SBIR Phase I: Deep learning diagnosis and platform for at-home ear evaluations in children

这项小企业创新研究（SBIR）第一阶段项目的更广泛影响/商业潜力将改善儿童健康。儿童耳部感染通常在夜间出现，儿童必须等到第二天进行评估和治疗。这个项目的目的是创建一个深度学习的家庭耳部感染诊断系统。这项小企业创新研究（SBIR）第一阶段将推进儿科耳部成像系统的翻译。目标包括：生成一个训练数据集，其中包含来自儿科临床环境的标记为正确诊断的图像；创建一种深度学习算法，从成熟的卷积神经网络中进行迁移学习，用于预测；创建一个原型软件界面，以标记呈现给系统的新图像；并设计了一个用于家庭图像采集的窥镜。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I Project will improve pediatric health. Pediatric ear infections often manifest at night and the child must wait until the next day for an evaluation and treatment. The intention of this project is to create a deep-learning at-home ear infection diagnostic system. This Small Business Innovation Research (SBIR) Phase I will advance translation of a pediatric ear-imaging system. The objectives include: generating a training data set with images labeled with correct diagnoses from a pediatric clinical setting; creating a deep learning algorithm with transfer learning from well-established convolutional neural networks for prediction; creating a prototype software interface to label a new image presented to the system; and designing a speculum for at-home image acquisition.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.