The delineation of target and organs-at-risk (OARs) is a necessary step in radiotherapy treatment planning. The accuracy of the target and OAR contours directly affects the quality of radiotherapy plans. Manual contouring of OARs is the routine procedure at present, which, however, is very time-consuming and requires significant expertise, especially for those head-and-neck (HN) cancer cases, where OARs densely distribute around tumors with complex anatomical structures. In this study, we propose a deep learning-based fully automated delineation method, namely, mask scoring regional convolutional neural network (MS-RCNN), to obtain consistent and reliable OAR contours in HN CT. In the model, MR images were synthesized by a cycle-consistent generative adversarial network given CT images. A backbone network was utilized to extract features from MRI and CT independently. The high bony-structure contrast in CT and soft-tissue contrast in MRI are complementary in nature. Through combining those complementary contrasts, the accuracy of OAR delineation is expected to be improved. Due to the ability of various object detection and classification, ResNet 101 was used as backbone in MS-RCNN. Quantities including Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), mean surface distance (MSD), and residual mean square distance (RMS) were calculated to evaluate the performance of the proposed method. An average DSC, HD95, MSD and RMS of 0.78 (0.58 - 0.89), 4.88 mm (2.79 mm - 7.46 mm), 1.39 mm (0.69 mm - 1.99 mm), and 2.23 mm (1.30 mm - 3.23 mm), were respectively achieved across all of the 12 OARs by our proposed method. The proposed method is promising in facilitating auto-contouring for radiotherapy treatment planning.
This work presents a learning-based method to synthesize dual energy CT (DECT) images from conventional single energy CT (SECT). The proposed method uses a residual attention generative adversarial network. Residual blocks with attention gates were used to force the model to focus on the difference between DECT maps and SECT images. To evaluate the accuracy of the method, we retrospectively investigated 20 headand-neck cancer patients with both DECT and SECT scans available. The high and low energy CT images acquired from DECT acted as learning targets in the training process for SECT datasets and were evaluated against results from the proposed method using a leave-one-out cross-validation strategy. The synthesized DECT images showed an average mean absolute error around 30 Hounsfield Unit (HU) across the wholebody volume. These results strongly indicate the high accuracy of synthesized DECT image by our machinelearning-based method.
This work aims to develop an automatic multi-organ segmentation approach based on deep learning for head - and- neck region on dual energy CT. The proposed method proposed a Mask scoring R-CNN where comprehensive features are first learnt from two independent pyramid networks and then are combined via deep attention strategy to highlight the informative ones extracted from both two channels of low and high energy CT. To perform multi-organ segmentation and solve the problem of misclassification, a mask scoring subnetwork was integrated into the Mask R-CNN framework to build the correlation between the class of potential detected organ’s ROI and the shape of that organ’s segmentation within that ROI. We trained and tested our model on DECT images from 66 head-and-neck cancer patients with manual contours of 19 organs as training target and ground truth. For large- and mid-sized organs such as brain and parotid, the proposed method successfully achieved average Dice similarity coefficient (DSC) larger than 0.8. For small-sized organs with very low contrast such as chiasm, cochlea, lens and optic nerves, the DSCs ranged between 0.5 and 0.8. With the propose method, using DECT images outperforms using SECT in all 19 organs with statistical significance in DSC (p<0.05). Quantitative results demonstrated the feasibility of the proposed method, the superiority of using DECT to conventional SECT, and the advantage of the proposed R-CNN over FCN. The proposed method has the potential to facilitate the current radiation therapy work flow in treatment planning.
Radiation treatment for head-and-neck (HN) cancers requires accurate treatment planning based on 3D patient models derived from CT images. In clinical practice, the treatment volumes and organs-at-risk (OARs) are manually contoured by experienced physicians. This tedious and time-consuming procedure limits clinical workflow and resources. In this work, we propose to use a 3D Faster R-CNN to automatically detect the location of head and neck organs, then apply a U-Net to segment the multi-organ contours, called U-RCNN. The mean Dice similarity coefficient (DSC) of esophagus, larynx, mandible, oral cavity, left parotid, right parotid, pharynx and spinal cord were ranging from 79% to 89%, which demonstrated the segmentation accuracy of the proposed U-RCNN method. This segmentation technique could be a useful tool to facilitate routine clinical workflow in H&N radiotherapy.
In this study, we propose a synthetic CT (sCT) aided MRI-CT deformable image registration for head and neck radiotherapy. An image synthesis network, cycle consistent generative adversarial network (CycleGAN), was first trained using 25 pre-aligned CT-MRI image pairs. Using the MR head and neck images, the trained CycleGAN then predicts sCT images, which were used as MRI’s surrogate in MRI-CT registration. Demons registration algorithm was used to perform the sCT-CT registration on 5 separate datasets. For comparison, the original MRI and CT images were registered using mutual information as similarity metric. Our results showed that the target registration errors after registration were on average 1.31 mm and 1.02 mm for MRI-CT and sCT-CT registration, respectively. The mean normalized cross correlation between the sCT and CT after registration was 0.97, indicating that the proposed method is a viable way to perform MRI-CT image registration for head neck patients.
We propose a method to automatically segment multiple organs at risk (OARs) from routinely-acquired thorax CT images using generative adversarial network (GAN). Multi-label U-Net was introduced in generator to enable end-to-end segmentation. Esophagus and spinal cord location information were used to train the GAN in specific regions of interest (ROI). The probability maps of new CT thorax multi-organ were generated by the well-trained network and fused to reconstruct the final contour. This proposed algorithm was evaluated using 20 patients' data with thorax CT images and manual contours. The mean Dice similarity coefficient (DSC) for esophagus, heart, left lung, right lung and spinal cord was 0.73±0.04, 0.85±0.02, 0.96±0.01, 0.97±0.02 and 0.88±0.03. This novel deep-learning-based approach with the GAN strategy can automatically and accurately segment multiple OARs in thorax CT images, which could be a useful tool to improve the efficiency of the lung radiotherapy treatment planning.
Accurate segmentation of organs-at-risk (OAR) is essential for treatment planning of head and neck (HaN) cancers. A desire to shift from manual segmentation to automated processes allows for more efficient treatment planning. However, the technology of automated segmentation is hindered by complex and irregular morphology, poor soft tissue contrast, artifacts from dental fillings, variability of patient's anatomy, and inter-observer variability. In this study, we propose a state-of-the-art automated segmentation of OAR using a multi-output support vector regression (MSVR) machine learning algorithm to address these challenges under various selectable parameters. Shape image features were extracted using the histogram of oriented gradients and ground truth boundaries were obtained from physicians. Automated delineation of the OAR was performed on CT images from 56 subjects consisting of the brain stem, cochleae, esophagus, eye globes, larynx, lenses, lips, mandible, oral cavity, parotid glands, spinal cord, submandibular glands, and thyroid. Testing was done on previously unseen CT images. Model performance was evaluated using the dice similarity coefficient (DSC) and leave-one-subject- out strategy. Segmentation results varied from 66.9% DSC for the left cochlea to 93.8% DSC for the left eye globe. Analysis of the performance of a state-of-the-art algorithm reported in literature compared to MSVR demonstrated similar or superior performance on the segmentation of the OAR listed in this study. The proposed MSVR model accurately and efficiently segmented the OAR using a representative database of 56 HaN CT images. Thus, this model is an effective tool to aid physicians in reducing diagnostic and prognostic time.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.