利用基于人工智能的图像分析检测口腔癌和口腔潜在恶性疾病。

IF 4.6 Q2 MATERIALS SCIENCE, BIOMATERIALS ACS Applied Bio Materials Pub Date : 2024-06-11 DOI:10.1002/hed.27843

Atsumu Kouketsu DDS, PhD, Chiaki Doi PhD, Hiroaki Tanaka BS, Takashi Araki BS, Rina Nakayama BS, Tsuguyoshi Toyooka PhD, Satoshi Hiyama PhD, Masahiro Iikubo DDS, PhD, Ken Osaka MD, PhD, Keiichi Sasaki DDS, PhD, Hirokazu Nagai DDS, PhD, Tsuyoshi Sugiura DDS, PhD, Kensuke Yamauchi DDS, PhD, Kanako Kuroda DDS, PhD, Yuta Yanagisawa DDS, PhD, Hitoshi Miyashita DDS, PhD, Tomonari Kajita DDS, PhD, Ryosuke Iwama DDS, PhD, Tsuyoshi Kurobane DDS, PhD, Tetsu Takahashi DDS, PhD

{"title":"利用基于人工智能的图像分析检测口腔癌和口腔潜在恶性疾病。","authors":"Atsumu Kouketsu DDS, PhD, Chiaki Doi PhD, Hiroaki Tanaka BS, Takashi Araki BS, Rina Nakayama BS, Tsuguyoshi Toyooka PhD, Satoshi Hiyama PhD, Masahiro Iikubo DDS, PhD, Ken Osaka MD, PhD, Keiichi Sasaki DDS, PhD, Hirokazu Nagai DDS, PhD, Tsuyoshi Sugiura DDS, PhD, Kensuke Yamauchi DDS, PhD, Kanako Kuroda DDS, PhD, Yuta Yanagisawa DDS, PhD, Hitoshi Miyashita DDS, PhD, Tomonari Kajita DDS, PhD, Ryosuke Iwama DDS, PhD, Tsuyoshi Kurobane DDS, PhD, Tetsu Takahashi DDS, PhD","doi":"10.1002/hed.27843","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>We aimed to construct an artificial intelligence-based model for detecting oral cancer and dysplastic leukoplakia using oral cavity images captured with a single-lens reflex camera.</p>\n </section>\n \n <section>\n \n <h3> Subjects and methods</h3>\n \n <p>We used 1043 images of lesions from 424 patients with oral squamous cell carcinoma (OSCC), leukoplakia, and other oral mucosal diseases. An object detection model was constructed using a Single Shot Multibox Detector to detect oral diseases and their locations using images. The model was trained using 523 images of oral cancer, and its performance was evaluated using images of oral cancer (<i>n</i> = 66), leukoplakia (<i>n</i> = 49), and other oral diseases (<i>n</i> = 405).</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>For the detection of only OSCC versus OSCC and leukoplakia, the model demonstrated a sensitivity of 93.9% versus 83.7%, a negative predictive value of 98.8% versus 94.5%, and a specificity of 81.2% versus 81.2%.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>Our proposed model is a potential diagnostic tool for oral diseases.</p>\n </section>\n </div>","PeriodicalId":2,"journal":{"name":"ACS Applied Bio Materials","volume":null,"pages":null},"PeriodicalIF":4.6000,"publicationDate":"2024-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/hed.27843","citationCount":"0","resultStr":"{\"title\":\"Detection of oral cancer and oral potentially malignant disorders using artificial intelligence-based image analysis\",\"authors\":\"Atsumu Kouketsu DDS, PhD, Chiaki Doi PhD, Hiroaki Tanaka BS, Takashi Araki BS, Rina Nakayama BS, Tsuguyoshi Toyooka PhD, Satoshi Hiyama PhD, Masahiro Iikubo DDS, PhD, Ken Osaka MD, PhD, Keiichi Sasaki DDS, PhD, Hirokazu Nagai DDS, PhD, Tsuyoshi Sugiura DDS, PhD, Kensuke Yamauchi DDS, PhD, Kanako Kuroda DDS, PhD, Yuta Yanagisawa DDS, PhD, Hitoshi Miyashita DDS, PhD, Tomonari Kajita DDS, PhD, Ryosuke Iwama DDS, PhD, Tsuyoshi Kurobane DDS, PhD, Tetsu Takahashi DDS, PhD\",\"doi\":\"10.1002/hed.27843\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n \\n <section>\\n \\n <h3> Background</h3>\\n \\n <p>We aimed to construct an artificial intelligence-based model for detecting oral cancer and dysplastic leukoplakia using oral cavity images captured with a single-lens reflex camera.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Subjects and methods</h3>\\n \\n <p>We used 1043 images of lesions from 424 patients with oral squamous cell carcinoma (OSCC), leukoplakia, and other oral mucosal diseases. An object detection model was constructed using a Single Shot Multibox Detector to detect oral diseases and their locations using images. The model was trained using 523 images of oral cancer, and its performance was evaluated using images of oral cancer (<i>n</i> = 66), leukoplakia (<i>n</i> = 49), and other oral diseases (<i>n</i> = 405).</p>\\n </section>\\n \\n <section>\\n \\n <h3> Results</h3>\\n \\n <p>For the detection of only OSCC versus OSCC and leukoplakia, the model demonstrated a sensitivity of 93.9% versus 83.7%, a negative predictive value of 98.8% versus 94.5%, and a specificity of 81.2% versus 81.2%.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Conclusions</h3>\\n \\n <p>Our proposed model is a potential diagnostic tool for oral diseases.</p>\\n </section>\\n </div>\",\"PeriodicalId\":2,\"journal\":{\"name\":\"ACS Applied Bio Materials\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2024-06-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/hed.27843\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACS Applied Bio Materials\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/hed.27843\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"MATERIALS SCIENCE, BIOMATERIALS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Applied Bio Materials","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/hed.27843","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, BIOMATERIALS","Score":null,"Total":0}

引用次数: 0

摘要

背景：我们的目的是利用单镜头反光相机拍摄的口腔图像构建一个基于人工智能的模型，用于检测口腔癌和发育不良的白斑病：我们使用了来自424名口腔鳞状细胞癌（OSCC）、白斑病和其他口腔黏膜疾病患者的1043张病变图像。我们使用单镜头多箱检测器构建了一个物体检测模型，以利用图像检测口腔疾病及其位置。使用 523 张口腔癌图像对模型进行了训练，并使用口腔癌（n = 66）、白斑（n = 49）和其他口腔疾病（n = 405）的图像对模型的性能进行了评估：结果：对于仅检测 OSCC 与 OSCC 和白斑病，该模型的灵敏度为 93.9% 对 83.7%，阴性预测值为 98.8% 对 94.5%，特异性为 81.2% 对 81.2%：我们提出的模型是一种潜在的口腔疾病诊断工具。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

摘要图片

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Detection of oral cancer and oral potentially malignant disorders using artificial intelligence-based image analysis

Background

We aimed to construct an artificial intelligence-based model for detecting oral cancer and dysplastic leukoplakia using oral cavity images captured with a single-lens reflex camera.

Subjects and methods

We used 1043 images of lesions from 424 patients with oral squamous cell carcinoma (OSCC), leukoplakia, and other oral mucosal diseases. An object detection model was constructed using a Single Shot Multibox Detector to detect oral diseases and their locations using images. The model was trained using 523 images of oral cancer, and its performance was evaluated using images of oral cancer (n = 66), leukoplakia (n = 49), and other oral diseases (n = 405).

Results

For the detection of only OSCC versus OSCC and leukoplakia, the model demonstrated a sensitivity of 93.9% versus 83.7%, a negative predictive value of 98.8% versus 94.5%, and a specificity of 81.2% versus 81.2%.