Chest CT image analysis using deep learning models: a case study on COVID-19

• Grant number: 21/02382-4
• Support Opportunities: Scholarships in Brazil - Master
• Start date: April 01, 2021
• End date: August 31, 2022
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Agreement: Microsoft Research
• Principal Investigator: Nina Sumiko Tomita Hirata
• Grantee: Liang Shen
• Host Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Company: Universidade de São Paulo (USP). Instituto de Matemática e Estatística (IME)
• Associated research grant: 17/25835-9 - Understanding images and deep learning models, AP.PITE

Abstract

Lung computed tomography (CT) images are being used to help diagnosis and monitoring of COVID-19 disease. In order to facilitate this task, automated methods for detecting COVID-19 lesions are being developed. These methods are mostly based on deep learning techniques and are already reaching high classification accuracy. However, most of the existing works are restricted to classifying individual cross-sections of the lung CT scan. It is not clear how it should be extended for evaluating the disease on the CT scan volume as a whole and how it should be deployed for practical use. This project will focus on these issues and also investigate aspects such as robustness with respect to data coming from distinct sources. Additionally, if possible, clinical data will also be incorporated in the method to be developed. (AU)