• Corpus ID: 220249738

Generalizable Cone Beam CT Esophagus Segmentation Using In Silico Data Augmentation

  title={Generalizable Cone Beam CT Esophagus Segmentation Using In Silico Data Augmentation},
  author={Sadegh R. Alam and Tianfang Li and Si-Yuan Zhang and Pengpeng Zhang and Saad Nadeem},
Lung cancer radiotherapy entails high quality planning computed tomography (pCT) imaging of the patient with radiation oncologist contouring of the tumor and the organs at risk (OARs) at the start of the treatment. This is followed by weekly low-quality cone beam CT (CBCT) imaging for treatment setup and qualitative visual assessment of tumor and critical OARs. In this work, we aim to make the weekly CBCT assessment quantitative by automatically segmenting the most critical OAR, esophagus… 

Figures and Tables from this paper


Automatic multi-organ segmentation in thorax CT images using U-Net-GAN
A 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.
Autosegmentation for thoracic radiation treatment planning: A grand challenge at AAPM 2017
The results of the Thoracic Auto-Segmentation Challenge showed that the lungs and heart can be segmented fairly accurately by various algorithms, while deep-learning methods performed better on the esophagus.
Artifacts reduction method for phase-resolved Cone-Beam CT (CBCT) images via a prior-guided CNN
Inspired by the high correlation among the 4D-CBCT images at different phases, a prior image reconstructed from full-sampled projections beforehand is incorporated into a lightweight structured convolutional neural network (CNN) as one input channel, referred to as Prior-guided CNN.
Atlas ranking and selection for automatic segmentation of the esophagus from CT scans.
An online atlas selection approach to choose a subset of optimal atlases for multi-atlas segmentation to the delineate esophagus automatically is developed and validated with promising results.
Fully automated esophagus segmentation with a hierarchical deep learning approach
Several extensions that improve the performance of Fully Convolutional Networks are presented, 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.
Deep convolutional neural network for segmentation of thoracic organs-at-risk using cropped 3D images.
The proposed DCNN method demonstrated good performance in automatic OAR segmentation from thoracic CT scans and has the potential for eventual clinical adoption of deep learning in radiation treatment planning due to improved accuracy and reduced cost for O AR segmentation.
A Probabilistic Model for Automatic Segmentation of the Esophagus in 3-D CT Scans
The method is compared to an alternative approach that uses a particle filter instead of a Markov chain to infer the approximate esophagus shape, to the performance of a human observer and also to state of the art methods, which are all semiautomatic.
Scatter Artifacts Removal Using Learning-Based Method for CBCT in IGRT System
A scatter-correction algorithm based on a deep convolutional neural network to reduce artifacts for CBCT in an image-guided radiation therapy (IGRT) system to enhance the performance on such applications as dose estimation and segmentation is proposed.
Quantification of Local Metabolic Tumor Volume Changes by Registering Blended PET-CT Images for Prediction of Pathologic Tumor Response
This novel framework can replace the conventional approach that applies CT-CT transformation to the PET data for longitudinal evaluation of tumor response and achieve the highest accuracy with only one Jacobian co-occurrence texture feature.
Esophagus Segmentation from 3D CT Data Using Skeleton Prior-Based Graph Cut
An original method to segment in thoracic CT scans the 3D esophagus using a skeleton-shape model to guide the segmentation, which yields encouraging results over 6 patients.