Texture analysis in sensor images for disease diagnosis: a study on transforms based on complex networks

• Grant number: 24/07241-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: August 01, 2024
• End date: July 31, 2025
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Lucas Correia Ribas
• Grantee: Ana Beatriz Silva Zerati
• Host Institution: Instituto de Biociências, Letras e Ciências Exatas (IBILCE). Universidade Estadual Paulista (UNESP). Campus de São José do Rio Preto. São José do Rio Preto , SP, Brazil
• Associated research grant: 18/22214-6 - Towards a convergence of technologies: from sensing and biosensing to information visualization and machine learning for data analysis in clinical diagnosis, AP.TEM

Abstract

Textures are essential attributes in pattern recognition in images and have practical applications in areas such as medicine, materials science and botany. Although some textures may present simple visual patterns, in general, real textures, such as those from sensors, involve non-linear processes in their formation, which adds complexity and makes analysis difficult. This project aims to study and implement image transformations using complex network concepts to improve texture analysis and classification, focusing on textures of sensory units used in diagnostics. The main advantage of complex networks lies in their ability to model patterns and offer interpretable characteristics, especially when facing challenges arising from non-linearity in practical scenarios. In this sense, the transformation procedure that we intend to investigate can be interpreted as a transformation of a complex network which models a texture image into multiple new images, offering an alternative perspective that can result in a fuller, richer description of the texture. In terms of application, the approaches studied will beapplied to microscopy images (such as sensory units) for the purpose of diagnosing diseases. Therefore, it is expected that this research will contribute to the computational field, developing improved techniques for texture analysis, and also advance in application areas, improving the performance of disease diagnoses. These contributions are aligned with the objectives of the thematic project (process 2018/22214-6), of which this project is part, whose goal is the convergence of diagnostic technologies.