Literature DB >> 29559291

Deep Learning Algorithm for Auto-Delineation of High-Risk Oropharyngeal Clinical Target Volumes With Built-In Dice Similarity Coefficient Parameter Optimization Function.

Carlos E Cardenas1, Rachel E McCarroll2, Laurence E Court2, Baher A Elgohari3, Hesham Elhalawani4, Clifton D Fuller4, Mona J Kamal5, Mohamed A M Meheissen6, Abdallah S R Mohamed6, Arvind Rao7, Bowman Williams4, Andrew Wong4, Jinzhong Yang2, Michalis Aristophanous8.   

Abstract

PURPOSE: Automating and standardizing the contouring of clinical target volumes (CTVs) can reduce interphysician variability, which is one of the largest sources of uncertainty in head and neck radiation therapy. In addition to using uniform margin expansions to auto-delineate high-risk CTVs, very little work has been performed to provide patient- and disease-specific high-risk CTVs. The aim of the present study was to develop a deep neural network for the auto-delineation of high-risk CTVs. METHODS AND MATERIALS: Fifty-two oropharyngeal cancer patients were selected for the present study. All patients were treated at The University of Texas MD Anderson Cancer Center from January 2006 to August 2010 and had previously contoured gross tumor volumes and CTVs. We developed a deep learning algorithm using deep auto-encoders to identify physician contouring patterns at our institution. These models use distance map information from surrounding anatomic structures and the gross tumor volume as input parameters and conduct voxel-based classification to identify voxels that are part of the high-risk CTV. In addition, we developed a novel probability threshold selection function, based on the Dice similarity coefficient (DSC), to improve the generalization of the predicted volumes. The DSC-based function is implemented during an inner cross-validation loop, and probability thresholds are selected a priori during model parameter optimization. We performed a volumetric comparison between the predicted and manually contoured volumes to assess our model.
RESULTS: The predicted volumes had a median DSC value of 0.81 (range 0.62-0.90), median mean surface distance of 2.8 mm (range 1.6-5.5), and median 95th Hausdorff distance of 7.5 mm (range 4.7-17.9) when comparing our predicted high-risk CTVs with the physician manual contours.
CONCLUSIONS: These predicted high-risk CTVs provided close agreement to the ground-truth compared with current interobserver variability. The predicted contours could be implemented clinically, with only minor or no changes.
Copyright © 2018 Elsevier Inc. All rights reserved.

Entities:  

Mesh:

Year:  2018        PMID: 29559291     DOI: 10.1016/j.ijrobp.2018.01.114

Source DB:  PubMed          Journal:  Int J Radiat Oncol Biol Phys        ISSN: 0360-3016            Impact factor:   7.038


  34 in total

Review 1.  Artificial Intelligence in radiotherapy: state of the art and future directions.

Authors:  Giulio Francolini; Isacco Desideri; Giulia Stocchi; Viola Salvestrini; Lucia Pia Ciccone; Pietro Garlatti; Mauro Loi; Lorenzo Livi
Journal:  Med Oncol       Date:  2020-04-22       Impact factor: 3.064

Review 2.  Artificial intelligence in radiation oncology.

Authors:  Elizabeth Huynh; Ahmed Hosny; Christian Guthier; Danielle S Bitterman; Steven F Petit; Daphne A Haas-Kogan; Benjamin Kann; Hugo J W L Aerts; Raymond H Mak
Journal:  Nat Rev Clin Oncol       Date:  2020-08-25       Impact factor: 66.675

Review 3.  Head and Neck Cancer Adaptive Radiation Therapy (ART): Conceptual Considerations for the Informed Clinician.

Authors:  Jolien Heukelom; Clifton David Fuller
Journal:  Semin Radiat Oncol       Date:  2019-07       Impact factor: 5.934

Review 4.  Artificial Intelligence: reshaping the practice of radiological sciences in the 21st century.

Authors:  Issam El Naqa; Masoom A Haider; Maryellen L Giger; Randall K Ten Haken
Journal:  Br J Radiol       Date:  2020-02-01       Impact factor: 3.039

5.  Deep learning-based GTV contouring modeling inter- and intra- observer variability in sarcomas.

Authors:  Thibault Marin; Yue Zhuo; Rita Maria Lahoud; Fei Tian; Xiaoyue Ma; Fangxu Xing; Maryam Moteabbed; Xiaofeng Liu; Kira Grogg; Nadya Shusharina; Jonghye Woo; Ruth Lim; Chao Ma; Yen-Lin E Chen; Georges El Fakhri
Journal:  Radiother Oncol       Date:  2021-11-19       Impact factor: 6.280

6.  Use of Crowd Innovation to Develop an Artificial Intelligence-Based Solution for Radiation Therapy Targeting.

Authors:  Raymond H Mak; Michael G Endres; Jin H Paik; Rinat A Sergeev; Hugo Aerts; Christopher L Williams; Karim R Lakhani; Eva C Guinan
Journal:  JAMA Oncol       Date:  2019-05-01       Impact factor: 31.777

7.  Characterization of knowledge-based volumetric modulated arc therapy plans created by three different institutions' models for prostate cancer.

Authors:  Yoshihiro Ueda; Hajime Monzen; Jun-Ichi Fukunaga; Shingo Ohira; Mikoto Tamura; Osamu Suzuki; Shoki Inui; Masaru Isono; Masayoshi Miyazaki; Iori Sumida; Kazuhiko Ogawa; Teruki Teshima
Journal:  Rep Pract Oncol Radiother       Date:  2020-08-25

8.  Automatic Segmentation of Clinical Target Volumes for Post-Modified Radical Mastectomy Radiotherapy Using Convolutional Neural Networks.

Authors:  Zhikai Liu; Fangjie Liu; Wanqi Chen; Xia Liu; Xiaorong Hou; Jing Shen; Hui Guan; Hongnan Zhen; Shaobin Wang; Qi Chen; Yu Chen; Fuquan Zhang
Journal:  Front Oncol       Date:  2021-02-16       Impact factor: 6.244

9.  Training deep-learning segmentation models from severely limited data.

Authors:  Yao Zhao; Dong Joo Rhee; Carlos Cardenas; Laurence E Court; Jinzhong Yang
Journal:  Med Phys       Date:  2021-02-19       Impact factor: 4.071

10.  Oropharyngeal primary tumor segmentation for radiotherapy planning on magnetic resonance imaging using deep learning.

Authors:  Roque Rodríguez Outeiral; Paula Bos; Abrahim Al-Mamgani; Bas Jasperse; Rita Simões; Uulke A van der Heide
Journal:  Phys Imaging Radiat Oncol       Date:  2021-07-02
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.