Mobile-based oral cancer classification for point-of-care screening.
Mobile-based oral cancer classification for point-of-care screening.
复制标题
基于移动设备的口腔癌分级用于即时筛查。
DOI：
10.1117/1.jbo.26.6.065003
复制
发表时间：
2021-06
影响因子：
3.5
通讯作者：
Liang R
中科院分区：
文献类型：
--
作者：
Song B;Sunny S;Li S;Gurushanth K;Mendonca P;Mukhia N;Patrick S;Gurudath S;Raghavan S;Imchen T;Leivon S;Kolur T;Shetty V;Bushan V;Ramesh R;Lima N;Pillai V;Wilder-Smith P;Sigamani A;Suresh A;Kuriakose M;Birur P;Liang R
意义：口腔癌是全球最常见的癌症之一，尤其是在低收入和中等收入国家。早期发现是降低死亡率的最有效方法。基于深度学习的癌症图像分类模型通常需要托管在计算服务器上。然而，在资源匮乏的环境中，互联网连接对于筛查来说并不可靠。目的：开发基于移动设备的双模式图像分类方法和定制的 Android 应用程序，用于口腔癌即时检测。方法：我们研究中使用的数据集是通过我们定制的双模态移动口腔筛查设备从 5025 名患者中获取的。我们训练了一个具有焦点损失的高效网络 MobileNet，并将模型转换为 TensorFlow Lite 格式。最终确定的精简版格式模型非常适合智能手机平台操作。我们开发了一款易于使用的 Android 智能手机应用程序，该应用程序实现了基于移动设备的双模态图像分类方法，以区分口腔潜在恶性和恶性图像与正常/良性图像。结果：我们研究了经济高效的智能手机计算平台上的准确性和运行速度。使用 Moto G5 Android 智能手机处理一对图像需要花费时间。我们在独立数据集上测试了所提出的方法，并使用基于口腔专家对图像的审查的临床印象的黄金标准，在区分正常/良性病变与临床可疑病变方面达到了 81% 的准确度。结论：我们的研究证明了在资源匮乏的环境中基于移动设备的口腔癌筛查方法的有效性。
Significance: Oral cancer is among the most common cancers globally, especially in low- and middle-income countries. Early detection is the most effective way to reduce the mortality rate. Deep learning-based cancer image classification models usually need to be hosted on a computing server. However, internet connection is unreliable for screening in low-resource settings. Aim: To develop a mobile-based dual-mode image classification method and customized Android application for point-of-care oral cancer detection. Approach: The dataset used in our study was captured among 5025 patients with our customized dual-modality mobile oral screening devices. We trained an efficient network MobileNet with focal loss and converted the model into TensorFlow Lite format. The finalized lite format model is and ideal for smartphone platform operation. We have developed an Android smartphone application in an easy-to-use format that implements the mobile-based dual-modality image classification approach to distinguish oral potentially malignant and malignant images from normal/benign images. Results: We investigated the accuracy and running speed on a cost-effective smartphone computing platform. It takes to process one image pair with the Moto G5 Android smartphone. We tested the proposed method on a standalone dataset and achieved 81% accuracy for distinguishing normal/benign lesions from clinically suspicious lesions, using a gold standard of clinical impression based on the review of images by oral specialists. Conclusions: Our study demonstrates the effectiveness of a mobile-based approach for oral cancer screening in low-resource settings.