Article
Engineering, Biomedical
Xianjin Dai, Yang Lei, Tonghe Wang, Anees H. Dhabaan, Mark McDonald, Jonathan J. Beitler, Walter J. Curran, Jun Zhou, Tian Liu, Xiaofeng Yang
Summary: The study aims to develop a fully automated approach for rapid and accurate multi-organ contouring in head-and-neck cancer patients using synthetic MRI and CBCT technology. By combining the information provided by MRI and CBCT, accurate multi-organ segmentation in HN cancer patients is expected. The proposed method shows promising results in terms of DSC values and can be a valuable tool for adaptive radiation therapy.
PHYSICS IN MEDICINE AND BIOLOGY
(2021)
Article
Multidisciplinary Sciences
Xianghua Ye, Dazhou Guo, Jia Ge, Senxiang Yan, Yi Xin, Yuchen Song, Yongheng Yan, Bing-shen Huang, Tsung-Min Hung, Zhuotun Zhu, Ling Peng, Yanping Ren, Rui Liu, Gong Zhang, Mengyuan Mao, Xiaohua Chen, Zhongjie Lu, Wenxiang Li, Yuzhen Chen, Lingyun Huang, Jing Xiao, Adam P. Harrison, Le Lu, Chien-Yu Lin, Dakai Jin, Tsung-Ying Ho
Summary: In this study, we propose an automated and highly effective stratified OAR segmentation system using deep learning (SOARS) that precisely delineates a comprehensive set of 42 H&N OARs. The results show that SOARS consistently outperforms other state-of-the-art methods in evaluations across different institutions, reducing workload significantly. Moreover, the segmentation and dosimetric accuracy are within or smaller than the inter-user variation.
NATURE COMMUNICATIONS
(2022)
Article
Physics, Multidisciplinary
Wei Wang, Qingxin Wang, Mengyu Jia, Zhongqiu Wang, Chengwen Yang, Daguang Zhang, Shujing Wen, Delong Hou, Ningbo Liu, Ping Wang, Jun Wang
Summary: The novel deep learning model SEB-Net was developed to improve the accuracy of automatic organs-at-risk (OARs) segmentation in CT images for head and neck (HaN) as well as small organs, achieving significantly higher Dice similarity coefficient and lower Hausdorff distance compared to other cutting-edge methods.
FRONTIERS IN PHYSICS
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Xianjin Dai, Yang Lei, Tonghe Wang, Jun Zhou, Justin Roper, Mark McDonald, Jonathan J. Beitler, Walter J. Curran, Tian Liu, Xiaofeng Yang
Summary: A deep learning-based automated OAR delineation method was developed in this study, utilizing synthetic MRI to enhance delineation accuracy. The proposed method outperformed current state-of-the-art algorithms in quantitatively evaluating OAR delineation performance on both in-house and public datasets.
Review
Chemistry, Multidisciplinary
Enrico Antonio Lo Faso, Orazio Gambino, Roberto Pirrone
Summary: The review focuses on delineation methods for head-neck cancer tumors, emphasizing the importance of multimodal images in radiotherapy. A comparison among different approaches highlights the gap in performance between computerized and manual methods.
APPLIED SCIENCES-BASEL
(2021)
Article
Multidisciplinary Sciences
Weijun Chen, Cheng Wang, Wenming Zhan, Yongshi Jia, Fangfang Ruan, Lingyun Qiu, Shuangyan Yang, Yucheng Li
Summary: Deep learning auto-segmentation technology provides good auto-contouring results for most organs in the chest and abdomen, meeting clinical planning requirements with slight modifications. However, using Atlas for auto-contouring yields inferior results compared to deep learning auto-segmentations, with only some organs usable clinically after modifications.
SCIENTIFIC REPORTS
(2021)
Article
Engineering, Biomedical
Xianjin Dai, Yang Lei, Tonghe Wang, Jun Zhou, Soumon Rudra, Mark McDonald, Walter J. Curran, Tian Liu, Xiaofeng Yang
Summary: This study develops a deep-learning-based automated multi-organ segmentation method using a novel R-CNN architecture, which can accurately and quickly delineate organ-at-risk in head-and-neck cancer radiotherapy, saving labor and time.
PHYSICS IN MEDICINE AND BIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
James C. Korte, Nicholas Hardcastle, Sweet Ping Ng, Brett Clark, Tomas Kron, Price Jackson
Summary: This study investigated multiple deep learning methods for automated segmentation of parotid glands, submandibular glands, and lymph nodes on MRI, finding that cascaded CNNs can generate high-resolution segmentations with improved geometric accuracy, with potential for clinical application in radiation therapy.
Article
Oncology
Seung Yeun Chung, Jee Suk Chang, Min Seo Choi, Yongjin Chang, Byong Su Choi, Jaehee Chun, Ki Chang Keum, Jin Sung Kim, Yong Bae Kim
Summary: The study demonstrated the feasibility of using deep learning-based auto-segmentation in breast radiotherapy planning. The correlation between auto-segmented and manual contours was acceptable, with mean DSC higher than 0.80 for all OARs. Additionally, the CTVs showed favorable results, with mean DSCs higher than 0.70 for all breast and regional lymph node CTVs.
RADIATION ONCOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yngve Mardal Moe, Aurora Rosvoll Groendahl, Oliver Tomic, Einar Dale, Eirik Malinen, Cecilia Marie Futsaether
Summary: This study evaluated the use of CNN for automatic delineation of GTV in FDG-PET/CT images of head and neck cancer patients. New structure-based metrics were introduced for in-depth evaluation of multi-structure auto-delineation. Results showed that models based on PET/CT images were more effective in identifying true GTV structures compared to models based solely on CT images.
EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING
(2021)
Article
Oncology
Shunyao Luan, Changchao Wei, Yi Ding, Xudong Xue, Wei Wei, Xiao Yu, Xiao Wang, Chi Ma, Benpeng Zhu
Summary: In this study, we propose a parallel network architecture called PCG-Net, which combines convolutional neural networks (CNN) and a Gate-Axial-Transformer (GAT) to effectively capture local and global information for the segmentation of Head and Neck (HN) Organs-At-Risks (OARs). We also employ a cascade graph module (CGM) to enhance feature fusion. Extensive experiments demonstrate that PCG-Net outperforms other methods in terms of accuracy and robustness in HN OARs segmentation.
FRONTIERS IN ONCOLOGY
(2023)
Article
Multidisciplinary Sciences
Feng Shi, Weigang Hu, Jiaojiao Wu, Miaofei Han, Jiazhou Wang, Wei Zhang, Qing Zhou, Jingjie Zhou, Ying Wei, Ying Shao, Yanbo Chen, Yue Yu, Xiaohuan Cao, Yiqiang Zhan, Xiang Sean Zhou, Yaozong Gao, Dinggang Shen
Summary: This paper proposes a lightweight deep learning framework, RTP-Net, for automatic, rapid, and precise initialization of organ-at-risk (OAR) and tumor delineation in radiotherapy. The framework achieves high accuracy and near real-time delineation, which could greatly accelerate the treatment planning process and reduce patient waiting time.
NATURE COMMUNICATIONS
(2022)
Article
Biology
Daisuke Kawahara, Masato Tsuneda, Shuichi Ozawa, Hiroyuki Okamoto, Mitsuhiro Nakamura, Teiji Nishio, Akito Saito, Yasushi Nagata
Summary: The current study proposes an auto-segmentation model using a stepwise deep neural network on CT images of head and neck cancer. The results show that the stepwise-network outperforms the atlas-based method and conventional U-net, indicating its potential value in improving the efficiency of head and neck radiotherapy treatment planning.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Review
Oncology
M. Chen, S. Wu, W. Zhao, Y. Zhou, Y. Zhou, G. Wang
Summary: The advancement of technology has introduced precision radiotherapy (RT), with the application of deep learning (DL) enabling automatic contouring of target volumes (TV) and organs at risk (OARs), potentially saving time and reducing inter-observer variability.
CANCER RADIOTHERAPIE
(2022)
Article
Oncology
Guillaume Vogin, Liza Hettal, Clarisse Bartau, Juliette Thariat, Marie-Virginie Claeys, Guillaume Peyraga, Paul Retif, Ulrike Schick, Delphine Antoni, Zsuzsa Bodgal, Frederic Dhermain, Loic Feuvret
Summary: The study evaluated inter-individual variability in delineation of common cranial organs at risk in neurooncology practice. Results showed higher Kappa index for larger OAR and lower for smaller OAR. Radiation oncologists performed better in all indicators compared to non-members.
RADIATION ONCOLOGY
(2021)