COVID19XrayNet: A Two-Step Transfer Learning Model for the COVID-19 Detecting Problem Based on a Limited Number of Chest
- PDF / 1,099,696 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 116 Downloads / 170 Views
SHORT COMMUNICATION
COVID19XrayNet: A Two‑Step Transfer Learning Model for the COVID‑19 Detecting Problem Based on a Limited Number of Chest X‑Ray Images Ruochi Zhang1 · Zhehao Guo2 · Yue Sun2 · Qi Lu2 · Zijian Xu2 · Zhaomin Yao1 · Meiyu Duan1 · Shuai Liu1 · Yanjiao Ren3 · Lan Huang1 · Fengfeng Zhou1 Received: 24 April 2020 / Revised: 2 September 2020 / Accepted: 5 September 2020 © International Association of Scientists in the Interdisciplinary Areas 2020
Abstract The novel coronavirus severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a major pandemic outbreak recently. Various diagnostic technologies have been under active development. The novel coronavirus disease (COVID-19) may induce pulmonary failures, and chest X-ray imaging becomes one of the major confirmed diagnostic technologies. The very limited number of publicly available samples has rendered the training of the deep neural networks unstable and inaccurate. This study proposed a two-step transfer learning pipeline and a deep residual network framework COVID19XrayNet for the COVID-19 detection problem based on chest X-ray images. COVID19XrayNet firstly tunes the transferred model on a large dataset of chest X-ray images, which is further tuned using a small dataset of annotated chest X-ray images. The final model achieved 0.9108 accuracy. The experimental data also suggested that the model may be improved with more training samples being released. Graphic abstract COVID19XrayNet, a two-step transfer learning framework designed for biomedical images. Feature Smoothing Layer (FSL)
Channel Invariant 1x1 Conv
Batch Norm
Feature Extrac on Layer (FEL)
Channel Expand 1x1 Conv
ReLU
Batch Norm
ReLU
Adap ve Average Pooling
Pretrained ResNet34
w 112x112x64
2
[56x56x64]x3 [28x28x128]x4 [14x14x256]x5
[7x7x512]x7
224x224x3
512
FSL 56x56x64 224x224x3
FSL [28x28x128]x4
FEL 7x7x512
3 512
Keywords Two-step transfer learning · COVID19XrayNet · ResNet34 · Feature smoothing layer (FSL) · Feature extraction layer (FEL) Extended author information available on the last page of the article
13
Vol.:(0123456789)
1 Introduction The recent outbreak of the novel coronavirus disease (COVID-19) started in Wuhan at the end of the last year, and now COVID-19 has been spreading across the world [1]. The disease was caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which was a single-stranded RNA virus. SARS-CoV-2 may have been transmitted from animals such as bats to humans, and the respiratory droplet nuclei were believed to facilitate the inter-human transmissions [1, 2]. Various clinical symptoms were observed in COVID-19 patients, including mild cough and acute respiratory failure, etc. COVID-19 patients with mild symptoms were estimated to have a low mortality rate, but the exact number is difficult to summarize because they were usually not tested [3]. However, those with respiratory failures had to take mechanical ventilation treatment in hospital and their mortality rate could reach as high as 81% [4]
Data Loading...
