https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=34421066&retmode=xml&tool=Litmetric&email=readroberts32@gmail.com&api_key=61f08fa0b96a73de8c900d749fcb997acc09<?xml version="1.0" ?>
<!DOCTYPE PubmedArticleSet PUBLIC "-//NLM//DTD PubMedArticle, 1st January 2024//EN" "https://dtd.nlm.nih.gov/ncbi/pubmed/out/pubmed_240101.dtd">
<PubmedArticleSet>
<PubmedArticle><MedlineCitation Status="MEDLINE" Owner="NLM" IndexingMethod="Automated"><PMID Version="1">34421066</PMID><DateCompleted><Year>2021</Year><Month>08</Month><Day>24</Day></DateCompleted><DateRevised><Year>2021</Year><Month>08</Month><Day>24</Day></DateRevised><Article PubModel="Print"><Journal><ISSN IssnType="Electronic">1881-4883</ISSN><JournalIssue CitedMedium="Internet"><Volume>77</Volume><Issue>8</Issue><PubDate><Year>2021</Year></PubDate></JournalIssue><Title>Nihon Hoshasen Gijutsu Gakkai zasshi</Title><ISOAbbreviation>Nihon Hoshasen Gijutsu Gakkai Zasshi</ISOAbbreviation></Journal><ArticleTitle>[A Study on Radiation Dermatitis Grading Support System Based on Deep Learning by Hybrid Generation Method].</ArticleTitle><Pagination><StartPage>787</StartPage><EndPage>794</EndPage><MedlinePgn>787-794</MedlinePgn></Pagination><ELocationID EIdType="doi" ValidYN="Y">10.6009/jjrt.2021_JSRT_77.8.787</ELocationID><Abstract><AbstractText Label="PURPOSE" NlmCategory="OBJECTIVE">Radiation dermatitis is one of the most common adverse events in patients undergoing radiotherapy. However, the objective evaluation of this condition is difficult to provide because the clinical evaluation of radiation dermatitis is made by visual assessment based on Common Terminology Criteria for Adverse Events (CTCAE). Therefore, we created a radiation dermatitis grading support system (RDGS) using a deep convolutional neural network (DCNN) and then evaluated the effectiveness of the RDGS.</AbstractText><AbstractText Label="METHODS" NlmCategory="METHODS">The DCNN was trained with a dataset that comprised 647 clinical skin images graded with radiation dermatitis (Grades 1-4) at our center from April 2011 to May 2019. We created the datasets by mixing data augmentation images generated by image conversion and images generated by Poisson image editing using the hybrid generation method (Hyb) against lowvolume severe dermatitis (Grade 4). We then evaluated the classification accuracy of RDGS based on the hybrid generation method (Hyb-RDGS).</AbstractText><AbstractText Label="RESULTS" NlmCategory="RESULTS">The overall accuracy of the Hyb-RDGS was 85.1%, which was higher than that of the data augmentation method generally used for image generation.</AbstractText><AbstractText Label="CONCLUSION" NlmCategory="CONCLUSIONS">Effectiveness of the Hyb-RDGS using Poisson image editing was suggested. This result shows a possible supporting system for objective evaluation in grading radiation dermatitis.</AbstractText></Abstract><AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Wada</LastName><ForeName>Kiyotaka</ForeName><Initials>K</Initials><AffiliationInfo><Affiliation>Medipolis Proton Therapy and Research Center.</Affiliation></AffiliationInfo><AffiliationInfo><Affiliation>Graduate School of Science and Engineering, Kagoshima University.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Watanabe</LastName><ForeName>Mutsumi</ForeName><Initials>M</Initials><AffiliationInfo><Affiliation>Graduate School of Science and Engineering, Kagoshima University.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Shinchi</LastName><ForeName>Masahiro</ForeName><Initials>M</Initials><AffiliationInfo><Affiliation>Graduate School of Science and Engineering, Kagoshima University.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Noguchi</LastName><ForeName>Kousuke</ForeName><Initials>K</Initials><AffiliationInfo><Affiliation>Graduate School of Science and Engineering, Kagoshima University.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Mukoyoshi</LastName><ForeName>Tokie</ForeName><Initials>T</Initials><AffiliationInfo><Affiliation>Medipolis Proton Therapy and Research Center.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Matsuyama</LastName><ForeName>Mitsugi</ForeName><Initials>M</Initials><AffiliationInfo><Affiliation>Medipolis Proton Therapy and Research Center.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Arimura</LastName><ForeName>Takeshi</ForeName><Initials>T</Initials><AffiliationInfo><Affiliation>Medipolis Proton Therapy and Research Center.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Ogino</LastName><ForeName>Takashi</ForeName><Initials>T</Initials><AffiliationInfo><Affiliation>Medipolis Proton Therapy and Research Center.</Affiliation></AffiliationInfo></Author></AuthorList><Language>jpn</Language><PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType></PublicationTypeList></Article><MedlineJournalInfo><Country>Japan</Country><MedlineTA>Nihon Hoshasen Gijutsu Gakkai Zasshi</MedlineTA><NlmUniqueID>7505722</NlmUniqueID><ISSNLinking>0369-4305</ISSNLinking></MedlineJournalInfo><CitationSubset>IM</CitationSubset><MeshHeadingList><MeshHeading><DescriptorName UI="D000077321" MajorTopicYN="Y">Deep Learning</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D003872" MajorTopicYN="Y">Dermatitis</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D006801" MajorTopicYN="N">Humans</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D016571" MajorTopicYN="N">Neural Networks, Computer</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D018787" MajorTopicYN="Y">Radiation Oncology</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D012867" MajorTopicYN="N">Skin</DescriptorName></MeshHeading></MeshHeadingList><KeywordList Owner="NOTNLM"><Keyword MajorTopicYN="N">Poisson image editing</Keyword><Keyword MajorTopicYN="N">deep learning</Keyword><Keyword MajorTopicYN="N">radiation dermatitis</Keyword><Keyword MajorTopicYN="N">radiation dermatitis grading support system</Keyword><Keyword MajorTopicYN="N">radiotherapy</Keyword></KeywordList></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="entrez"><Year>2021</Year><Month>8</Month><Day>23</Day><Hour>6</Hour><Minute>17</Minute></PubMedPubDate><PubMedPubDate PubStatus="pubmed"><Year>2021</Year><Month>8</Month><Day>24</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>2021</Year><Month>8</Month><Day>25</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate></History><PublicationStatus>ppublish</PublicationStatus><ArticleIdList><ArticleId IdType="pubmed">34421066</ArticleId><ArticleId IdType="doi">10.6009/jjrt.2021_JSRT_77.8.787</ArticleId></ArticleIdList></PubmedData></PubmedArticle></PubmedArticleSet>