Malarial Retinopathy Screening System for Improved Diagnosis of Cerebral Malaria

描述（由申请人提供）：VisionQuest Biomedical及其合作者组建了一个跨学科科学家团队，在自动视网膜图像分析、临床眼科学以及疟疾视网膜病变（MR）和脑型疟疾诊断（CM）方面具有丰富的经验。该团队将开发和测试一种自动化MR筛查软件系统，该系统与VisionQuest开发的低成本便携式视网膜摄像机iRxCam集成，以帮助和提高CM诊断的准确性。CM是与疟疾相关的最致命的临床综合征。它每年影响2亿多人，并在全世界造成约80万人死亡，其中包括70万非洲儿童死亡。由于CM的高发病率，它经常被误诊为具有类似症状的其他病理，导致不正确的治疗。一旦临床怀疑，一个准确的手段来确认CM的存在或调查非疟疾疾病是至关重要的，以改善结果。由于MR是大于90%的敏感性和特异性的CM的存在，一旦临床诊断，视网膜筛查MR代表了一种有效的手段，以帮助和提高CM诊断的特异性。我们提出的系统不会取代目前的CM诊断标准，而是将其添加到CM诊断中，以提高CM诊断的准确性，从而减少假阳性结果的数量。我们提出了一个完全自动化的磁共振筛查系统，消除了对临床专业知识和设备的需要，以及其低成本和便携性，使该系统更容易获得和负担得起的受影响的人口在非洲。该项目第一阶段有三个具体目标要实现。首先，我们将开发新的方法，并适应以前开发的方法，用于自动检测MR的视网膜体征，并使用回顾性图像数据对其进行测试。第二个目标是将自动化软件系统与VisionQuest开发的低成本便携式视网膜相机连接起来。第三，我们将测试我们的软件系统的回顾性图像数据从糖尿病视网膜病变患者用我们的相机成像，以证明软件系统的适用性从我们的相机获得的图像。

DESCRIPTION (provided by applicant): VisionQuest Biomedical and its collaborators have assembled a team of inter-disciplinary scientists with considerable experience in automated retinal image analysis, clinical ophthalmology with specialized research in malarial retinopathy (MR), and cerebral malaria diagnosis (CM). This team will develop and test an automated MR screening software system integrated with a low-cost and portable retinal camera, iRxCam, developed by VisionQuest; to assist and improve the accuracy of CM diagnosis. CM is the most lethal clinical syndrome associated with malarial disease. It affects more than 200 million people annually and claims about 800,000 deaths worldwide which include 700,000 mortalities from African children. As a consequence of high incidence of CM, it is often misdiagnosed for other pathologies with similar symptoms, leading to an incorrect treatment. Once clinically suspected, an accurate means to confirm the presence of CM or to investigate for a non-malarial illness is critically needed to improve outcomes. Since MR is greater than 90% sensitive and specific to the presence of CM once clinically diagnosed, retinal screening for MR represents an effective means to assist and improve the specificity of CM diagnosis. Our proposed system will not replace the current CM diagnostic standard, but instead will be added to it to increase the accuracy of CM diagnosis leading to a smaller number of false positive outcomes. We propose a fully automated MR screening system that eliminates the need of clinical expertise and equipment, as well as its low-cost and portability make this system more accessible and affordable to affected population in Africa. There are three specific aims to be achieved in phase I of this project. First, we will develop new methods and adapt previously developed methods for automated detection of retinal signs of MR and test them using a retrospective image data. The second aim will focus on interfacing the automated software system with the low-cost and portable retinal camera developed by VisionQuest. Third, we will test our software system on a retrospective image data obtained from diabetic retinopathy patients imaged with our camera to demonstrate the applicability of the software system on images obtained from our camera.