Dataset Information

Geometric and dosimetric evaluations of atlas-based segmentation methods of MR images in the head and neck region.

ABSTRACT: Owing to its excellent soft-tissue contrast, magnetic resonance (MR) imaging has found an increased application in radiation therapy (RT). By harnessing these properties for treatment planning, automated segmentation methods can alleviate the manual workload burden to the clinical workflow. We investigated atlas-based segmentation methods of organs at risk (OARs) in the head and neck (H&N) region using one approach that selected the most similar atlas from a library of segmented images and two multi-atlas approaches. The latter were based on weighted majority voting and an iterative atlas-fusion approach called STEPS. We built the atlas library from pre-treatment T1-weighted MR images of 12 patients with manual contours of the parotids, spinal cord and mandible, delineated by a clinician. Following a leave-one-out cross-validation strategy, we measured the geometric accuracy by calculating Dice similarity coefficients (DSC), standard and 95% Hausdorff distances (HD and HD95), and the mean surface distance (MSD), whereby the manual contours served as the gold standard. To benchmark the algorithm, we determined the inter-observer variability (IOV) between three observers. To investigate the dosimetric effect of segmentation inaccuracies, we implemented an auto-planning strategy within the treatment planning system Monaco (Elekta AB, Stockholm, Sweden). For each set of auto-segmented OARs, we generated a plan for a 9-beam step and shoot intensity modulated RT treatment, designed according to our institution's clinical H&N protocol. Superimposing the dose distributions on the gold standard OARs, we calculated dose differences to OARs caused by delineation differences between auto-segmented and gold standard OARs. We investigated the correlations between geometric and dosimetric differences. The mean DSC was larger than 0.8 and the mean MSD smaller than 2?mm for the multi-atlas approaches, resulting in a geometric accuracy comparable to previously published results and within the range of the IOV. While dosimetric differences could be as large as 23% of the clinical goal, treatment plans fulfilled all imposed clinical goals for the gold standard OARs. Correlations between geometric and dosimetric measures were low with R2??

SUBMITTER: Kieselmann JP

PROVIDER: S-EPMC6296440 | biostudies-literature | 2018 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Geometric and dosimetric evaluations of atlas-based segmentation methods of MR images in the head and neck region.

Kieselmann J P JP Kamerling C P CP Burgos N N Menten M J MJ Fuller C D CD Nill S S Cardoso M J MJ Oelfke U U

Physics in medicine and biology 20180711 14

Owing to its excellent soft-tissue contrast, magnetic resonance (MR) imaging has found an increased application in radiation therapy (RT). By harnessing these properties for treatment planning, automated segmentation methods can alleviate the manual workload burden to the clinical workflow. We investigated atlas-based segmentation methods of organs at risk (OARs) in the head and neck (H&N) region using one approach that selected the most similar atlas from a library of segmented images and two m ...[more]

PMID: 29882749

Similar Datasets

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.

Project description:BackgroundBoluses are routinely used in radiotherapy to modify surface doses. Nevertheless, considerable dose discrepancies may occur in some cases due to fit inaccuracy of commercially available standard flat boluses. Moreover, due to the simple geometric design of conventional boluses, also surrounding healthy skin areas may be unintentionally covered, resulting in the unwanted dose buildup. With the fused deposition modeling (FDM) technique, there is a simple and possibly cost-effective way to solve these problems in routine clinical practice. This paper presents a procedure of self-manufacturing bespoke patient-specific silicone boluses and the evaluation of buildup and fit accuracy in comparison to standard rectangular commercially available silicone boluses.Methods3D-conformal silicone boluses were custom-built to cover the surgical scar region of 25 patients who received adjuvant radiotherapy of head and neck cancer at the University Hospital Würzburg. During a standard CT-based planning procedure, a 5-mm-thick 3D bolus contour was generated to cover the radiopaque marked surgical scar with an additional safety margin. From these digital contours, molds were 3D printed and poured with silicone. Dose measurements for both types of boluses were performed with radiochromic films (EBT3) at three points per patient-at least one aimed to be in the high-dose area (scar) and one in the lower-dose area (spared healthy skin). Surface-bolus distance, which ideally should not be present, was determined from cone-beam CT performed for positioning control. The dosimetric influence of surface-bolus distance was also determined on slab phantom for different field sizes. The trial was performed with hardware that may be routinely available in every radiotherapy department, with the exception of the 3D printer. The required number of patients was determined based on the results of preparatory measurements with the help of the statistical consultancy of the University of Würzburg. The number of measuring points represents the total number of patients.ResultsIn the high-dose area of the scar, there was a significantly better intended dose buildup of 2.45% (95%CI 0.0014-0.0477, p = 0.038, N = 30) in favor of a 3D-conformal bolus. Median distances between the body surface and bolus differed significantly between 3D-conformal and commercially available boluses (3.5 vs. 7.9 mm, p = 0.001). The surface dose at the slab phantom did not differ between commercially available and 3D-conformal boluses. Increasing the surface-bolus distance from 5 to 10 mm decreased the surface dose by approximately 2% and 11% in the 6 × 6- and 3 × 3-cm2 fields, respectively. In comparison to the commercially available bolus, an unintended dose buildup in the healthy skin areas was reduced by 25.9% (95%CI 19.5-32.3, p < 0.01, N = 37) using the 3D-conformal bolus limited to the region surrounding the surgical scar.ConclusionsUsing 3D-conformal boluses allows a comparison to the commercially available boluses' dose buildup in the covered areas. Smaller field size is prone to a larger surface-bolus distance effect. Higher conformity of 3D-conformal boluses reduces this effect. This may be especially relevant for volumetric modulated arc therapy (VMAT) and intensity-modulated radiotherapy (IMRT) techniques with a huge number of smaller fields. High conformity of 3D-conformal boluses reduces an unintended dose buildup in healthy skin. The limiting factor in the conformity of 3D-conformal boluses in our setting was the immobilization mask, which was produced primarily for the 3D boluses. The mask itself limited tight contact of subsequently produced 3D-conformal boluses to the mask-covered body areas. In this respect, bolus adjustment before mask fabrication will be done in the future setting.

Project description:PURPOSE:We evaluated the feasibility of using an automatic segmentation tool to delineate cardiac substructures from noncontrast computed tomography (CT) images for cardiac dosimetry and toxicity analyses for patients with nonsmall cell lung cancer (NSCLC) after radiotherapy. MATERIAL AND METHODS:We used an in-house developed multi-atlas segmentation tool to delineate 11cardiac substructures, including the whole heart, four heart chambers, and six greater vessels, automatically from the averaged 4D-CT planning images of 49 patients with NSCLC. Two experienced radiation oncologists edited the auto-segmented contours. Times for automatic segmentation and modification were recorded. The modified contours were compared with the auto-segmented contours in terms of Dice similarity coefficient (DSC) and mean surface distance (MSD) to evaluate the extent of modification. Differences in dose-volume histogram (DVH) characteristics were also evaluated for the modified versus auto-segmented contours. RESULTS:The mean automatic segmentation time for all 11 structures was 7-9?min. For the 49 patients, the mean DSC values (±SD) ranged from .73?±?.08 to .95?±?.04, and the mean MSD values ranged from 1.3?±?.6?mm to 2.9?±?5.1?mm. Overall, the modifications were small; the largest modifications were in the pulmonary vein and the inferior vena cava. The heart V30 (volume receiving dose ?30?Gy) and the mean dose to the whole heart and the four heart chambers were not different for the modified versus the auto-segmented contours based on the statistically significant condition of p?<?.05. Also, the maximum dose to the great vessels was no different except for the pulmonary vein. CONCLUSIONS:Automatic segmentation of cardiac substructures did not require substantial modifications. Dosimetric evaluation showed no significant difference between the auto-segmented and modified contours for most structures, which suggests that the auto-segmented contours can be used to study cardiac dose-responses in clinical practice.

Project description:The location and extent of white matter lesions on magnetic resonance imaging (MRI) are important criteria for diagnosis, follow-up and prognosis of multiple sclerosis (MS). Clinical trials have shown that quantitative values, such as lesion volumes, are meaningful in MS prognosis. Manual lesion delineation for the segmentation of lesions is, however, time-consuming and suffers from observer variability. In this paper, we propose MSmetrix, an accurate and reliable automatic method for lesion segmentation based on MRI, independent of scanner or acquisition protocol and without requiring any training data. In MSmetrix, 3D T1-weighted and FLAIR MR images are used in a probabilistic model to detect white matter (WM) lesions as an outlier to normal brain while segmenting the brain tissue into grey matter, WM and cerebrospinal fluid. The actual lesion segmentation is performed based on prior knowledge about the location (within WM) and the appearance (hyperintense on FLAIR) of lesions. The accuracy of MSmetrix is evaluated by comparing its output with expert reference segmentations of 20 MRI datasets of MS patients. Spatial overlap (Dice) between the MSmetrix and the expert lesion segmentation is 0.67 ± 0.11. The intraclass correlation coefficient (ICC) equals 0.8 indicating a good volumetric agreement between the MSmetrix and expert labelling. The reproducibility of MSmetrix' lesion volumes is evaluated based on 10 MS patients, scanned twice with a short interval on three different scanners. The agreement between the first and the second scan on each scanner is evaluated through the spatial overlap and absolute lesion volume difference between them. The spatial overlap was 0.69 ± 0.14 and absolute total lesion volume difference between the two scans was 0.54 ± 0.58 ml. Finally, the accuracy and reproducibility of MSmetrix compare favourably with other publicly available MS lesion segmentation algorithms, applied on the same data using default parameter settings.

Dataset Information

Geometric and dosimetric evaluations of atlas-based segmentation methods of MR images in the head and neck region.

Publications

Geometric and dosimetric evaluations of atlas-based segmentation methods of MR images in the head and neck region.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets