Analysis of plain chest x-ray images of patients with fungal infections and lung cancer using artificial intelligence tools applied to diagnostic aids.

• Grant number: 23/12569-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: November 01, 2023
• End date: October 31, 2024
• Field of knowledge: Health Sciences - Medicine - Medical Radiology
• Principal Investigator: Marcel Koenigkam Santos
• Grantee: Kaio Henrique Avelino Domeni de Paulo
• Host Institution: Faculdade de Medicina de Ribeirão Preto (FMRP). Universidade de São Paulo (USP). Ribeirão Preto , SP, Brazil
• Associated research grant: 19/22577-4 - Clinical application of artificial intelligence tools to diagnostic aid in simple chest radiography images, AP.JP

Abstract

In most situations, a simple chest x-ray (X-ray) represents the first radiological examination in the evaluation of thoracic and pulmonary diseases. Most bronchopulmonary diseases present on X-ray as opacities, such as tuberculosis, fungal infections, interstitial lung diseases, lung cancer and viral pneumonia. These diseases have high morbidity and mortality and require additional investigation, with computed tomography (CT) and/or laboratory tests. In recent years, computerized diagnosis/detection tools (CAD) have been created to help detect changes in imaging exams, interpret findings and improve the workflow of healthcare services. . To this end, the development of artificial intelligence (AI), machine learning and deep learning tools has been highlighted. Fungal pneumonias are uncommon, but they represent an important cause of morbidity and mortality, especially in the population of immunosuppressed individuals. Lung cancer represents the main cause of cancer-related death in the world and, although screening should not be carried out using an X-ray, the radiographic examination is often the first to detect the presence of a suspicious lung nodule or mass. The lung is also one of the most common sites of metastasis from other tumors.