A Deep Learning System to Predict Epithelial Dysplasia in Oral Leukoplakia.

Journal of dental research Pub Date : 2024-11-01 Epub Date: 2024-10-09 DOI:10.1177/00220345241272048
J Adeoye, A Chaurasia, A Akinshipo, I K Suleiman, L-W Zheng, A W I Lo, J J Pu, S Bello, F O Oginni, E T Agho, R O Braimah, Y X Su
{"title":"A Deep Learning System to Predict Epithelial Dysplasia in Oral Leukoplakia.","authors":"J Adeoye, A Chaurasia, A Akinshipo, I K Suleiman, L-W Zheng, A W I Lo, J J Pu, S Bello, F O Oginni, E T Agho, R O Braimah, Y X Su","doi":"10.1177/00220345241272048","DOIUrl":null,"url":null,"abstract":"<p><p>Oral leukoplakia (OL) has an inherent disposition to develop oral cancer. OL with epithelial dysplasia (OED) is significantly likely to undergo malignant transformation; however, routine OED assessment is invasive and challenging. This study investigated whether a deep learning (DL) model can predict dysplasia probability among patients with leukoplakia using oral photographs. In addition, we assessed the performance of the DL model in comparison with clinicians' ratings and in providing decision support on dysplasia assessment. Retrospective images of leukoplakia taken before biopsy/histopathology were obtained to construct the DL model (<i>n</i> = 2,073). OED status following histopathology was used as the gold standard for all images. We first developed, fine-tuned, and internally validated a DL architecture with an EfficientNet-B2 backbone that outputs the predicted probability of OED, OED status, and regions-of-interest heat maps. Then, we tested the performance of the DL model on a temporal cohort before geographical validation. We also assessed the model's performance at external validation with opinions provided by human raters on OED status. Performance evaluation included discrimination, calibration, and potential net benefit. The DL model achieved good Brier scores, areas under the curve, and balanced accuracies of 0.124 (0.079-0.169), 0.882 (0.838-0.926), and 81.8% (76.5-87.1) at testing and 0.146 (0.112-0.18), 0.828 (0.792-0.864), and 76.4% (72.3-80.5) at external validation, respectively. In addition, the model had a higher potential net benefit in selecting patients with OL for biopsy/histopathology during OED assessment than when biopsies were performed for all patients. External validation also showed that the DL model had better accuracy than 92.3% (24/26) of human raters in classifying the OED status of leukoplakia from oral images (balanced accuracy: 54.8%-79.7%). Overall, the photograph-based intelligent model can predict OED probability and status in leukoplakia with good calibration and discrimination, which shows potential for decision support to select patients for biopsy/histopathology, obviate unnecessary biopsy, and assist in patient self-monitoring.</p>","PeriodicalId":94075,"journal":{"name":"Journal of dental research","volume":" ","pages":"1218-1226"},"PeriodicalIF":0.0000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of dental research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1177/00220345241272048","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/10/9 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Oral leukoplakia (OL) has an inherent disposition to develop oral cancer. OL with epithelial dysplasia (OED) is significantly likely to undergo malignant transformation; however, routine OED assessment is invasive and challenging. This study investigated whether a deep learning (DL) model can predict dysplasia probability among patients with leukoplakia using oral photographs. In addition, we assessed the performance of the DL model in comparison with clinicians' ratings and in providing decision support on dysplasia assessment. Retrospective images of leukoplakia taken before biopsy/histopathology were obtained to construct the DL model (n = 2,073). OED status following histopathology was used as the gold standard for all images. We first developed, fine-tuned, and internally validated a DL architecture with an EfficientNet-B2 backbone that outputs the predicted probability of OED, OED status, and regions-of-interest heat maps. Then, we tested the performance of the DL model on a temporal cohort before geographical validation. We also assessed the model's performance at external validation with opinions provided by human raters on OED status. Performance evaluation included discrimination, calibration, and potential net benefit. The DL model achieved good Brier scores, areas under the curve, and balanced accuracies of 0.124 (0.079-0.169), 0.882 (0.838-0.926), and 81.8% (76.5-87.1) at testing and 0.146 (0.112-0.18), 0.828 (0.792-0.864), and 76.4% (72.3-80.5) at external validation, respectively. In addition, the model had a higher potential net benefit in selecting patients with OL for biopsy/histopathology during OED assessment than when biopsies were performed for all patients. External validation also showed that the DL model had better accuracy than 92.3% (24/26) of human raters in classifying the OED status of leukoplakia from oral images (balanced accuracy: 54.8%-79.7%). Overall, the photograph-based intelligent model can predict OED probability and status in leukoplakia with good calibration and discrimination, which shows potential for decision support to select patients for biopsy/histopathology, obviate unnecessary biopsy, and assist in patient self-monitoring.

预测口腔白斑病上皮发育不良的深度学习系统
口腔白斑病(OL)具有发展成口腔癌的固有倾向。上皮发育不良(OED)的口腔白斑发生恶性转化的可能性很大;然而,常规的 OED 评估具有侵入性和挑战性。本研究探讨了深度学习(DL)模型能否利用口腔照片预测白斑病患者的发育不良概率。此外,我们还评估了深度学习模型与临床医生评分的比较以及在提供发育不良评估决策支持方面的性能。我们获取了活检/组织病理学检查前拍摄的白斑病回顾性图像来构建 DL 模型(n = 2,073)。组织病理学检查后的 OED 状态被用作所有图像的金标准。我们首先开发、微调并在内部验证了带有 EfficientNet-B2 主干网的 DL 架构,该架构可输出 OED 预测概率、OED 状态和感兴趣区热图。然后,我们在地理验证之前,在一个时间群组上测试了 DL 模型的性能。我们还利用人类评分者提供的关于 OED 状态的意见评估了该模型的外部验证性能。性能评估包括判别、校准和潜在净效益。DL 模型的 Brier 分数、曲线下面积和平衡准确度都很高,测试结果分别为 0.124 (0.079-0.169)、0.882 (0.838-0.926) 和 81.8% (76.5-87.1),外部验证结果分别为 0.146 (0.112-0.18)、0.828 (0.792-0.864) 和 76.4% (72.3-80.5)。此外,与对所有患者进行活检相比,该模型在OED评估期间选择OL患者进行活检/组织病理学检查的潜在净收益更高。外部验证还表明,在根据口腔图像对白斑病的 OED 状态进行分类时,DL 模型的准确率高于 92.3%(24/26)的人类评分员(平衡准确率:54.8%-79.7%)。总之,基于照片的智能模型可以预测白斑病的 OED 概率和状态,并具有良好的校准和辨别能力,在选择患者进行活检/组织病理学检查、避免不必要的活检以及协助患者进行自我监测等方面具有决策支持的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信