AI Article Synopsis
- The study aims to improve early diagnosis of COVID-19 to reduce its high death toll by introducing a new classification model called PSSPNN.
- The model includes five key improvements, such as a unique pooling module and enhanced data augmentation techniques, which together enhance its accuracy.
- Results show the PSSPNN achieved a microaveraged F1 score of 95.79%, outperforming nine existing methods, thereby aiding radiologists in making faster and more accurate diagnoses.
Article Abstract
Aim: COVID-19 has caused large death tolls all over the world. Accurate diagnosis is of significant importance for early treatment.
Methods: In this study, we proposed a novel PSSPNN model for classification between COVID-19, secondary pulmonary tuberculosis, community-captured pneumonia, and healthy subjects. PSSPNN entails five improvements: we first proposed the n-conv stochastic pooling module. Second, a novel stochastic pooling neural network was proposed. Third, PatchShuffle was introduced as a regularization term. Fourth, an improved multiple-way data augmentation was used. Fifth, Grad-CAM was utilized to interpret our AI model.
Results: The 10 runs with random seed on the test set showed our algorithm achieved a microaveraged F1 score of 95.79%. Moreover, our method is better than nine state-of-the-art approaches.
Conclusion: This proposed PSSPNN will help assist radiologists to make diagnosis more quickly and accurately on COVID-19 cases.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7945676 | PMC |
| http://dx.doi.org/10.1155/2021/6633755 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!