Exploring uncertainty measures in convolutional neural network for semantic segmentation of oral cancer images.
Exploring uncertainty measures in convolutional neural network for semantic segmentation of oral cancer images.
复制标题
DOI：
10.1117/1.jbo.27.11.115001
复制
发表时间：
2022-11
影响因子：
3.5
通讯作者：
Liang, Rongguang
中科院分区：
文献类型：
--
作者：
Song, Bofan;Li, Shaobai;Sunny, Sumsum;Gurushanth, Keerthi;Mendonca, Pramila;Mukhia, Nirza;Patrick, Sanjana;Peterson, Tyler;Gurudath, Shubha;Raghavan, Subhashini;Tsusennaro, Imchen;Leivon, Shirley T.;Kolur, Trupti;Shetty, Vivek;Bushan, Vidya;Ramesh, Rohan;Pillai, Vijay;Wilder-Smith, Petra;Suresh, Amritha;Kuriakose, Moni Abraham;Birur, Praveen;Liang, Rongguang
关键词：
口腔癌是最常见的癌症之一，特别是在印度等中低收入国家。口腔癌图像的自动分割可以改善口腔癌的诊断流程，是口腔癌图像分析中的一项重要任务。尽管深度学习网络在医学分割方面取得了显著的成功，但它们很少为其输出提供不确定性量化。我们的目标是在深度学习方法中估计口腔癌图像语义分割的不确定性，并提高预测的准确性和可靠性。这项工作引入了基于UNet的贝叶斯深度学习（BDL）模型来分割口腔中潜在的恶性和恶性病变区域。该模型可以量化预测中的不确定性。我们还开发了一个有效的模型，提高了推理速度，比原来的UNet小了近六倍，快了两倍（推理速度）。本研究中的数据集是使用我们定制的筛查平台收集的，并由口腔肿瘤学专家进行注释。该方法实现了良好的分割性能以及良好的不确定性估计性能。在实验中，我们观察到通过去除不确定的像素，像素精度和平均交集优于并集。这一结果反映了该模型在可能需要更多关注和进一步检查的不确定领域提供了不太准确的预测。实验还表明，在一些性能上的妥协，有效的模型减少了计算时间和模型的大小，这扩大了在资源有限的设置中使用的便携式设备上实现的潜力。我们的研究表明，基于UNet的BDL模型不仅可以执行潜在的恶性和恶性口腔病变分割，而且还可以提供信息的像素级的不确定性估计。利用这些额外的不确定性信息，可以提高模型预测的准确性和可靠性。
Oral cancer is one of the most prevalent cancers, especially in middle- and low-income countries such as India. Automatic segmentation of oral cancer images can improve the diagnostic workflow, which is a significant task in oral cancer image analysis. Despite the remarkable success of deep-learning networks in medical segmentation, they rarely provide uncertainty quantification for their output. We aim to estimate uncertainty in a deep-learning approach to semantic segmentation of oral cancer images and to improve the accuracy and reliability of predictions. This work introduced a UNet-based Bayesian deep-learning (BDL) model to segment potentially malignant and malignant lesion areas in the oral cavity. The model can quantify uncertainty in predictions. We also developed an efficient model that increased the inference speed, which is almost six times smaller and two times faster (inference speed) than the original UNet. The dataset in this study was collected using our customized screening platform and was annotated by oral oncology specialists. The proposed approach achieved good segmentation performance as well as good uncertainty estimation performance. In the experiments, we observed an improvement in pixel accuracy and mean intersection over union by removing uncertain pixels. This result reflects that the model provided less accurate predictions in uncertain areas that may need more attention and further inspection. The experiments also showed that with some performance compromises, the efficient model reduced computation time and model size, which expands the potential for implementation on portable devices used in resource-limited settings. Our study demonstrates the UNet-based BDL model not only can perform potentially malignant and malignant oral lesion segmentation, but also can provide informative pixel-level uncertainty estimation. With this extra uncertainty information, the accuracy and reliability of the model’s prediction can be improved.