Video Experimental Relacionado
Updated: Feb 11, 2026
07:29
Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound
Published on: October 4, 2021
2.9K
El primer marco de aprendizaje profundo para la mejora de la interacción de aniquilación de positrones-transmisión de
Rasool Safari1,2, Mohammadreza Parishan1,2, Zahra Rakeb1,2
1Department of Nuclear Engineering, School of Mechanical Engineering, Shiraz University, Shiraz, Iran.
Medical physics
|February 10, 2026
Resumen
DeepPAITI, un novedoso método de aprendizaje profundo, mejora significativamente la precisión de la extracción de mapas secundarios mediante imágenes de transmisión por interacción de aniquilación de positrones (PAITI). Este avance mejora la precisión para aplicaciones clínicas como la planificación del tratamiento de la terapia iónica.
Área de la Ciencia:
- Imágenes médicas de imágenes médicas.
- La inteligencia artificial es inteligencia artificial.
- Radioterapia Física de la radioterapia La física de la radioterapia es la misma que la de la radioterapia.
Sus antecedentes:
- La proyección de imágenes de transmisión por interacción de aniquilación de positrones (PAITI, por sus siglas en inglés) es una técnica de proyección de imágenes de dosis baja que genera múltiples mapas 2D.
- Los métodos analíticos actuales para extraer mapas secundarios (por ejemplo, densidad de electrones) tienen un error relativo promedio del 4,32%.
Objetivo del estudio:
- Introducir DeepPAITI, el primer enfoque de aprendizaje profundo para PAITI, para mejorar la precisión de la extracción de mapas secundarios.
- Mejorar la precisión para aplicaciones clínicas como la planificación del tratamiento de la terapia iónica.
Principales métodos:
- Desarrolló una arquitectura especializada de aprendizaje profundo con un marco multibrancario, de múltiples entradas y múltiples salidas.
- Entrenado y probado el modelo utilizando simulaciones numéricas y conjuntos de datos de GATE Monte Carlo.
- Comparó el DeepPAITI con modelos convencionales como ResNet, UNet y VGG-16.
Principales resultados:
- DeepPAITI logró errores medios relativos (MREs) del 0,63% (simulaciones) y del 0,91% (pruebas GATE), una mejora del 77% con respecto a los métodos analíticos.
- La confianza en la descomposición de la densidad de electrones aumentó del 63% al 99% en condiciones de dosis bajas (< 1 μGy).
- Demostró al menos una mejora del 83% en MRE en comparación con los modelos convencionales de aprendizaje profundo.
Conclusiones:
- DeepPAITI supera significativamente los métodos tradicionales y convencionales de aprendizaje profundo para la extracción de mapas secundarios de PAITI.
- Abre el camino para implementaciones clínicas más precisas en la planificación del tratamiento de radiación y terapia iónica.
Videos de Conceptos Relacionados
01:25Imaging Studies II: Positron Emission Tomography and Scintigraphy
610
Positron Emission Tomography (PET) is a medical imaging technique that provides crucial insights into the body's physiological functions at a molecular level. It is an indispensable resource for diagnosing, staging, and monitoring various illnesses, notably cancer, neurological disorders, and cardiovascular conditions.
Fundamental Principles of PET
Fundamental Principles of PET
610
01:29Positron Emission Tomography
7.6K
Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
7.6K
02:39Predator-Prey Interactions
21.7K
Predators consume prey for energy. Predators that acquire prey and prey that avoid predation both increase their chances of survival and reproduction (i.e., fitness). Routine predator-prey interactions elicit mutual adaptations that improve predator offenses, such as claws, teeth, and speed, as well as prey defenses, including crypsis, aposematism, and mimicry. Thus, predator-prey interactions resemble an evolutionary arms race.
21.7K
03:00Self-Evaluation: Self-Enhancement and Self-Verification
5.8K
Social psychologists have documented that feeling good about ourselves and maintaining positive self-esteem is a powerful motivator of human behavior (Tavris & Aronson, 2008). In the United States, members of the predominant culture typically think very highly of themselves and view themselves as good people who are above average on many desirable traits (Ehrlinger, Gilovich, & Ross, 2005). Often, our behavior, attitudes, and beliefs are affected when we experience a threat to our...
5.8K
03:37Uncertainty in Measurement: Accuracy and Precision
104.1K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.
104.1K
01:14Avoidance Learning and Learned Helplessness
2.6K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.6K