Segmentation Of Organs At Risk Research Articles

Shape Constrained Fully Convolutional DenseNet with Adversarial Training for Multi-organ Segmentation on Head and Neck Low Field MR Images

MR guided radiotherapy provides images not only for patient positioning but also for online adaptive radiotherapy. Accurate delineation of organs-at-risk (OARs) on Head and Neck (H&N) MR images is valuable to both initial treatment planning and adaptive planning, but manual contouring is laborious and inconsistent. A novel method based on the generative adversarial network (GAN) with shape constraint (SC-GAN) is developed for fully automated H&N OARs segmentation on CT and low field MRI. A deep supervised fully convolutional DenseNet is employed as the segmentation network for voxel-wise prediction. A CNN based discriminator network is then utilized to correct predicted errors and image-level inconsistency between the prediction and ground truth. An additional shape representation loss between the prediction and ground truth in the latent shape space is integrated into the segmentation and adversarial loss functions to reduce false positivity and constrain the predicted shapes. The proposed segmentation method was first benchmarked on a public H&N database including 32 patients, and then on 25 0.35T MR images obtained from an MR guided radiotherapy system. The OARs include brainstem, optical chiasm, larynx (MR only), mandible, pharynx (MR only), parotid glands (both left and right), optical nerves (both left and right), and submandibular glands (both left and right, CT only). The performance of the proposed SC-GAN was compared with GAN alone and GAN with SRM but without the Densenet (GAN-SRM) to quantify the contributions of shape constraint and DenseNet in the deep neural network segmentation. The proposed SC-GAN slightly but consistently improves the segmentation accuracy on the benchmark H&N CT images compared with our previous deep segmentation network, which outperformed other published methods on the same or similar CT H&N dataset. On the low field MR dataset, the following average Dice’s indices were obtained using improved SC-GAN: 0.916 (Brainstem), 0.589 (Optical chiasm), 0.816 (Mandible), 0.703 (Optical nerves), 0.799 (Larynx), 0.706 (Pharynx), and 0.845 (Parotid glands). The average surface distances ranged from 0.68mm (Brainstem) to 1.70mm (Larynx). The 95% surface distance ranged from 1.48mm (Left optical nerve) to 3.92mm (Larynx). Compared with CT, using 95% surface distance evaluation, the automated segmentation accuracy is higher on MR for the brainstem, optical chiasm, optical nerves and parotids, and lower for the mandible. The SC-GAN performance is superior to GAN-SRM, which is more accurate than GAN alone on both the CT and MR datasets. The segmentation time for one patient is 14 seconds using a single GPU. The shape constrained FCNN is further improved by incorporating GAN and DenseNet. With the novel method, we showed that the low field MR images acquired on a MR guided radiation radiotherapy system can support accurate and fully automated segmentation of both bony and soft tissue OARs for adaptive radiotherapy.

Organs at Risk Delineation for Brain Tumor Radiation Planning in Patients with Glioblastoma Using Deep Learning

Our standalone software, using deep learning technology, performs fully automatic organs at risk (OAR) segmentation within the brain in 2 minutes for brain radiation planning in patients with glioblastoma (GBM). The aim of the present study is to evaluate, if fully automated segmentation of the OAR within the brain in GBM patients is non-inferior to human rater segmentation for radiation planning. We included post-OP T1w, T1c, T2w and FLAIR MRI datasets of 23 patients with newly diagnosed, surgically resected and histologically confirmed GBM. Manual segmentations of the brain OAR (brainstem, cochleae, eyes, hippocampus, lacrimal glands, lenses, optic chiasm, optic nerves, pituitary gland and retinae) according to Scoccianti et al. (Scoccianti 2015) were performed by 3 experienced radiation oncologists on the T1c MRI sequence. For fully automatic segmentation, we developed an OAR segmentation method. The MRI data was co-registered for automatic segmentation. Manual delineations were utilized for training the deep learning system based on the U-Net architecture. We evaluated the segmentation method on the results of a 6-fold cross-validation considering the imaging data of all patients in terms of dice-coefficient (DC) (volumetric overlap) and volume similarity (VS) using the Kruskal-Wallis test. Median DC and interquartile range (IQR) of the different pairings of expert raters (reported as tuples) were (0.74, 0.19), (0.67, 0.28) and (0.72, 0.20) for all OAR structures combined. The results of the automatic segmentation compared to the three different raters were (0.63, 0.39), (0.65, 0.36) and (0.63, 0.41). Large distribution of DC and VS were observed for small OAR like the left cochlea between the raters [(0.78, 0.12), (0.43, 0.13), (0.49, 0.12); Kruskal-Wallis test: chi-square=43.80, p=0.001)] and the automatic method: [(0.00, 0.23), (0.00, 0.26), (0.00, 0.18; Kruskal-Wallis test: chi-square=81.29, p=0.001)]. The cochlea was missed completely by the automatic method in 9 patients. For larger OAR, such as the brainstem, no statistical difference was detected between measured volumes among raters (Kruskal-Wallis test: chi-square=4.6, p=0.098) [(0.91, 0.02), (0.91, 0.02), (0.89, 0.02)], and compared to the automatic segmentation: [(0.91, 0.02), (0.91, 0.01), (0.90, 0.02)]. The performance of the proposed system is highly dependent on the raters agreement. The higher the agreement among raters, the better predicts the prototype the OAR within the brain. With this proof of concept study, we generate first promising results, and plan next steps to improve results.

Shape constrained fully convolutional DenseNet with adversarial training for multiorgan segmentation on head and neck CT and low-field MR images.

Image-guided radiotherapy provides images not only for patient positioning but also for online adaptive radiotherapy. Accurate delineation of organs-at-risk (OARs) on Head and Neck (H&N) CT and MR images is valuable to both initial treatment planning and adaptive planning, but manual contouring is laborious and inconsistent. A novel method based on the generative adversarial network (GAN) with shape constraint (SC-GAN) is developed for fully automated H&N OARs segmentation on CT and low-field MRI. A deep supervised fully convolutional DenseNet is employed as the segmentation network for voxel-wise prediction. A convolutional neural network (CNN)-based discriminator network is then utilized to correct predicted errors and image-level inconsistency between the prediction and ground truth. An additional shape representation loss between the prediction and ground truth in the latent shape space is integrated into the segmentation and adversarial loss functions to reduce false positivity and constrain the predicted shapes. The proposed segmentation method was first benchmarked on a public H&N CT database including 32 patients, and then on 25 0.35T MR images obtained from an MR-guided radiotherapy system. The OARs include brainstem, optical chiasm, larynx (MR only), mandible, pharynx (MR only), parotid glands (both left and right), optical nerves (both left and right), and submandibular glands (both left and right, CT only). The performance of the proposed SC-GAN was compared with GAN alone and GAN with the shape constraint (SC) but without the DenseNet (SC-GAN-ResNet) to quantify the contributions of shape constraint and DenseNet in the deep neural network segmentation. The proposed SC-GAN slightly but consistently improve the segmentation accuracy on the benchmark H&N CT images compared with our previous deep segmentation network, which outperformed other published methods on the same or similar CT H&N dataset. On the low-field MR dataset, the following average Dice's indices were obtained using improved SC-GAN: 0.916 (brainstem), 0.589 (optical chiasm), 0.816 (mandible), 0.703 (optical nerves), 0.799 (larynx), 0.706 (pharynx), and 0.845 (parotid glands). The average surface distances ranged from 0.68mm (brainstem) to 1.70mm (larynx). The 95% surface distance ranged from 1.48mm (left optical nerve) to 3.92mm (larynx). Compared with CT, using 95% surface distance evaluation, the automated segmentation accuracy is higher on MR for the brainstem, optical chiasm, optical nerves and parotids, and lower for the mandible. The SC-GAN performance is superior to SC-GAN-ResNet, which is more accurate than GAN alone on both the CT and MR datasets. The segmentation time for one patient is 14seconds using a single GPU. The performance of our previous shape constrained fully CNNs for H&N segmentation is further improved by incorporating GAN and DenseNet. With the novel segmentation method, we showed that the low-field MR images acquired on a MR-guided radiation radiotherapy system can support accurate and fully automated segmentation of both bony and soft tissue OARs for adaptive radiotherapy.

Deep convolutional neural network for segmentation of thoracic organs-at-risk using cropped 3D images.

Automatic segmentation of organs-at-risk (OARs) is a key step in radiation treatment planning to reduce human efforts and bias. Deep convolutional neural networks (DCNN) have shown great success in many medical image segmentation applications but there are still challenges in dealing with large 3D images for optimal results. The purpose of this study is to develop a novel DCNN method for thoracic OARs segmentation using cropped 3D images. To segment the five organs (left and right lungs, heart, esophagus and spinal cord) from the thoracic CT scans, preprocessing to unify the voxel spacing and intensity was first performed, a 3D U-Net was then trained on resampled thoracic images to localize each organ, then the original images were cropped to only contain one organ and served as the input to each individual organ segmentation network. The segmentation maps were then merged to get the final results. The network structures were optimized for each step, as well as the training and testing strategies. A novel testing augmentation with multiple iterations of image cropping was used. The networks were trained on 36 thoracic CT scans with expert annotations provided by the organizers of the 2017 AAPM Thoracic Auto-segmentation Challenge and tested on the challenge testing dataset as well as a private dataset. The proposed method earned second place in the live phase of the challenge and first place in the subsequent ongoing phase using a newly developed testing augmentation approach. It showed superior-than-human performance on average in terms of Dice scores (spinal cord: 0.893±0.044, right lung: 0.972±0.021, left lung: 0.979±0.008, heart: 0.925±0.015, esophagus: 0.726± 0.094), mean surface distance (spinal cord: 0.662±0.248mm, right lung: 0.933±0.574mm, left lung: 0.586±0.285mm, heart: 2.297±0.492mm, esophagus: 2.341±2.380mm) and 95% Hausdorff distance (spinal cord: 1.893±0.627mm, right lung: 3.958±2.845mm, left lung: 2.103±0.938mm, heart: 6.570±1.501mm, esophagus: 8.714±10.588mm). It also achieved good performance in the private dataset and reduced the editing time to 7.5min per patient following automatic segmentation. The proposed DCNN method demonstrated good performance in automatic OAR segmentation from thoracic CT scans. It has the potential for eventual clinical adoption of deep learning in radiation treatment planning due to improved accuracy and reduced cost for OAR segmentation.

Dual-energy CT for automatic organs-at-risk segmentation in brain-tumor patients using a multi-atlas and deep-learning approach

In radiotherapy, computed tomography (CT) datasets are mostly used for radiation treatment planning to achieve a high-conformal tumor coverage while optimally sparing healthy tissue surrounding the tumor, referred to as organs-at-risk (OARs). Based on CT scan and/or magnetic resonance images, OARs have to be manually delineated by clinicians, which is one of the most time-consuming tasks in the clinical workflow. Recent multi-atlas (MA) or deep-learning (DL) based methods aim to improve the clinical routine by an automatic segmentation of OARs on a CT dataset. However, so far no studies investigated the performance of these MA or DL methods on dual-energy CT (DECT) datasets, which have been shown to improve the image quality compared to conventional 120 kVp single-energy CT. In this study, the performance of an in-house developed MA and a DL method (two-step three-dimensional U-net) was quantitatively and qualitatively evaluated on various DECT-derived pseudo-monoenergetic CT datasets ranging from 40 keV to 170 keV. At lower energies, the MA method resulted in more accurate OAR segmentations. Both the qualitative and quantitative metric analysis showed that the DL approach often performed better than the MA method.

Multiorgan segmentation using distance-aware adversarial networks.

Segmentation of organs at risk (OAR) in computed tomography (CT) is of vital importance in radiotherapy treatment. This task is time consuming and for some organs, it is very challenging due to low-intensity contrast in CT. We propose a framework to perform the automatic segmentation of multiple OAR: esophagus, heart, trachea, and aorta. Different from previous works using deep learning techniques, we make use of global localization information, based on an original distance map that yields not only the localization of each organ, but also the spatial relationship between them. Instead of segmenting directly the organs, we first generate the localization map by minimizing a reconstruction error within an adversarial framework. This map that includes localization information of all organs is then used to guide the segmentation task in a fully convolutional setting. Experimental results show encouraging performance on CT scans of 60 patients totaling 11,084 slices in comparison with other state-of-the-art methods.

A recursive ensemble organ segmentation (REOS) framework: application in brain radiotherapy

The aim of this work is to develop a novel recursive ensemble OARs segmentation (REOS) framework for accurate organs-at-risk (OARs) automatic segmentation. The REOS recursively segment individual OARs by ensembling images features extracted from an organ localization module and a contour detection module. Both modules are based on a 3D U-Net architecture. The organ localization module is trained for rough segmentation to localize a region of interest (ROI) that encompasses the to-be-delineated OAR, while the contour detection module is trained to segment the OAR within the identified ROI. In this study, the developed REOS framework is applied for brain radiotherapy on segmenting six OARs including the eyes, the brainstem (BS), the optical nerves and the chiasm. Eighty T1-weighted magnetic resonance images (MRI) from 80 brain cancer patients’ cases with OARs’ gold standard contours were collected for training and testing REOS. On 20 testing cases, the REOS achieve a high segmentation accuracy with Dice similarity coefficient (DSC) mean and standard deviation of 93.9% ± 1.4%, 94.5% ± 2.0%, 90.6% ± 2.7%, on the left and right eyes and the BS, respectively. On small and segmentation-challenging organs, the left and right optical nerves and the chiasm, the REOS achieves DSC of 78.0% ± 10.5%, 82.2% ± 5.9% and 71.1% ± 9.1%. The satisfactory performances demonstrated the effectiveness of the REOS in OARs segmentation.

Fully automatic multi-organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks.

Intensity modulated radiation therapy (IMRT) is commonly employed for treating head and neck (H&N) cancer with uniform tumor dose and conformal critical organ sparing. Accurate delineation of organs-at-risk (OARs) on H&N CT images is thus essential to treatment quality. Manual contouring used in current clinical practice is tedious, time-consuming, and can produce inconsistent results. Existing automated segmentation methods are challenged by the substantial inter-patient anatomical variation and low CT soft tissue contrast. To overcome the challenges, we developed a novel automated H&N OARs segmentation method that combines a fully convolutional neural network (FCNN) with a shape representation model (SRM). Based on manually segmented H&N CT, the SRM and FCNN were trained in two steps: (a) SRM learned the latent shape representation of H&N OARs from the training dataset; (b) the pre-trained SRM with fixed parameters were used to constrain the FCNN training. The combined segmentation network was then used to delineate nine OARs including the brainstem, optic chiasm, mandible, optical nerves, parotids, and submandibular glands on unseen H&N CT images. Twenty-two and 10 H&N CT scans provided by the Public Domain Database for Computational Anatomy (PDDCA) were utilized for training and validation, respectively. Dice similarity coefficient (DSC), positive predictive value (PPV), sensitivity (SEN), average surface distance (ASD), and 95% maximum surface distance (95%SD) were calculated to quantitatively evaluate the segmentation accuracy of the proposed method. The proposed method was compared with an active appearance model that won the 2015 MICCAI H&N Segmentation Grand Challenge based on the same dataset, an atlas method and a deep learning method based on different patient datasets. An average DSC = 0.870 (brainstem), DSC = 0.583 (optic chiasm), DSC = 0.937 (mandible), DSC = 0.653 (left optic nerve), DSC = 0.689 (right optic nerve), DSC = 0.835 (left parotid), DSC = 0.832 (right parotid), DSC = 0.755 (left submandibular), and DSC = 0.813 (right submandibular) were achieved. The segmentation results are consistently superior to the results of atlas and statistical shape based methods as well as a patch-wise convolutional neural network method. Once the networks are trained off-line, the average time to segment all 9 OARs for an unseen CT scan is 9.5 s. Experiments on clinical datasets of H&N patients demonstrated the effectiveness of the proposed deep neural network segmentation method for multi-organ segmentation on volumetric CT scans. The accuracy and robustness of the segmentation were further increased by incorporating shape priors using SMR. The proposed method showed competitive performance and took shorter time to segment multiple organs in comparison to state of the art methods.

SEGMENTATION OF ORGANS AT RISK IN THORACIC CT IMAGES USING A SHARPMASK ARCHITECTURE AND CONDITIONAL RANDOM FIELDS.

Cancer is one of the leading causes of death worldwide. Radiotherapy is a standard treatment for this condition and the first step of the radiotherapy process is to identify the target volumes to be targeted and the healthy organs at risk (OAR) to be protected. Unlike previous methods for automatic segmentation of OAR that typically use local information and individually segment each OAR, in this paper, we propose a deep learning framework for the joint segmentation of OAR in CT images of the thorax, specifically the heart, esophagus, trachea and the aorta. Making use of Fully Convolutional Networks (FCN), we present several extensions that improve the performance, including a new architecture that allows to use low level features with high level information, effectively combining local and global information for improving the localization accuracy. Finally, by using Conditional Random Fields (specifically the CRF as Recurrent Neural Network model), we are able to account for relationships between the organs to further improve the segmentation results. Experiments demonstrate competitive performance on a dataset of 30 CT scans.

Joint Segmentation of Multiple Thoracic Organs in CT Images with Two Collaborative Deep Architectures.

Computed Tomography (CT) is the standard imaging technique for radiotherapy planning. The delineation of Organs at Risk (OAR) in thoracic CT images is a necessary step before radiotherapy, for preventing irradiation of healthy organs. However, due to low contrast, multi-organ segmentation is a challenge. In this paper, we focus on developing a novel framework for automatic delineation of OARs. Different from previous works in OAR segmentation where each organ is segmented separately, we propose two collaborative deep architectures to jointly segment all organs, including esophagus, heart, aorta and trachea. Since most of the organ borders are ill-defined, we believe spatial relationships must be taken into account to overcome the lack of contrast. The aim of combining two networks is to learn anatomical constraints with the first network, which will be used in the second network, when each OAR is segmented in turn. Specifically, we use the first deep architecture, a deep SharpMask architecture, for providing an effective combination of low-level representations with deep high-level features, and then take into account the spatial relationships between organs by the use of Conditional Random Fields (CRF). Next, the second deep architecture is employed to refine the segmentation of each organ by using the maps obtained on the first deep architecture to learn anatomical constraints for guiding and refining the segmentations. Experimental results show superior performance on 30 CT scans, comparing with other state-of-the-art methods.

TH‐CD‐206‐05: Machine‐Learning Based Segmentation of Organs at Risks for Head and Neck Radiotherapy Planning

Purpose:Accurate and efficient delineation of tumor target and organs‐at‐risks is essential for the success of radiotherapy. In reality, despite of decades of intense research efforts, auto‐segmentation has not yet become clinical practice. In this study, we present, for the first time, a deep learning‐based classification algorithm for autonomous segmentation in head and neck (HaN) treatment planning.Methods:Fifteen HN datasets of CT, MR and PET images with manual annotation of organs‐at‐risk (OARs) including spinal cord, brainstem, optic nerves, chiasm, eyes, mandible, tongue, parotid glands were collected and saved in a library of plans. We also have ten super‐resolution MR images of the tongue area, where the genioglossus and inferior longitudinalis tongue muscles are defined as organs of interest. We applied the concepts of random forest‐ and deep learning‐based object classification for automated image annotation with the aim of using machine learning to facilitate head and neck radiotherapy planning process. In this new paradigm of segmentation, random forests were used for landmark‐assisted segmentation of super‐resolution MR images. Alternatively to auto‐segmentation with random forest‐based landmark detection, deep convolutional neural networks were developed for voxel‐wise segmentation of OARs in single and multi‐modal images. The network consisted of three pairs of convolution and pooing layer, one RuLU layer and a softmax layer.Results:We present a comprehensive study on using machine learning concepts for auto‐segmentation of OARs and tongue muscles for the HaN radiotherapy planning. An accuracy of 81.8% in terms of Dice coefficient was achieved for segmentation of genioglossus and inferior longitudinalis tongue muscles. Preliminary results of OARs regimentation also indicate that deep‐learning afforded an unprecedented opportunities to improve the accuracy and robustness of radiotherapy planning.Conclusion:A novel machine learning framework has been developed for image annotation and structure segmentation. Our results indicate the great potential of deep learning in radiotherapy treatment planning.

SU‐F‐T‐411: A Quantitative Parameter for Treatment Plan Quality

Purpose:To create an IMRT treatment plan quantitative score using QUANTEC dose/volume parameters to assess plan quality.Methods:132 IMRT patient plans of various treatment sites were evaluated. The optimized plan's dose volume histogram (DVH) was exported to Velocity for evaluation. The proposed scoring was based on calculating the shortest distance from the QUANTEC objective to the DVH line of each organ. Each plan was normalized against the “perfect” plan where the organs at risk (OAR) received no dose and hence the distance between the QUANTEC objective and the DVH line was maximized. The normalized scores allowed comparing the quality of plans across the treatment sites, dosimetrists, and physicians. The scores were plotted and statistically analyzed to serve as basis for future plans.Results:The score for each site was evaluated and the average percentage score resulted in the abdomen having an average percent score of 1.68 ± 1.49, 34.61 ± 35.19, 11.00 ± 15.39, 28.44 ± 25.13, 1.99 ± 5.83 for abdomen, brain, chest, head/neck, and pelvis. Differences in scores between the treatment sites are largely attributed to OAR segmentation and proximity of the OAR to the PTV. Small score differences between dosimetrist were attributed to the number of plans they have completed per site. A larger sample of treatment plans is being evaluated to investigate the effect of dosimetrist's experience on plan quality.Conclusion:This approach allows comparison of patient treatments which will help improve patient care and treatment outcomes with a quantitative score. A larger number of patient plans is being evaluated for improved statistics.

Validation of clinical acceptability of an atlas-based segmentation algorithm for the delineation of organs at risk in head and neck cancer.

The aim of this study was to assess whether clinically acceptable segmentations of organs at risk (OARs) in head and neck cancer can be obtained automatically and efficiently using the novel "similarity and truth estimation for propagated segmentations" (STEPS) compared to the traditional "simultaneous truth and performance level estimation" (STAPLE) algorithm. First, 6 OARs were contoured by 2 radiation oncologists in a dataset of 100 patients with head and neck cancer on planning computed tomography images. Each image in the dataset was then automatically segmented with STAPLE and STEPS using those manual contours. Dice similarity coefficient (DSC) was then used to compare the accuracy of these automatic methods. Second, in a blind experiment, three separate and distinct trained physicians graded manual and automatic segmentations into one of the following three grades: clinically acceptable as determined by universal delineation guidelines (grade A), reasonably acceptable for clinical practice upon manual editing (grade B), and not acceptable (grade C). Finally, STEPS segmentations graded B were selected and one of the physicians manually edited them to grade A. Editing time was recorded. Significant improvements in DSC can be seen when using the STEPS algorithm on large structures such as the brainstem, spinal canal, and left/right parotid compared to the STAPLE algorithm (all p < 0.001). In addition, across all three trained physicians, manual and STEPS segmentation grades were not significantly different for the brainstem, spinal canal, parotid (right/left), and optic chiasm (all p > 0.100). In contrast, STEPS segmentation grades were lower for the eyes (p < 0.001). Across all OARs and all physicians, STEPS produced segmentations graded as well as manual contouring at a rate of 83%, giving a lower bound on this rate of 80% with 95% confidence. Reduction in manual interaction time was on average 61% and 93% when automatic segmentations did and did not, respectively, require manual editing. The STEPS algorithm showed better performance than the STAPLE algorithm in segmenting OARs for radiotherapy of the head and neck. It can automatically produce clinically acceptable segmentation of OARs, with results as relevant as manual contouring for the brainstem, spinal canal, the parotids (left/right), and optic chiasm. A substantial reduction in manual labor was achieved when using STEPS even when manual editing was necessary.

Prospective randomized double-blind study of atlas-based organ-at-risk autosegmentation-assisted radiation planning in head and neck cancer

Background and purposeTarget volumes and organs-at-risk (OARs) for radiotherapy (RT) planning are manually defined, which is a tedious and inaccurate process. We sought to assess the feasibility, time reduction, and acceptability of an atlas-based autosegmentation (AS) compared to manual segmentation (MS) of OARs. Materials and methodsA commercial platform generated 16 OARs. Resident physicians were randomly assigned to modify AS OAR (AS+R) or to draw MS OAR followed by attending physician correction. Dice similarity coefficient (DSC) was used to measure overlap between groups compared with attending approved OARs (DSC=1 means perfect overlap). 40 cases were segmented. ResultsMean±SD segmentation time in the AS+R group was 19.7±8.0min, compared to 28.5±8.0min in the MS cohort, amounting to a 30.9% time reduction (Wilcoxon p<0.01). For each OAR, AS DSC was statistically different from both AS+R and MS ROIs (all Steel–Dwass p<0.01) except the spinal cord and the mandible, suggesting oversight of AS/MS processes is required; AS+R and MS DSCs were non-different. AS compared to attending approved OAR DSCs varied considerably, with a chiasm mean±SD DSC of 0.37±0.32 and brainstem of 0.97±0.03. ConclusionsAutosegmentation provides a time savings in head and neck regions of interest generation. However, attending physician approval remains vital.

Atlas-based automatic segmentation of head and neck organs at risk and nodal target volumes: a clinical validation

BackgroundIntensity modulated radiotherapy for head and neck cancer necessitates accurate definition of organs at risk (OAR) and clinical target volumes (CTV). This crucial step is time consuming and prone to inter- and intra-observer variations. Automatic segmentation by atlas deformable registration may help to reduce time and variations. We aim to test a new commercial atlas algorithm for automatic segmentation of OAR and CTV in both ideal and clinical conditions.MethodsThe updated Brainlab automatic head and neck atlas segmentation was tested on 20 patients: 10 cN0-stages (ideal population) and 10 unselected N-stages (clinical population). Following manual delineation of OAR and CTV, automatic segmentation of the same set of structures was performed and afterwards manually corrected. Dice Similarity Coefficient (DSC), Average Surface Distance (ASD) and Maximal Surface Distance (MSD) were calculated for “manual to automatic” and “manual to corrected” volumes comparisons.ResultsIn both groups, automatic segmentation saved about 40% of the corresponding manual segmentation time. This effect was more pronounced for OAR than for CTV. The edition of the automatically obtained contours significantly improved DSC, ASD and MSD. Large distortions of normal anatomy or lack of iodine contrast were the limiting factors.ConclusionsThe updated Brainlab atlas-based automatic segmentation tool for head and neck Cancer patients is timesaving but still necessitates review and corrections by an expert.

Interobserver variation in clinical target volume and organs at risk segmentation in post-parotidectomy radiotherapy: can segmentation protocols help?

A study of interobserver variation in the segmentation of the post-operative clinical target volume (CTV) and organs at risk (OARs) for parotid tumours was undertaken. The segmentation exercise was performed as a baseline, and repeated after 3 months using a segmentation protocol to assess whether CTV conformity improved. Four head and neck oncologists independently segmented CTVs and OARs (contralateral parotid, spinal cord and brain stem) on CT data sets of five patients post parotidectomy. For each CTV or OAR delineation, total volume was calculated. The conformity level (CL) between different clinicians' outlines was measured using a validated outline analysis tool. The data for CTVs were re-analysed after using the cochlear sparing therapy and conventional radiation segmentation protocol. Significant differences in CTV morphology were observed at baseline, yielding a mean CL of 30% (range 25-39%). The CL improved after using the segmentation protocol with a mean CL of 54% (range 50-65%). For OARs, the mean CL was 60% (range 53-68%) for the contralateral parotid gland, 23% (range 13-27%) for the brain stem and 25% (range 22-31%) for the spinal cord. There was low conformity for CTVs and OARs between different clinicians. The CL for CTVs improved with use of a segmentation protocol, but the CLs remained lower than expected. This study supports the need for clear guidelines for segmentation of target and OARs to compare and interpret the results of head and neck cancer radiation studies.

Evaluation of an atlas-based automatic segmentation software for the delineation of brain organs at risk in a radiation therapy clinical context

Background and purpose Conformal radiation therapy techniques require the delineation of volumes of interest, a time-consuming and operator-dependent task. In this work, we aimed to evaluate the potential interest of an atlas-based automatic segmentation software (ABAS) of brain organs at risk (OAR), when used under our clinical conditions. Materials and methods Automatic and manual segmentations of the eyes, optic nerves, optic chiasm, pituitary gland, brain stem and cerebellum of 11 patients on T1-weighted magnetic resonance, 3-mm thick slice images were compared using the Dice similarity coefficient (DSC). The sensitivity and specificity of the ABAS were also computed and analysed from a radiotherapy point of view by splitting the ROC (Receiver Operating Characteristic) space into four sub-regions. Results Automatic segmentation of OAR was achieved in 7–8 min. Excellent agreement was obtained between automatic and manual delineations for organs exceeding 7 cm 3: the DSC was greater than 0.8. For smaller structures, the DSC was lower than 0.41. Conclusions These tests demonstrated that this ABAS is a robust and reliable tool for automatic delineation of large structures under clinical conditions in our daily practice, even though the small structures must continue to be delineated manually by an expert.