arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.08897cs.CV
收藏

TBNet:基于深度神经网络的肺结核诊断系统

TBNet:Pulmonary Tuberculosis Diagnosing System using Deep Neural Networks

Australian National University(澳大利亚国立大学)

Ram Srivatsav Ghorakavi

摘要:

结核病是一种流行于世界各地的致命传染病。由于缺乏适当的技术,无法及早发现这种疾病。此外,检测结核病的现有方法由于依赖于不必要的特征而没有达到值得称赞的标准,这使得这种技术对于可靠的医疗保健技术来说已经过时。在本文中,我提出了一个基于深度学习的系统,该系统根据胸部X光片中的重要特征以及原始胸部X光片来诊断结核病。采用我们的系统将通过克服执行耗时的基于结核病的测试方法(诊断微生物学)的需要来加速结核病诊断的过程。与以前的方法\cite{kant2018towards, melendez2016automated}相比,我们的工作利用了最先进的ResNet \cite{he2016deep},并使用传统的强大功能(如Haar \cite{viola2005detecting,viola2001rapid}和LBP \cite{ojala1994performance,ojala1996comparative})进行适当的数据增强。我注意到,这种程序将结核病的检测率提高到了非常令人满意的水平。我们的工作使用公开的肺部胸部X射线数据集来训练我们的网络\cite{jaeger2014two}。然而,公开的数据集非常小,不足以达到最佳准确性。为了克服这个问题,我设计了一个直观的功能为基础的数据增强管道。我们的方法将帮助深度神经网络\cite{lecun2015deep,he2016deep,krizhevsky2012imagenet}将其训练集中在结核病影响区域,使其与使用镜像和旋转等程序的其他传统方法相比更加强大和准确。通过使用我们简单而强大的技术,我观察到性能准确性提高了10%。

英文摘要:

Tuberculosis is a deadly infectious disease prevalent around the world. Due to the lack of proper technology in place, the early detection of this disease is unattainable. Also, the available methods to detect Tuberculosis is not up-to a commendable standards due to their dependency on unnecessary features, this make such technology obsolete for a reliable health-care technology. In this paper, I propose a deep-learning based system which diagnoses tuberculosis based on the important features in Chest X-rays along with original chest X-rays. Employing our system will accelerate the process of tuberculosis diagnosis by overcoming the need to perform the time-consuming sputum-based testing method (Diagnostic Microbiology). In contrast to the previous methods \cite{kant2018towards, melendez2016automated}, our work utilizes the state-of-the-art ResNet \cite{he2016deep} with proper data augmentation using traditional robust features like Haar \cite{viola2005detecting,viola2001rapid} and LBP \cite{ojala1994performance,ojala1996comparative}. I observed that such a procedure enhances the rate of tuberculosis detection to a highly satisfactory level. Our work uses the publicly available pulmonary chest X-ray dataset to train our network \cite{jaeger2014two}. Nevertheless, the publicly available dataset is very small and is inadequate to achieve the best accuracy. To overcome this issue I have devised an intuitive feature based data augmentation pipeline. Our approach shall help the deep neural network \cite{lecun2015deep,he2016deep,krizhevsky2012imagenet} to focus its training on tuberculosis affected regions making it more robust and accurate, when compared to other conventional methods that use procedures like mirroring and rotation. By using our simple yet powerful techniques, I observed a 10\% boost in performance accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑