Automated Detection and Classification of Oral Lesions Using Deep Learning for Early Detection of Oral Cancer
Automated Detection and Classification of Oral Lesions Using Deep Learning for Early Detection of Oral Cancer
复制标题
DOI：
10.1109/access.2020.3010180
复制
发表时间：
2020-01-01
期刊：
影响因子：
3.9
通讯作者：
Barman, Sarah Ann
中科院分区：
文献类型：
--
作者：
Welikala, Roshan Alex;Remagnino, Paolo;Barman, Sarah Ann
口腔癌是一个重大的全球健康问题，2018年造成177384人死亡，在低收入和中等收入国家最为普遍。在口腔中实现潜在恶性和恶性病变的自动化识别可能会导致低成本和早期诊断疾病。建立一个大型的口腔病变注释库是关键。作为MeMoSA(R)（任何地方的移动口腔筛查）项目的一部分，目前正在从世界各地的临床专家那里收集图像，他们已经提供了一个注释工具来生成丰富的标签。本文提供了一种新的策略来组合来自多个临床医生的边界框注释。此外，深度神经网络被用于构建自动化系统，其中复杂的模式被导出来处理这一艰巨的任务。利用本研究收集的初始数据，评估了两种基于深度学习的计算机视觉方法用于口腔病变的自动检测和分类，以早期发现口腔癌，这两种方法是使用ResNet-101进行图像分类和使用Faster R-CNN进行物体检测。图像分类对含有病变的图像的识别达到F-1分87.07%，对需要转诊的图像的识别达到78.30%。对于需要转诊的病变，物体检测的F-1评分为41.18%。根据转诊决定的类型进行分类，报告了进一步的表现。我们的初步结果表明，深度学习有潜力解决这一具有挑战性的任务。
Oral cancer is a major global health issue accounting for 177,384 deaths in 2018 and it is most prevalent in low- and middle-income countries. Enabling automation in the identification of potentially malignant and malignant lesions in the oral cavity would potentially lead to low-cost and early diagnosis of the disease. Building a large library of well-annotated oral lesions is key. As part of the MeMoSA(R)(Mobile Mouth Screening Anywhere) project, images are currently in the process of being gathered from clinical experts from across the world, who have been provided with an annotation tool to produce rich labels. A novel strategy to combine bounding box annotations from multiple clinicians is provided in this paper. Further to this, deep neural networks were used to build automated systems, in which complex patterns were derived for tackling this difficult task. Using the initial data gathered in this study, two deep learning based computer vision approaches were assessed for the automated detection and classification of oral lesions for the early detection of oral cancer, these were image classification with ResNet-101 and object detection with the Faster R-CNN. Image classification achieved an F-1 score of 87.07% for identification of images that contained lesions and 78.30% for the identification of images that required referral. Object detection achieved an F-1 score of 41.18% for the detection of lesions that required referral. Further performances are reported with respect to classifying according to the type of referral decision. Our initial results demonstrate deep learning has the potential to tackle this challenging task.