Descripción del proyecto
Un método de aprendizaje automático innovador para la imagen médica
La imagenología tiene una capacidad inigualable para identificar con gran precisión enfermedades, lo que impulsa una fuerte demanda de técnicas de imagen médica con apoyo diagnóstico automatizado para profesionales sanitarios y cuidadores. Se prevé que el aprendizaje automático proporcione una solución algorítmica para la automatización del diagnóstico. Sin embargo, las máquinas deben ser capaces de analizar las nuevas imágenes en función de los conocimientos sobre la anatomía sana y la variabilidad fisiológica prevista. En el proyecto MIA-NORMAL, financiado por el Consejo Europeo de Investigación, se desarrollará el aprendizaje de representación normativa como un novedoso método de aprendizaje profundo para la imagenología médica, proporcionando herramientas informáticas personalizadas para la confirmación de la normalidad, el control de calidad de las imágenes, el cribado sanitario y la prevención de enfermedades. Los modelos resultantes obtendrán información clínicamente útil a partir de datos de pacientes sanos con la mayor frecuencia posible durante el itinerario asistencial de los pacientes.
Objetivo
As one of the most important aspects of diagnosis, treatment planning, treatment delivery, and follow-up, medical imaging provides an unmatched ability to identify disease with high accuracy. As a result of its success, referrals for imaging examinations have increased significantly. However, medical imaging depends on interpretation by highly specialised clinical experts and is thus rarely available at the front-line-of-care, for patient triage, or for frequent follow-ups. Very often, excluding certain conditions or confirming physiological normality would be essential at many stages of the patient journey, to streamline referrals and relieve pressure on human experts who have limited capacity. Hence, there is a strong need for increased imaging with automated diagnostic support for clinicians, healthcare professionals, and caregivers.
Machine learning is expected to be an algorithmic panacea for diagnostic automation. However, despite significant advances such as Deep Learning with notable impact on real-world applications, robust confirmation of normality is still an unsolved problem, which cannot be addressed with established approaches.
Like clinical experts, machines should also be able to verify the absence of pathology by contrasting new images with their knowledge about healthy anatomy and expected physiological variability. Thus, the aim of this proposal is to develop normative representation learning as a new machine learning paradigm for medical imaging, providing patient-specific computational tools for robust confirmation of normality, image quality control, health screening, and prevention of disease before onset. We will do this by developing novel Deep Learning approaches that can learn without manual labels from healthy patient data only, applicable to cross-sectional, sequential, and multi-modal data. Resulting models will be able to extract clinically useful and actionable information as early and frequent as possible during patient journeys.
Ámbito científico
- medical and health sciencesbasic medicineanatomy and morphology
- social sciencessociologyindustrial relationsautomation
- medical and health sciencesbasic medicinepathology
- natural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learning
- engineering and technologymedical engineeringdiagnostic imaging
Palabras clave
Programa(s)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Régimen de financiación
HORIZON-ERC - HORIZON ERC GrantsInstitución de acogida
91054 Erlangen
Alemania