oncologists (ROs) using retrospective, de-identified patient data.MethodsTwo head and neck expert ROs used dedicated time to create gold standard (GS) contours on computed tomography (CT) images. 445 CTs were used to train a custom 3D U-Net DL model covering 42 organs-at-risk, with an additional 20 CTs were held out for the randomized trial. For each held-out patient dataset, one of the eight participant ROs was randomly allocated to review and revise the contours produced by the DL model, while another reviewed contours produced by a medical dosimetry assistant (MDA), both blinded to their origin. Time required for MDAs and ROs to contour was recorded, and the unrevised DL contours, as well as the RO-revised contours by the MDAs and DL model were compared to the GS for that patient.ResultsMean time for initial MDA contouring was 2.3 hours (range 1.6-3.8 hours) and RO-revision took 1.1 hours (range, 0.4-4.4 hours), compared to 0.7 hours (range 0.1-2.0 hours) for the RO-revisions to DL contours. Total time reduced by 76% (95%-Confidence Interval: 65%-88%) and RO-revision time reduced by 35% (95%-CI,-39%-91%). All geometric and dosimetric metrics computed, agreement with GS was equivalent or significantly greater (p<0.05) for RO-revised DL contours compared to the RO-revised MDA contours, including volumetric Dice similarity coefficient (VDSC), surface DSC, added path length, and the 95%-Hausdorff distance. 32 OARs (76%) had mean VDSC greater than 0.8 for the RO-revised DL contours, compared to 20 (48%) for RO-revised MDA contours, and 34 (81%) for the unrevised DL OARs.ConclusionDL autosegmentation demonstrated significant time-savings for organ-at-risk contouring while improving agreement with the institutional GS, indicating comparable accuracy of DL model. Integration into the clinical practice with a prospective evaluation is currently underway.
| S-EPMC10115982 | biostudies-literature
Project description:Electroporation is the phenomenon that occurs when a cell is exposed to a high electric field, which causes transient cell membrane permeabilization. A paramount electroporation-based application is electrochemotherapy, which is performed by delivering high-voltage electric pulses that enable the chemotherapeutic drug to more effectively destroy the tumor cells. Electrochemotherapy can be used for treating deep-seated metastases (e.g. in the liver, bone, brain, soft tissue) using variable-geometry long-needle electrodes. To treat deep-seated tumors, patient-specific treatment planning of the electroporation-based treatment is required. Treatment planning is based on generating a 3D model of the organ and target tissue subject to electroporation (i.e. tumor nodules). The generation of the 3D model is done by segmentation algorithms. We implemented and evaluated three automatic liver segmentation algorithms: region growing, adaptive threshold, and active contours (snakes). The algorithms were optimized using a seven-case dataset manually segmented by the radiologist as a training set, and finally validated using an additional four-case dataset that was previously not included in the optimization dataset. The presented results demonstrate that patient's medical images that were not included in the training set can be successfully segmented using our three algorithms. Besides electroporation-based treatments, these algorithms can be used in applications where automatic liver segmentation is required.
| S-EPMC3732275 | biostudies-literature
Project description:PURPOSE:Manual delineation of head and neck (H&N) organ-at-risk (OAR) structures for radiation therapy planning is time consuming and highly variable. Therefore, we developed a dynamic multiatlas selection-based approach for fast and reproducible segmentation. METHODS:Our approach dynamically selects and weights the appropriate number of atlases for weighted label fusion and generates segmentations and consensus maps indicating voxel-wise agreement between different atlases. Atlases were selected for a target as those exceeding an alignment weight called dynamic atlas attention index. Alignment weights were computed at the image level and called global weighted voting (GWV) or at the structure level and called structure weighted voting (SWV) by using a normalized metric computed as the sum of squared distances of computed tomography (CT)-radiodensity and modality-independent neighborhood descriptors (extracting edge information). Performance comparisons were performed using 77 H&N CT images from an internal Memorial Sloan-Kettering Cancer Center dataset (N = 45) and an external dataset (N = 32) using Dice similarity coefficient (DSC), Hausdorff distance (HD), 95th percentile of HD, median of maximum surface distance, and volume ratio error against expert delineation. Pairwise DSC accuracy comparisons of proposed (GWV, SWV) vs single best atlas (BA) or majority voting (MV) methods were performed using Wilcoxon rank-sum tests. RESULTS:Both SWV and GWV methods produced significantly better segmentation accuracy than BA (P < 0.001) and MV (P < 0.001) for all OARs within both datasets. SWV generated the most accurate segmentations with DSC of: 0.88 for oral cavity, 0.85 for mandible, 0.84 for cord, 0.76 for brainstem and parotids, 0.71 for larynx, and 0.60 for submandibular glands. SWV's accuracy exceeded GWV's for submandibular glands (DSC = 0.60 vs 0.52, P = 0.019). CONCLUSIONS:The contributed SWV and GWV methods generated more accurate automated segmentations than the other two multiatlas-based segmentation techniques. The consensus maps could be combined with segmentations to visualize voxel-wise consensus between atlases within OARs during manual review.
| S-EPMC7042892 | biostudies-literature
Project description:Prostate gland segmentation is a critical step in prostate radiotherapy planning, where dose plans are typically formulated on CT. Pretreatment MRI is now beginning to be acquired at several medical centers. Delineation of the prostate on MRI is acknowledged as being significantly simpler to perform, compared to delineation on CT. In this work, the authors present a novel framework for building a linked statistical shape model (LSSM), a statistical shape model (SSM) that links the shape variation of a structure of interest (SOI) across multiple imaging modalities. This framework is particularly relevant in scenarios where accurate boundary delineations of the SOI on one of the modalities may not be readily available, or difficult to obtain, for training a SSM. In this work the authors apply the LSSM in the context of multimodal prostate segmentation for radiotherapy planning, where the prostate is concurrently segmented on MRI and CT.The framework comprises a number of logically connected steps. The first step utilizes multimodal registration of MRI and CT to map 2D boundary delineations of the prostate from MRI onto corresponding CT images, for a set of training studies. Hence, the scheme obviates the need for expert delineations of the gland on CT for explicitly constructing a SSM for prostate segmentation on CT. The delineations of the prostate gland on MRI and CT allows for 3D reconstruction of the prostate shape which facilitates the building of the LSSM. In order to perform concurrent prostate MRI and CT segmentation using the LSSM, the authors employ a region-based level set approach where the authors deform the evolving prostate boundary to simultaneously fit to MRI and CT images in which voxels are classified to be either part of the prostate or outside the prostate. The classification is facilitated by using a combination of MRI-CT probabilistic spatial atlases and a random forest classifier, driven by gradient and Haar features.The authors acquire a total of 20 MRI-CT patient studies and use the leave-one-out strategy to train and evaluate four different LSSMs. First, a fusion-based LSSM (fLSSM) is built using expert ground truth delineations of the prostate on MRI alone, where the ground truth for the gland on CT is obtained via coregistration of the corresponding MRI and CT slices. The authors compare the fLSSM against another LSSM (xLSSM), where expert delineations of the gland on both MRI and CT are employed in the model building; xLSSM representing the idealized LSSM. The authors also compare the fLSSM against an exclusive CT-based SSM (ctSSM), built from expert delineations of the gland on CT alone. In addition, two LSSMs trained using trainee delineations (tLSSM) on CT are compared with the fLSSM. The results indicate that the xLSSM, tLSSMs, and the fLSSM perform equivalently, all of them out-performing the ctSSM.The fLSSM provides an accurate alternative to SSMs that require careful expert delineations of the SOI that may be difficult or laborious to obtain. Additionally, the fLSSM has the added benefit of providing concurrent segmentations of the SOI on multiple imaging modalities.
| S-EPMC3337664 | biostudies-other