Dr Hanya Mahmood (NIHR Academic Clinical Fellow in Oral Surgery), Academic Unit of Oral & Maxillofacial Surgery, School of Clinical Dentistry, University of Sheffield, 19 Claremont Crescent, S10 2TA, UK.
Muhammad Shaban (Research Student), Department of Computer Science, University of Warwick, Coventry, UK.
Oral Oncol. 2020 Nov;110:104885. doi: 10.1016/j.oraloncology.2020.104885. Epub 2020 Jul 13.
This systematic review analyses and describes the application and diagnostic accuracy of Artificial Intelligence (AI) methods used for detection and grading of potentially malignant (pre-cancerous) and cancerous head and neck lesions using whole slide images (WSI) of human tissue slides. Electronic databases MEDLINE via OVID, Scopus and Web of Science were searched between October 2009 - April 2020. Tailored search-strings were developed using database-specific terms. Studies were selected using a strict inclusion criterion following PRISMA Guidelines. Risk of bias assessment was conducted using a tailored QUADAS-2 tool. Out of 315 records, 11 fulfilled the inclusion criteria. AI-based methods were employed for analysis of specific histological features for oral epithelial dysplasia (n = 1), oral submucous fibrosis (n = 5), oral squamous cell carcinoma (n = 4) and oropharyngeal squamous cell carcinoma (n = 1). A combination of heuristics, supervised and unsupervised learning methods were employed, including more than 10 different classification and segmentation techniques. Most studies used uni-centric datasets (range 40-270 images) comprising small sub-images within WSI with accuracy between 79 and 100%. This review provides early evidence to support the potential application of supervised machine learning methods as a diagnostic aid for some oral potentially malignant and malignant lesions; however, there is a paucity of evidence using AI for diagnosis of other head and neck pathologies. Overall, the quality of evidence is low, with most studies showing a high risk of bias which is likely to have overestimated accuracy rates. This review highlights the need for development of state-of-the-art deep learning techniques in future head and neck research.
本系统评价分析和描述了使用人工智能（AI）方法在使用人组织切片的全切片图像（WSI）检测和分级潜在恶性（癌前）和恶性头颈部病变中的应用和诊断准确性。在 2009 年 10 月至 2020 年 4 月期间，检索了 MEDLINE 电子数据库（通过 OVID）、Scopus 和 Web of Science。使用数据库特定术语开发了定制的搜索字符串。研究使用 PRISMA 指南严格的纳入标准进行选择。使用量身定制的 QUADAS-2 工具进行偏倚风险评估。在 315 条记录中，有 11 条符合纳入标准。基于 AI 的方法用于分析口腔上皮异型增生（n=1）、口腔黏膜下纤维化（n=5）、口腔鳞状细胞癌（n=4）和口咽鳞状细胞癌（n=1）的特定组织学特征。采用了启发式、监督和无监督学习方法的组合，包括 10 多种不同的分类和分割技术。大多数研究使用单一中心数据集（范围 40-270 张图像），包括 WSI 中的小子图像，准确率在 79%至 100%之间。本综述提供了早期证据，支持监督机器学习方法作为某些口腔潜在恶性和恶性病变的诊断辅助手段的应用潜力；然而，使用 AI 诊断其他头颈部病变的证据很少。总的来说，证据质量较低，大多数研究显示出高度的偏倚风险，这可能高估了准确率。本综述强调了在未来的头颈部研究中开发最先进的深度学习技术的必要性。
