Scalable radiotherapy data curation infrastructure for deep-learning based autosegmentation of organs-at-risk: A case study in head and neck cancer
In this era of patient-centered, outcomes-driven and adaptive radiotherapy, deep learning is now being successfully applied to tackle imaging-related workflow bottlenecks such as autosegmentation and dose planning. These applications typically require supervised learning approaches enabled by relati...
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-08-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.936134/full |
| _version_ | 1811282972314173440 |
|---|---|
| author | E. Tryggestad A. Anand C. Beltran J. Brooks J. Cimmiyotti N. Grimaldi T. Hodge A. Hunzeker J. J. Lucido N. N. Laack R. Momoh D. J. Moseley S. H. Patel A. Ridgway S. Seetamsetty S. Shiraishi L. Undahl R. L. Foote |
| author_facet | E. Tryggestad A. Anand C. Beltran J. Brooks J. Cimmiyotti N. Grimaldi T. Hodge A. Hunzeker J. J. Lucido N. N. Laack R. Momoh D. J. Moseley S. H. Patel A. Ridgway S. Seetamsetty S. Shiraishi L. Undahl R. L. Foote |
| author_sort | E. Tryggestad |
| collection | DOAJ |
| description | In this era of patient-centered, outcomes-driven and adaptive radiotherapy, deep learning is now being successfully applied to tackle imaging-related workflow bottlenecks such as autosegmentation and dose planning. These applications typically require supervised learning approaches enabled by relatively large, curated radiotherapy datasets which are highly reflective of the contemporary standard of care. However, little has been previously published describing technical infrastructure, recommendations, methods or standards for radiotherapy dataset curation in a holistic fashion. Our radiation oncology department has recently embarked on a large-scale project in partnership with an external partner to develop deep-learning-based tools to assist with our radiotherapy workflow, beginning with autosegmentation of organs-at-risk. This project will require thousands of carefully curated radiotherapy datasets comprising all body sites we routinely treat with radiotherapy. Given such a large project scope, we have approached the need for dataset curation rigorously, with an aim towards building infrastructure that is compatible with efficiency, automation and scalability. Focusing on our first use-case pertaining to head and neck cancer, we describe our developed infrastructure and novel methods applied to radiotherapy dataset curation, inclusive of personnel and workflow organization, dataset selection, expert organ-at-risk segmentation, quality assurance, patient de-identification, data archival and transfer. Over the course of approximately 13 months, our expert multidisciplinary team generated 490 curated head and neck radiotherapy datasets. This task required approximately 6000 human-expert hours in total (not including planning and infrastructure development time). This infrastructure continues to evolve and will support ongoing and future project efforts. |
| first_indexed | 2024-04-13T02:02:08Z |
| format | Article |
| id | doaj.art-deea417b4dd644b8bf14536d3f6ef88a |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-13T02:02:08Z |
| publishDate | 2022-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-deea417b4dd644b8bf14536d3f6ef88a2022-12-22T03:07:36ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-08-011210.3389/fonc.2022.936134936134Scalable radiotherapy data curation infrastructure for deep-learning based autosegmentation of organs-at-risk: A case study in head and neck cancerE. Tryggestad0A. Anand1C. Beltran2J. Brooks3J. Cimmiyotti4N. Grimaldi5T. Hodge6A. Hunzeker7J. J. Lucido8N. N. Laack9R. Momoh10D. J. Moseley11S. H. Patel12A. Ridgway13S. Seetamsetty14S. Shiraishi15L. Undahl16R. L. Foote17Department of Radiation Oncology, Mayo Clinic Rochester, Rochester, MN, United StatesDepartment of Radiation Oncology, Mayo Clinic Arizona, Phoenix, AZ, United StatesDepartment of Radiation Oncology, Mayo Clinic Florida, Jacksonville, FL, United StatesDepartment of Radiation Oncology, Mayo Clinic Rochester, Rochester, MN, United StatesDepartment of Radiation Oncology, Mayo Clinic Rochester, Rochester, MN, United StatesDepartment of Radiation Oncology, Mayo Clinic Rochester, Rochester, MN, United StatesDepartment of Radiation Oncology, Mayo Clinic Rochester, Rochester, MN, United StatesDepartment of Radiation Oncology, Mayo Clinic Rochester, Rochester, MN, United StatesDepartment of Radiation Oncology, Mayo Clinic Rochester, Rochester, MN, United StatesDepartment of Radiation Oncology, Mayo Clinic Rochester, Rochester, MN, United StatesDepartment of Radiation Oncology, Mayo Clinic Rochester, Rochester, MN, United StatesDepartment of Radiation Oncology, Mayo Clinic Rochester, Rochester, MN, United StatesDepartment of Radiation Oncology, Mayo Clinic Arizona, Phoenix, AZ, United StatesDepartment of Radiation Oncology, Mayo Clinic Arizona, Phoenix, AZ, United StatesDepartment of Radiation Oncology, Mayo Clinic Rochester, Rochester, MN, United StatesDepartment of Radiation Oncology, Mayo Clinic Rochester, Rochester, MN, United StatesDepartment of Radiation Oncology, Mayo Clinic Rochester, Rochester, MN, United StatesDepartment of Radiation Oncology, Mayo Clinic Rochester, Rochester, MN, United StatesIn this era of patient-centered, outcomes-driven and adaptive radiotherapy, deep learning is now being successfully applied to tackle imaging-related workflow bottlenecks such as autosegmentation and dose planning. These applications typically require supervised learning approaches enabled by relatively large, curated radiotherapy datasets which are highly reflective of the contemporary standard of care. However, little has been previously published describing technical infrastructure, recommendations, methods or standards for radiotherapy dataset curation in a holistic fashion. Our radiation oncology department has recently embarked on a large-scale project in partnership with an external partner to develop deep-learning-based tools to assist with our radiotherapy workflow, beginning with autosegmentation of organs-at-risk. This project will require thousands of carefully curated radiotherapy datasets comprising all body sites we routinely treat with radiotherapy. Given such a large project scope, we have approached the need for dataset curation rigorously, with an aim towards building infrastructure that is compatible with efficiency, automation and scalability. Focusing on our first use-case pertaining to head and neck cancer, we describe our developed infrastructure and novel methods applied to radiotherapy dataset curation, inclusive of personnel and workflow organization, dataset selection, expert organ-at-risk segmentation, quality assurance, patient de-identification, data archival and transfer. Over the course of approximately 13 months, our expert multidisciplinary team generated 490 curated head and neck radiotherapy datasets. This task required approximately 6000 human-expert hours in total (not including planning and infrastructure development time). This infrastructure continues to evolve and will support ongoing and future project efforts.https://www.frontiersin.org/articles/10.3389/fonc.2022.936134/fullcurationartificial intelligencedeep learningconvolutional neural networkautosegmentationradiotherapy |
| spellingShingle | E. Tryggestad A. Anand C. Beltran J. Brooks J. Cimmiyotti N. Grimaldi T. Hodge A. Hunzeker J. J. Lucido N. N. Laack R. Momoh D. J. Moseley S. H. Patel A. Ridgway S. Seetamsetty S. Shiraishi L. Undahl R. L. Foote Scalable radiotherapy data curation infrastructure for deep-learning based autosegmentation of organs-at-risk: A case study in head and neck cancer Frontiers in Oncology curation artificial intelligence deep learning convolutional neural network autosegmentation radiotherapy |
| title | Scalable radiotherapy data curation infrastructure for deep-learning based autosegmentation of organs-at-risk: A case study in head and neck cancer |
| title_full | Scalable radiotherapy data curation infrastructure for deep-learning based autosegmentation of organs-at-risk: A case study in head and neck cancer |
| title_fullStr | Scalable radiotherapy data curation infrastructure for deep-learning based autosegmentation of organs-at-risk: A case study in head and neck cancer |
| title_full_unstemmed | Scalable radiotherapy data curation infrastructure for deep-learning based autosegmentation of organs-at-risk: A case study in head and neck cancer |
| title_short | Scalable radiotherapy data curation infrastructure for deep-learning based autosegmentation of organs-at-risk: A case study in head and neck cancer |
| title_sort | scalable radiotherapy data curation infrastructure for deep learning based autosegmentation of organs at risk a case study in head and neck cancer |
| topic | curation artificial intelligence deep learning convolutional neural network autosegmentation radiotherapy |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2022.936134/full |
| work_keys_str_mv | AT etryggestad scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT aanand scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT cbeltran scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT jbrooks scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT jcimmiyotti scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT ngrimaldi scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT thodge scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT ahunzeker scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT jjlucido scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT nnlaack scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT rmomoh scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT djmoseley scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT shpatel scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT aridgway scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT sseetamsetty scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT sshiraishi scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT lundahl scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer AT rlfoote scalableradiotherapydatacurationinfrastructurefordeeplearningbasedautosegmentationoforgansatriskacasestudyinheadandneckcancer |