Search

Your search keyword '"Zhoubing Xu"' showing total 110 results
Start Over Author "Zhoubing Xu"
110 results on '"Zhoubing Xu"'

1. A deep image-to-image network organ segmentation algorithm for radiation treatment planning: principles and evaluation

Author

Sebastian Marschner, Manasi Datarb, Aurélie Gaasch, Zhoubing Xu, Sasa Grbic, Guillaume Chabin, Bernhard Geiger, Julian Rosenman, Stefanie Corradini, Maximilian Niyazi, Tobias Heimann, Christian Möhler, Fernando Vega, Claus Belka, and Christian Thieke

Subjects
Radiation, Planning, Algorithm, Deep-image-to-image-network, Contour, Organs at risk, Medical physics. Medical radiology. Nuclear medicine, R895-920, Neoplasms. Tumors. Oncology. Including cancer and carcinogens, RC254-282
Abstract

Abstract Background We describe and evaluate a deep network algorithm which automatically contours organs at risk in the thorax and pelvis on computed tomography (CT) images for radiation treatment planning. Methods The algorithm identifies the region of interest (ROI) automatically by detecting anatomical landmarks around the specific organs using a deep reinforcement learning technique. The segmentation is restricted to this ROI and performed by a deep image-to-image network (DI2IN) based on a convolutional encoder-decoder architecture combined with multi-level feature concatenation. The algorithm is commercially available in the medical products “syngo.via RT Image Suite VB50” and “AI-Rad Companion Organs RT VA20” (Siemens Healthineers). For evaluation, thoracic CT images of 237 patients and pelvic CT images of 102 patients were manually contoured following the Radiation Therapy Oncology Group (RTOG) guidelines and compared to the DI2IN results using metrics for volume, overlap and distance, e.g., Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD95). The contours were also compared visually slice by slice. Results We observed high correlations between automatic and manual contours. The best results were obtained for the lungs (DSC 0.97, HD95 2.7 mm/2.9 mm for left/right lung), followed by heart (DSC 0.92, HD95 4.4 mm), bladder (DSC 0.88, HD95 6.7 mm) and rectum (DSC 0.79, HD95 10.8 mm). Visual inspection showed excellent agreements with some exceptions for heart and rectum. Conclusions The DI2IN algorithm automatically generated contours for organs at risk close to those by a human expert, making the contouring step in radiation treatment planning simpler and faster. Few cases still required manual corrections, mainly for heart and rectum.

Published
2022
Full Text
View/download PDF

2. Correction: A deep image-to-image network organ segmentation algorithm for radiation treatment planning: principles and evaluation

Author

Sebastian Marschner, Manasi Datar, Aurélie Gaasch, Zhoubing Xu, Sasa Grbic, Guillaume Chabin, Bernhard Geiger, Julian Rosenman, Stefanie Corradini, Maximilian Niyazi, Tobias Heimann, Christian Möhler, Fernando Vega, Claus Belka, and Christian Thieke

Subjects
Medical physics. Medical radiology. Nuclear medicine, R895-920, Neoplasms. Tumors. Oncology. Including cancer and carcinogens, RC254-282
Published
2022
Full Text
View/download PDF

3. Quantitative CT Imaging of Ventral Hernias: Preliminary Validation of an Anatomical Labeling Protocol.

Author

Zhoubing Xu, Andrew J Asman, Rebeccah B Baucom, Richard G Abramson, Benjamin K Poulose, and Bennett A Landman

Subjects
Medicine, Science
Abstract

We described and validated a quantitative anatomical labeling protocol for extracting clinically relevant quantitative parameters for ventral hernias (VH) from routine computed tomography (CT) scans. This information was then used to predict the need for mesh bridge closure during ventral hernia repair (VHR).A detailed anatomical labeling protocol was proposed to enable quantitative description of VH including shape, location, and surrounding environment (61 scans). Intra- and inter-rater reproducibilities were calculated for labeling on 18 and 10 clinically acquired CT scans, respectively. Preliminary clinical validation was performed by correlating 20 quantitative parameters derived from anatomical labeling with the requirement for mesh bridge closure at surgery (26 scans). Prediction of this clinical endpoint was compared with similar models fit on metrics from the semi-quantitative European Hernia Society Classification for Ventral Hernia (EHSCVH).High labeling reproducibilities were achieved for abdominal walls (±2 mm in mean surface distance), key anatomical landmarks (±5 mm in point distance), and hernia volumes (0.8 in Cohen's kappa). 9 out of 20 individual quantitative parameters of hernia properties were significantly different between patients who required mesh bridge closure versus those in whom fascial closure was achieved at the time of VHR (p

Published
2015
Full Text
View/download PDF

28. Quantification of Tomographic Patterns associated with COVID-19 from Chest CT.

Author

Shikha Chaganti, Abishek Balachandran, Guillaume Chabin, Stuart Cohen, Thomas Flohr 0001, Bogdan Georgescu, Philippe Grenier, Sasa Grbic, Siqi Liu 0001, François Mellot, Nicolas Murray, Savvas Nicolaou, William Parker, Thomas J. Re, Pina C. Sanelli, Alexander W. Sauter, Zhoubing Xu, Youngjin Yoo, Valentin Ziebandt, and Dorin Comaniciu

Published
2020

48. SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truth

Author

Zhoubing Xu, Shunxing Bao, Yuankai Huo, Michael R. Savona, Hyeonsoo Moon, Richard G. Abramson, Tamara K. Moyo, Albert Assad, and Bennett A. Landman

Subjects
FOS: Computer and information sciences, Ground truth, Modality (human–computer interaction), Radiological and Ultrasound Technology, Computer science, business.industry, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Pattern recognition, Image segmentation, Convolutional neural network, Article, 030218 nuclear medicine & medical imaging, Computer Science Applications, 03 medical and health sciences, 0302 clinical medicine, Segmentation, Artificial intelligence, Electrical and Electronic Engineering, business, Software
Abstract

A key limitation of deep convolutional neural networks (DCNN) based image segmentation methods is the lack of generalizability. Manually traced training images are typically required when segmenting organs in a new imaging modality or from distinct disease cohort. The manual efforts can be alleviated if the manually traced images in one imaging modality (e.g., MRI) are able to train a segmentation network for another imaging modality (e.g., CT). In this paper, we propose an end-to-end synthetic segmentation network (SynSeg-Net) to train a segmentation network for a target imaging modality without having manual labels. SynSeg-Net is trained by using (1) unpaired intensity images from source and target modalities, and (2) manual labels only from source modality. SynSeg-Net is enabled by the recent advances of cycle generative adversarial networks (CycleGAN) and DCNN. We evaluate the performance of the SynSeg-Net on two experiments: (1) MRI to CT splenomegaly synthetic segmentation for abdominal images, and (2) CT to MRI total intracranial volume synthetic segmentation (TICV) for brain images. The proposed end-to-end approach achieved superior performance to two stage methods. Moreover, the SynSeg-Net achieved comparable performance to the traditional segmentation network using target modality labels in certain scenarios. The source code of SynSeg-Net is publicly available (https://github.com/MASILab/SynSeg-Net)., Comment: IEEE Transactions on Medical Imaging (TMI)

Published
2019
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results