Hiroki Hase, Y. Mine, S. Okazaki, Yuki Yoshimi, S. Ito, Tzu-Yu Peng, Mizuho Sano, Yuma Koizumi, Naoya Kakimoto, Kotaro Tanimoto, Takeshi Murayama
{"title":"利用深度学习方法从颌面部 X 光片估测性别。","authors":"Hiroki Hase, Y. Mine, S. Okazaki, Yuki Yoshimi, S. Ito, Tzu-Yu Peng, Mizuho Sano, Yuma Koizumi, Naoya Kakimoto, Kotaro Tanimoto, Takeshi Murayama","doi":"10.4012/dmj.2023-253","DOIUrl":null,"url":null,"abstract":"The purpose of this study was to construct deep learning models for more efficient and reliable sex estimation. Two deep learning models, VGG16 and DenseNet-121, were used in this retrospective study. In total, 600 lateral cephalograms were analyzed. A saliency map was generated by gradient-weighted class activation mapping for each output. The two deep learning models achieved high values in each performance metric according to accuracy, sensitivity (recall), precision, F1 score, and areas under the receiver operating characteristic curve. Both models showed substantial differences in the positions indicated in saliency maps for male and female images. The positions in saliency maps also differed between VGG16 and DenseNet-121, regardless of sex. This analysis of our proposed system suggested that sex estimation from lateral cephalograms can be achieved with high accuracy using deep learning.","PeriodicalId":11065,"journal":{"name":"Dental materials journal","volume":null,"pages":null},"PeriodicalIF":1.9000,"publicationDate":"2024-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Sex estimation from maxillofacial radiographs using a deep learning approach.\",\"authors\":\"Hiroki Hase, Y. Mine, S. Okazaki, Yuki Yoshimi, S. Ito, Tzu-Yu Peng, Mizuho Sano, Yuma Koizumi, Naoya Kakimoto, Kotaro Tanimoto, Takeshi Murayama\",\"doi\":\"10.4012/dmj.2023-253\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The purpose of this study was to construct deep learning models for more efficient and reliable sex estimation. Two deep learning models, VGG16 and DenseNet-121, were used in this retrospective study. In total, 600 lateral cephalograms were analyzed. A saliency map was generated by gradient-weighted class activation mapping for each output. The two deep learning models achieved high values in each performance metric according to accuracy, sensitivity (recall), precision, F1 score, and areas under the receiver operating characteristic curve. Both models showed substantial differences in the positions indicated in saliency maps for male and female images. The positions in saliency maps also differed between VGG16 and DenseNet-121, regardless of sex. This analysis of our proposed system suggested that sex estimation from lateral cephalograms can be achieved with high accuracy using deep learning.\",\"PeriodicalId\":11065,\"journal\":{\"name\":\"Dental materials journal\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2024-04-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Dental materials journal\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.4012/dmj.2023-253\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"DENTISTRY, ORAL SURGERY & MEDICINE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Dental materials journal","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.4012/dmj.2023-253","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"DENTISTRY, ORAL SURGERY & MEDICINE","Score":null,"Total":0}
Sex estimation from maxillofacial radiographs using a deep learning approach.
The purpose of this study was to construct deep learning models for more efficient and reliable sex estimation. Two deep learning models, VGG16 and DenseNet-121, were used in this retrospective study. In total, 600 lateral cephalograms were analyzed. A saliency map was generated by gradient-weighted class activation mapping for each output. The two deep learning models achieved high values in each performance metric according to accuracy, sensitivity (recall), precision, F1 score, and areas under the receiver operating characteristic curve. Both models showed substantial differences in the positions indicated in saliency maps for male and female images. The positions in saliency maps also differed between VGG16 and DenseNet-121, regardless of sex. This analysis of our proposed system suggested that sex estimation from lateral cephalograms can be achieved with high accuracy using deep learning.
期刊介绍:
Dental Materials Journal is a peer review journal published by the Japanese Society for Dental Materials and Devises aiming to introduce the progress of the basic and applied sciences in dental materials and biomaterials. The dental materials-related clinical science and instrumental technologies are also within the scope of this journal. The materials dealt include synthetic polymers, ceramics, metals and tissue-derived biomaterials. Forefront dental materials and biomaterials used in developing filed, such as tissue engineering, bioengineering and artificial intelligence, are positively considered for the review as well. Recent acceptance rate of the submitted manuscript in the journal is around 30%.