Autosegmentation for thoracic radiation treatment planning: A grand challenge at AAPM 2017

Yang, Jinzhong; Veeraraghavan, Harini; Armato, Samuel G.; Farahani, Keyvan; Kirby, Justin; Kalpathy-Kramer, Jayashree; Elmpt, Wouter van; Dekker, André; Han, Xiao; Feng, Xue; Aljabar, Paul; Oliveira, Bruno; Heyden, Brent van der; Zamdborg, Leonid; Lam, Dao; Gooding, Mark J.; Sharp, G

doi:10.1002/mp.13141

Cited by 197 publications

(212 citation statements)

References 30 publications

Supporting

Mentioning

202

Contrasting

Unclassified

Order By: Relevance

“…The datasets used in this work are obtained from 2017 AAPM Thoracic Auto‐segmentation Challenges. Reference shows the segmentation results from seven institutes. Five of seven institutes developed deep learning‐based methods, and the other two (institute #4 and #6) used multiatlas‐based methods.…”

Section: Discussionmentioning

confidence: 99%

“…The 35 sets of thoracic CT images used in this study are obtained from 2017 AAPM Thoracic Auto‐segmentation Challenges . Each scan contains the entire thoracic region, and manual contours are delineated according to RTOG1106 guidelines.…”

Section: Methodsmentioning

confidence: 99%

“…Each scan contains the entire thoracic region, and manual contours are delineated according to RTOG1106 guidelines. The detailed descriptions of the datasets can be found in references …”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Automatic multiorgan segmentation in thorax CT images using U‐net‐GAN

et al. 2019

View full text Add to dashboard Cite

Purpose Accurate and timely organs‐at‐risk (OARs) segmentation is key to efficient and high‐quality radiation therapy planning. The purpose of this work is to develop a deep learning‐based method to automatically segment multiple thoracic OARs on chest computed tomography (CT) for radiotherapy treatment planning. Methods We propose an adversarial training strategy to train deep neural networks for the segmentation of multiple organs on thoracic CT images. The proposed design of adversarial networks, called U‐Net‐generative adversarial network (U‐Net‐GAN), jointly trains a set of U‐Nets as generators and fully convolutional networks (FCNs) as discriminators. Specifically, the generator, composed of U‐Net, produces an image segmentation map of multiple organs by an end‐to‐end mapping learned from CT image to multiorgan‐segmented OARs. The discriminator, structured as an FCN, discriminates between the ground truth and segmented OARs produced by the generator. The generator and discriminator compete against each other in an adversarial learning process to produce the optimal segmentation map of multiple organs. Our segmentation results were compared with manually segmented OARs (ground truth) for quantitative evaluations in geometric difference, as well as dosimetric performance by investigating the dose‐volume histogram in 20 stereotactic body radiation therapy (SBRT) lung plans. Results This segmentation technique was applied to delineate the left and right lungs, spinal cord, esophagus, and heart using 35 patients’ chest CTs. The averaged dice similarity coefficient for the above five OARs are 0.97, 0.97, 0.90, 0.75, and 0.87, respectively. The mean surface distance of the five OARs obtained with proposed method ranges between 0.4 and 1.5 mm on average among all 35 patients. The mean dose differences on the 20 SBRT lung plans are −0.001 to 0.155 Gy for the five OARs. Conclusion We have investigated a novel deep learning‐based approach with a GAN strategy to segment multiple OARs in the thorax using chest CT images and demonstrated its feasibility and reliability. This is a potentially valuable method for improving the efficiency of chest radiotherapy treatment planning.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic multiorgan segmentation in thorax CT images using U‐net‐GAN

et al. 2019

View full text Add to dashboard Cite

show abstract

“…However, they all shown statistically superior performances than the rest of the entries, including deep learning and traditional atlas‐based methods. A review of the challenge was recently published to summarize the performances of different methods with their brief descriptions.…”

Section: Discussionmentioning

confidence: 99%

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

et al. 2019

Self Cite

View full text Add to dashboard Cite

Purpose 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. Methods 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. Results 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 ± 0.248 mm, right lung: 0.933 ± 0.574 mm, left lung: 0.586 ± 0.285 mm, heart: 2.297 ± 0.492 mm, esophagus: 2.341 ± 2.380 mm) and 95% Hausdorff distance (spinal cord: 1.893 ± 0.627 mm, right lung: 3.958 ± 2.845 mm, left lung: 2.103 ± 0.938 mm, heart: 6.570 ± 1.501 mm, esophagus: 8.714 ± 10.588 mm). It also achieved good performance in the private dataset and reduced the editing time to 7.5 min per patient following automatic segmentation. Conclusions 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.

show abstract

“…Essentially, this technique can only be applied to lung CT images, and the lung volume should be delineated before the approach can be applied. Existing auto‐segmentation tools could be used for lung auto‐delineation, but the tumor and high‐density vessels should be properly excluded from the lung region because they should not be corrected for density. The deep learning approaches are promising in achieving this goal, but a visual check of the lung contours are recommended before proceeding to density correction.…”

Section: Discussionmentioning

confidence: 99%

Technical Note: Density correction to improve CT number mapping in thoracic deformable image registration

Yang

Zhang

et al. 2019

Medical Physics

Self Cite

View full text Add to dashboard Cite

Purpose To improve the accuracy of computed tomography (CT) number mapping inside the lung in deformable image registration with large differences in lung volume for applications in vertical CT imaging and adaptive radiotherapy. Methods The deep inspiration breath hold (DIBH) CT image and the end of exhalation (EE) phase image in four‐dimensional CT of 14 thoracic cancer patients were used in this study. Lung volumes were manually delineated. A Demons‐based deformable registration was first applied to register the EE CT to the DIBH CT for each patient, and the resulting deformation vector field deformed the EE CT image to the DIBH CT space. Given that the mass of the lung remains the same during respiration, we created a mass‐preserving model to correlate lung density variations with volumetric changes, which were characterized by the Jacobian derived from the deformation field. The Jacobian determinant was used to correct the lung CT numbers transferred from the EE CT image. The absolute intensity differences created by subtracting the deformed EE CT from the DIBH CT with and without density correction were compared. Results The ratio of DIBH CT to EE CT lung volumes was 1.6 on average. The deformable registration registered the lung shape well, but the appearance of voxel intensities inside the lung was different, demonstrating the need for density correction. Without density correction, the mean and standard deviation of the absolute intensity difference between the deformed EE CT and the DIBH CT inside the lung were 54.5 ± 45.5 for all cases. After density correction, these numbers decreased to 18.1 ± 34.9, demonstrating greater accuracy. The cumulative histogram of the intensity difference also showed that density correction improved CT number mapping greatly. Conclusion Density correction improves CT number mapping inside the lung in deformable image registration for difficult cases with large lung volume differences.

show abstract

Autosegmentation for thoracic radiation treatment planning: A grand challenge at AAPM 2017

Cited by 197 publications

References 30 publications

Automatic multiorgan segmentation in thorax CT images using U‐net‐GAN

Automatic multiorgan segmentation in thorax CT images using U‐net‐GAN

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

Technical Note: Density correction to improve CT number mapping in thoracic deformable image registration

Contact Info

Product

Resources

About