Literature DB >> 35094390

General and custom deep learning autosegmentation models for organs in head and neck, abdomen, and male pelvis.

Asma Amjad1, Jiaofeng Xu2, Dan Thill2, Colleen Lawton1, William Hall1, Musaddiq J Awan1, Monica Shukla1, Beth A Erickson1, X Allen Li1.   

Abstract

PURPOSE: To reduce workload and inconsistencies in organ segmentation for radiation treatment planning, we developed and evaluated general and custom autosegmentation models on computed tomography (CT) for three major tumor sites using a well-established deep convolutional neural network (DCNN).
METHODS: Five CT-based autosegmentation models for 42 organs at risk (OARs) in head and neck (HN), abdomen (ABD), and male pelvis (MP) were developed using a full three-dimensional (3D) DCNN architecture. Two types of deep learning (DL) models were separately trained using either general diversified multi-institutional datasets or custom well-controlled single-institution datasets. To improve segmentation accuracy, an adaptive spatial resolution approach for small and/or narrow OARs and a pseudo scan extension approach, when CT scan length is too short to cover entire organs, were implemented. The performance of the obtained models was evaluated based on accuracy and clinical applicability of the autosegmented contours using qualitative visual inspection and quantitative calculation of dice similarity coefficient (DSC), mean distance to agreement (MDA), and time efficiency.
RESULTS: The five DL autosegmentation models developed for the three anatomical sites were found to have high accuracy (DSC ranging from 0.8 to 0.98) for 74% OARs and marginally acceptable for 26% OARs. The custom models performed slightly better than the general models, even with smaller custom datasets used for the custom model training. The organ-based approaches improved autosegmentation accuracy for small or complex organs (e.g., eye lens, optic nerves, inner ears, and bowels). Compared with traditional manual contouring times, the autosegmentation times, including subsequent manual editing, if necessary, were substantially reduced by 88% for MP, 80% for HN, and 65% for ABD models.
CONCLUSIONS: The obtained autosegmentation models, incorporating organ-based approaches, were found to be effective and accurate for most OARs in the male pelvis, head and neck, and abdomen. We have demonstrated that our multianatomical DL autosegmentation models are clinically useful for radiation treatment planning.
© 2022 American Association of Physicists in Medicine.

Entities:  

Keywords:  CT-based autosegmentation; adaptive radiation therapy; deep learning; radiation therapy planning

Mesh:

Year:  2022        PMID: 35094390      PMCID: PMC8917093          DOI: 10.1002/mp.15507

Source DB:  PubMed          Journal:  Med Phys        ISSN: 0094-2405            Impact factor:   4.071


  51 in total

1.  Dosimetric benefit of adaptive re-planning in pancreatic cancer stereotactic body radiotherapy.

Authors:  Yongbao Li; Jeremy D P Hoisak; Nan Li; Carrie Jiang; Zhen Tian; Quentin Gautier; Masoud Zarepisheh; Zhaoxia Wu; Yaqiang Liu; Xun Jia; Jona Hattangadi-Gluth; Loren K Mell; Steve Jiang; James D Murphy
Journal:  Med Dosim       Date:  2015-05-19       Impact factor: 1.482

2.  Use of image registration and fusion algorithms and techniques in radiotherapy: Report of the AAPM Radiation Therapy Committee Task Group No. 132.

Authors:  Kristy K Brock; Sasa Mutic; Todd R McNutt; Hua Li; Marc L Kessler
Journal:  Med Phys       Date:  2017-05-23       Impact factor: 4.071

Review 3.  Uncertainties in volume delineation in radiation oncology: A systematic review and recommendations for future studies.

Authors:  Shalini K Vinod; Michael G Jameson; Myo Min; Lois C Holloway
Journal:  Radiother Oncol       Date:  2016-10-08       Impact factor: 6.280

Review 4.  Vision 20/20: perspectives on automated image segmentation for radiotherapy.

Authors:  Gregory Sharp; Karl D Fritscher; Vladimir Pekar; Marta Peroni; Nadya Shusharina; Harini Veeraraghavan; Jinzhong Yang
Journal:  Med Phys       Date:  2014-05       Impact factor: 4.071

5.  FocusNetv2: Imbalanced large and small organ segmentation with adversarial shape constraint for head and neck CT images.

Authors:  Yunhe Gao; Rui Huang; Yiwei Yang; Jie Zhang; Kainan Shao; Changjuan Tao; Yuanyuan Chen; Dimitris N Metaxas; Hongsheng Li; Ming Chen
Journal:  Med Image Anal       Date:  2020-10-10       Impact factor: 8.545

Review 6.  The changing therapeutic landscape of head and neck cancer.

Authors:  John D Cramer; Barbara Burtness; Quynh Thu Le; Robert L Ferris
Journal:  Nat Rev Clin Oncol       Date:  2019-06-12       Impact factor: 66.675

7.  Fast and robust adaptation of organs-at-risk delineations from planning scans to match daily anatomy in pre-treatment scans for online-adaptive radiotherapy of abdominal tumors.

Authors:  Vikas Gupta; Yibing Wang; Alejandra Méndez Romero; Andriy Myronenko; Petr Jordan; Calvin Maurer; Ben Heijmen; Mischa Hoogeman
Journal:  Radiother Oncol       Date:  2018-03-08       Impact factor: 6.280

8.  Clinical evaluation of atlas and deep learning based automatic contouring for lung cancer.

Authors:  Tim Lustberg; Johan van Soest; Mark Gooding; Devis Peressutti; Paul Aljabar; Judith van der Stoep; Wouter van Elmpt; Andre Dekker
Journal:  Radiother Oncol       Date:  2017-12-05       Impact factor: 6.280

9.  Dummy run for a phase II multi-institute trial of chemoradiotherapy for unresectable pancreatic cancer: inter-observer variance in contour delineation.

Authors:  Hideya Yamazaki; Kinji Nishiyama; Eiichi Tanaka; Keiichiro Koiwai; Naoto Shikama; Yoshinori Ito; Satoko Arahira; Tetsuro Tamamoto; Toru Shibata; Yoshio Tamaki; Takeshi Kodaira; Masahiko Oguchi
Journal:  Anticancer Res       Date:  2007 Jul-Aug       Impact factor: 2.480

10.  A Preliminary Experience of Implementing Deep-Learning Based Auto-Segmentation in Head and Neck Cancer: A Study on Real-World Clinical Cases.

Authors:  Yang Zhong; Yanju Yang; Yingtao Fang; Jiazhou Wang; Weigang Hu
Journal:  Front Oncol       Date:  2021-05-05       Impact factor: 6.244

View more
  2 in total

1.  Automatic Contour Refinement for Deep Learning Auto-segmentation of Complex Organs in MRI-guided Adaptive Radiation Therapy.

Authors:  Jie Ding; Ying Zhang; Asma Amjad; Jiaofeng Xu; Daniel Thill; X Allen Li
Journal:  Adv Radiat Oncol       Date:  2022-04-20

2.  Optimising a 3D convolutional neural network for head and neck computed tomography segmentation with limited training data.

Authors:  Edward G A Henderson; Eliana M Vasquez Osorio; Marcel van Herk; Andrew F Green
Journal:  Phys Imaging Radiat Oncol       Date:  2022-04-28
  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.