Division of Engineering in Medicine, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts 02139, United States.
Department of Biotechnology, Institute of Health Sciences, Federal University of Bahia, Salvador, BA 40110-100, Brazil.
ACS Nano. 2021 Jan 26;15(1):665-673. doi: 10.1021/acsnano.0c06807. Epub 2020 Nov 23.
Deep-learning (DL)-based image processing has potential to revolutionize the use of smartphones in mobile health (mHealth) diagnostics of infectious diseases. However, the high variability in cellphone image data acquisition and the common need for large amounts of specialist-annotated images for traditional DL model training may preclude generalizability of smartphone-based diagnostics. Here, we employed adversarial neural networks with conditioning to develop an easily reconfigurable virus diagnostic platform that leverages a dataset of smartphone-taken microfluidic chip photos to rapidly generate image classifiers for different target pathogens on-demand. Adversarial learning was also used to augment this real image dataset by generating 16,000 realistic synthetic microchip images, through style generative adversarial networks (StyleGAN). We used this platform, termed martphone-based athogen tection esource ultiplier using dversarial etworks (SPyDERMAN), to accurately detect different intact viruses in clinical samples and to detect viral nucleic acids through integration with CRISPR diagnostics. We evaluated the performance of the system in detecting five different virus targets using 179 patient samples. The generalizability of the system was confirmed by rapid reconfiguration to detect SARS-CoV-2 antigens in nasal swab samples ( = 62) with 100% accuracy. Overall, the SPyDERMAN system may contribute to epidemic preparedness strategies by providing a platform for smartphone-based diagnostics that can be adapted to a given emerging viral agent within days of work.
基于深度学习的图像处理有可能彻底改变智能手机在移动医疗（mHealth）传染病诊断中的应用。然而，手机图像数据采集的高度可变性以及传统深度学习模型训练通常需要大量专业注释图像，这可能会限制基于智能手机的诊断的通用性。在这里，我们采用具有条件的对抗神经网络来开发一个易于重新配置的病毒诊断平台，该平台利用智能手机拍摄的微流控芯片照片数据集，按需快速生成针对不同目标病原体的图像分类器。对抗学习还通过使用样式生成对抗网络（StyleGAN）生成 16000 张逼真的合成微芯片图像来扩充这个真实图像数据集。我们将这个平台称为基于智能手机的病原体检测资源倍增器（SPyDERMAN），用于准确检测临床样本中的不同完整病毒，并通过与 CRISPR 诊断相结合来检测病毒核酸。我们使用 179 个患者样本评估了该系统检测五个不同病毒靶标的性能。通过快速重新配置，该系统在检测 62 份鼻拭子样本中的 SARS-CoV-2 抗原时达到了 100%的准确率，证明了该系统的通用性。总的来说，SPyDERMAN 系统通过提供一种可在几天内适应特定新兴病毒的基于智能手机的诊断平台，可能有助于疫情防范策略。
