Human treelike tubular structure segmentation in medical images

Segmentation of treelike tubular structures in medical imaging is crucial for accurate diagnosis and treatment. Traditional methods often struggle with the complex morphology and inherent data variability of structures like blood vessels and lung branching. To tackle these challenges, this work pres...

Descripción completa

Detalles Bibliográficos
Autor: Vargas Daza, Luisa Fernanda
Tipo de recurso: tesis de maestría
Estado:Versión aceptada para publicación
Fecha de publicación:2023
País:Colombia
Institución:Universidad de los Andes
Repositorio:Séneca: repositorio Uniandes
Idioma:inglés
OAI Identifier:oai:repositorio.uniandes.edu.co:1992/73410
Acceso en línea:https://hdl.handle.net/1992/73410
Access Level:acceso abierto
Palabra clave:Segmentation
Blood vessels
Airways
Nerves
Computer vision
Medical images
CT
MRI
Ingeniería
Descripción
Sumario:Segmentation of treelike tubular structures in medical imaging is crucial for accurate diagnosis and treatment. Traditional methods often struggle with the complex morphology and inherent data variability of structures like blood vessels and lung branching. To tackle these challenges, this work presents three significant contributions. First, it introduces a comprehensive dataset aggregation, focusing on tubular structures, to challenge and benchmark existing segmentation algorithms. Second, an innovative evaluation framework is developed, surpassing traditional metrics by accurately assessing segmentation quality based on geometrical and topological characteristics of tubular structures. Lastly, the thesis proposes the Joint Brain-Vessel Segmentation (JoB-VS) framework, an end-to-end solution for segmenting brain vessels in TOF-MRA images, enhancing performance by forgoing additional preprocessing steps. These contributions collectively advance the field of medical image analysis, bridging the gap between technical segmentation techniques and their clinical application, thereby enhancing diagnostics and treatment planning in healthcare.