SCH: INT A.Soclotechnilcal Systems Systems Approach for Improving Tuberculosis Diagnostics Using Mobile Health Technologies

 描述(申请人提供)：减少结核病(TB)负担的努力受到卫生领域持续存在的社会不平等、当地医疗专业人员数量有限以及资源匮乏社区薄弱的医疗基础设施的挑战。减少结核病诊断延迟对于减少疾病传播和最大限度地减少高负担地区结核病流行的繁殖率至关重要。这项提议的主要目标是通过开发新的图像处理和机器学习技术来分析胸部X光图像，从而加快结核病诊断进程，从而减少患者被诊断为结核病的等待时间。这项研究将在Carabayllo区进行，Carabayllo区是珀鲁省首府利马的一个人口密集、高负担的结核病地区。开发拟议的以用户为中心的基于移动设备的计算系统的努力与国家生物医学成像和生物工程研究所(NIBIB)的使命及其战略目标2和4相一致--拟议的社会技术干预旨在开发生物医学成像技术(即无线和图像传感/分析)，以实现用于结核病筛查和诊断的基于护理点的移动设备计算系统。预期成果包括a)用于结核病筛查的大规模、真实、注释良好和公开可用的胸部X光图像数据库，b)开发用于X光图像捕获和预处理的新图像分析技术，以及c)新的基于学习的特征提取和分类算法。在研究的所有阶段都有社区、大学、医院和卫生保健机构参与，这一跨学科努力满足了学术界和社区利益攸关方之间加强伙伴关系的需要，以及在双向(南北、南北)卫生方面生物医学和技术解决方案方面的能力建设的潜力。它的科学贡献在于NIBIB的三个科学项目领域的交叉，包括图像处理、远程健康和生物医学信息学。

 DESCRIPTION (provided by applicant): Efforts to reduce the burden of Tuberculosis (TB) are challenged by the persistent social inequalities in health, the limited number of local healthcare professionals, and the weak healthcare infrastructure found in resource-poor communities. Reducing the TB diagnosis delay is critical in mitigating disease transmission and minimizing the reproductive rate of the TB epidemic in high-burden areas. The main objective of this proposal is to expedite the TB diagnosis process by developing novel image processing and machine learning techniques to analyze chest X-ray images thus reducing patient wait times for being diagnosed with TB. The study will be conducted in the district of Carabayllo, a densely occupied, high-burden TB area in Lima, the capital of Perú. Efforts to develop the proposed user-centered, mobile device-based computing system are aligned with the mission of the National Institute of Biomedical Imaging and Bioengineering (NIBIB) and its strategic goals 2 and 4 in particular-the proposed socio-technical intervention aims at developing biomedical imaging techniques (i.e. wireless and image sensing/analyzing) to enable a point-of-care mobile device-based computing system for TB screening and diagnostic. Anticipated outcomes include a) a large-scale, real-world, well-annotated, and public available chest X-ray image database for TB screening, b) development of new image analysis techniques for X-ray image capturing and pre- processing, and c) novel learning-based feature extraction and classification algorithms. This interdisciplinary effort, involving community, university, hospitals and health care establishments in all stages of the research, responds to the need for increased partnerships between academia and community stakeholders, and the potential for building capacity in biomedical and technology solutions for health in both directions (North-South, South-North). Its scientific contribution lies in the intersection of three NIBIB scientific program areas including image processing, telehealth, and biomedical informatics.