Cited 22 times in
Feasibility of Continual Deep Learning-Based Segmentation for Personalized Adaptive Radiation Therapy in Head and Neck Area
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 금기창 | - |
dc.contributor.author | 김나리 | - |
dc.contributor.author | 김진성 | - |
dc.contributor.author | 이창걸 | - |
dc.contributor.author | 장지석 | - |
dc.date.accessioned | 2021-04-29T17:14:01Z | - |
dc.date.available | 2021-04-29T17:14:01Z | - |
dc.date.issued | 2021-02 | - |
dc.identifier.uri | https://ir.ymlib.yonsei.ac.kr/handle/22282913/182243 | - |
dc.description.abstract | This study investigated the feasibility of deep learning-based segmentation (DLS) and continual training for adaptive radiotherapy (RT) of head and neck (H&N) cancer. One-hundred patients treated with definitive RT were included. Based on 23 organs-at-risk (OARs) manually segmented in initial planning computed tomography (CT), modified FC-DenseNet was trained for DLS: (i) using data obtained from 60 patients, with 20 matched patients in the test set (DLSm); (ii) using data obtained from 60 identical patients with 20 unmatched patients in the test set (DLSu). Manually contoured OARs in adaptive planning CT for independent 20 patients were provided as test sets. Deformable image registration (DIR) was also performed. All 23 OARs were compared using quantitative measurements, and nine OARs were also evaluated via subjective assessment from 26 observers using the Turing test. DLSm achieved better performance than both DLSu and DIR (mean Dice similarity coefficient; 0.83 vs. 0.80 vs. 0.70), mainly for glandular structures, whose volume significantly reduced during RT. Based on subjective measurements, DLS is often perceived as a human (49.2%). Furthermore, DLSm is preferred over DLSu (67.2%) and DIR (96.7%), with a similar rate of required revision to that of manual segmentation (28.0% vs. 29.7%). In conclusion, DLS was effective and preferred over DIR. Additionally, continual DLS training is required for an effective optimization and robustness in personalized adaptive RT. | - |
dc.description.statementOfResponsibility | open | - |
dc.language | English | - |
dc.publisher | MDPI | - |
dc.relation.isPartOf | CANCERS | - |
dc.rights | CC BY-NC-ND 2.0 KR | - |
dc.title | Feasibility of Continual Deep Learning-Based Segmentation for Personalized Adaptive Radiation Therapy in Head and Neck Area | - |
dc.type | Article | - |
dc.contributor.college | College of Medicine (의과대학) | - |
dc.contributor.department | Dept. of Radiation Oncology (방사선종양학교실) | - |
dc.contributor.googleauthor | Nalee Kim | - |
dc.contributor.googleauthor | Jaehee Chun | - |
dc.contributor.googleauthor | Jee Suk Chang | - |
dc.contributor.googleauthor | Chang Geol Lee | - |
dc.contributor.googleauthor | Ki Chang Keum | - |
dc.contributor.googleauthor | Jin Sung Kim | - |
dc.identifier.doi | 10.3390/cancers13040702 | - |
dc.contributor.localId | A00272 | - |
dc.contributor.localId | A05709 | - |
dc.contributor.localId | A04548 | - |
dc.contributor.localId | A03240 | - |
dc.contributor.localId | A04658 | - |
dc.relation.journalcode | J03449 | - |
dc.identifier.eissn | 2072-6694 | - |
dc.identifier.pmid | 33572310 | - |
dc.contributor.alternativeName | Keum, Ki Chang | - |
dc.contributor.affiliatedAuthor | 금기창 | - |
dc.contributor.affiliatedAuthor | 김나리 | - |
dc.contributor.affiliatedAuthor | 김진성 | - |
dc.contributor.affiliatedAuthor | 이창걸 | - |
dc.contributor.affiliatedAuthor | 장지석 | - |
dc.citation.volume | 13 | - |
dc.citation.number | 4 | - |
dc.citation.startPage | 702 | - |
dc.identifier.bibliographicCitation | CANCERS, Vol.13(4) : 702, 2021-02 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.