Dataset Information

Automatic segmentation of head and neck CT images for radiotherapy treatment planning using multiple atlases, statistical appearance models, and geodesic active contours.

ABSTRACT: Accurate delineation of organs at risk (OARs) is a precondition for intensity modulated radiation therapy. However, manual delineation of OARs is time consuming and prone to high interobserver variability. Because of image artifacts and low image contrast between different structures, however, the number of available approaches for autosegmentation of structures in the head-neck area is still rather low. In this project, a new approach for automated segmentation of head-neck CT images that combine the robustness of multiatlas-based segmentation with the flexibility of geodesic active contours and the prior knowledge provided by statistical appearance models is presented.The presented approach is using an atlas-based segmentation approach in combination with label fusion in order to initialize a segmentation pipeline that is based on using statistical appearance models and geodesic active contours. An anatomically correct approximation of the segmentation result provided by atlas-based segmentation acts as a starting point for an iterative refinement of this approximation. The final segmentation result is based on using model to image registration and geodesic active contours, which are mutually influencing each other.18 CT images in combination with manually segmented labels of parotid glands and brainstem were used in a leave-one-out cross validation scheme in order to evaluate the presented approach. For this purpose, 50 different statistical appearance models have been created and used for segmentation. Dice coefficient (DC), mean absolute distance and max. Hausdorff distance between the autosegmentation results and expert segmentations were calculated. An average Dice coefficient of DC = 0.81 (right parotid gland), DC = 0.84 (left parotid gland), and DC = 0.86 (brainstem) could be achieved.The presented framework provides accurate segmentation results for three important structures in the head neck area. Compared to a segmentation approach based on using multiple atlases in combination with label fusion, the proposed hybrid approach provided more accurate results within a clinically acceptable amount of time.

SUBMITTER: Fritscher KD

PROVIDER: S-EPMC4000401 | biostudies-other | 2014 May

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

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.

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.

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.

Dataset Information

Automatic segmentation of head and neck CT images for radiotherapy treatment planning using multiple atlases, statistical appearance models, and geodesic active contours.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets