Visual attention models and arse representations for morphometrical image analysis

Abstract. Medical diagnosis, treatment, follow-up and research activities are nowadays strongly supported on different types of diagnostic images, whose main goal is to provide an useful exchange of medical knowledge. This multi-modal information needs to be processed in order to extract information exploitable within the context of a particular medical task. In despite of the relevance of these complementary sources of medical knowledge, medical images are rarely further processed in actual clinical practice, so the specialists take decisions only based in the raw data. A new trend in the development of medical image processing and analysis tools follows the idea of biologically-inspired methods, which resemble the performance of the human vision system. Visual attention models and sparse representations are examples of this tendency. Based on this, the aim of this thesis was the development of a set of computational methods for automatic morph metrical analysis, combining the relevant region extraction power of visual attention models with the incorporation of a priori information capabilities of sparse representations. The combination of these biologically inspired tools with common machine learning techniques allowed the identification of visual patterns relevant for pathology discrimination, improving the accuracy and interpretability of morph metric measures and comparisons. After extensive validations with different image data sets, the computational methods proposed in this thesis seems to be promising tools for the definition of anatomical biomarkers, based on visual pattern analysis, and suitable for patient's diagnosis, prognosis and follow-up.

• Autores: Rueda Olarte, Andrea del Pilar
• Tipo de recurso: Doctoral thesis
• Fecha de publicación: 2013
• Institución: Universidad Nacional de Colombia
• Repositorio: Universidad Nacional de Colombia
• Idioma: spa
• OAI Identifier: oai:repositorio.unal.edu.co:unal/21177
• Acceso en línea: https://repositorio.unal.edu.co/handle/unal/21177; http://bdigital.unal.edu.co/11932/
• Palabra clave: 46 Lenguas española y portuguesa / Specific languages; 61 Ciencias médicas; Medicina / Medicine and health; 62 Ingeniería y operaciones afines / Engineering; Computational neuroanantomy; Sparse representations; Visual attention models; Machine learning techniques; Alzheimer's disease; Semantic-based representations; Visual pattern analysis; Neuroanatomía computacional; Representaciones escasas; Modelos de atención visual; Técnicas de aprendizaje de máquina; Enfermedad de Alzheimer; Representaciones basadas en semántica; Análisis de patrones visuales
• Rights: openAccess
• License: Atribución-NoComercial 4.0 Internacional