COVID-Efficientnet: COVID-19 Detection with Chest X-ray Images and Deep Learning by Weichen Huang
COVID-19 (Coronavirus Disease 2019) is an infectious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The first cases were seen in Wuhan, China, in late December 2019 before spreading globally and becoming a pandemic. The virus has caused a devastating effect on both daily lives, public health, and the global economy. It is critical to detect the positive cases as early as possible so as to prevent the further spread of this epidemic and to quickly treat affected patients. Definitive diagnosis of COVID-19 requires a positive RT-PCR test. Current best practice advises that chest radiological imaging such as computed tomography (CT) and X-ray have vital roles in early diagnosis and treatment of this disease. It is stated that CT is a sensitive method to detect COVID-19 pneumonia and can be considered as a screening tool with RT-PRC. In this article, we present a novel method that combines human lung x-ray images and deep learning models to reliably and quickly detect COVID-19 in real time.
54-year-old patient with dyspnoea, cough and pyrexia (http://www.imj.ie/wp-content/uploads/2020/04/Imaging-of-Covid-19-an-Irish-Perspective-1.pdf) Efficientnet In ICML 2019, Google proposed EfficientNet, a novel model scaling method that uses “a simple yet highly effective compound coefficient to scale up CNNs in a more structured manner”. Unlike conventional approaches that arbitrarily scale network dimensions, such as width, depth and resolution, EfficientNet uniformly scales each dimension with a fixed set of scaling coefficients.
Efficientnet The EfficientNets models surpass state-of-the-art accuracy with up to 10x better efficiency (smaller and faster). Architecture Inspired by COVID-Next and the efficiency and mobility of Efficientnet, we designed a COVID-19 x-ray image classification model (Covid-EfficientNet) based on EfficientNet using Pytorch. COVID-Efficientnet features an architecture that builds upon Efficientnet b7 architecture, an AutoML architecture for optimizing both accuracy and mobility. Dataset The dataset we compiled was based on two existing datasets: -the COVID-19 x-ray dataset -the RSNA (Pneumonia) dataset We used the RSNA dataset to provide images of normal lungs at a large scale. Performance We achieved state of the art validation (05/05/20) performance for the accuracy metric for our dataset, outperforming COVID-Next and COVID-Net at 96% accuracy, a 2% increase from previous SOTA. Code Our code is available here: https://github.com/weichen-huang/COVID-Efficientnet-Pytorch