Video Experimental Relacionado
Updated: Feb 13, 2026
10:25
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
Published on: November 11, 2022
10.9K
[Algoritmos de segmentación automatizada basados en aprendizaje profundo de las subestructuras cerebrales y
Wei Wang1, Shuxian Chen1, Mawei Jiang1
1Oncology Department, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, 200092.
Resumen
FuseNet demuestra un rendimiento superior en la segmentación de subestructuras cerebrales y vertebrales pediátricas, reduciendo significativamente el tiempo de corrección manual. nnU-Net también muestra prometedoras capacidades de segmentación para la planificación del tratamiento del medulloblastoma.
Área de la Ciencia:
- Imágenes médicas de imágenes médicas.
- La inteligencia artificial en la medicina.
- Oncología Pediátrica Oncología Pediátrica.
Sus antecedentes:
- La segmentación precisa de las subestructuras del meduloblastoma es crucial para la planificación eficaz de la radioterapia en pacientes pediátricos.
- Los métodos de segmentación existentes pueden tener limitaciones en cuanto a precisión y eficiencia, particularmente en diferentes grupos de edad.
Objetivo del estudio:
- Evaluar la viabilidad y el rendimiento de nnU-Net y FuseNet para la segmentación automática de subestructuras de meduloblastoma pediátrico.
- Comparar estos modelos de aprendizaje profundo con los métodos tradicionales basados en Atlas y U-Net.
Principales métodos:
- Análisis retrospectivo de 60 pacientes pediátricos (≤5 y >5 años) que se sometieron a radioterapia.
- Segmentación de las subestructuras cerebrales utilizando imágenes de fusión CT-MRI y subestructuras vertebrales utilizando imágenes de TC.
- Formación y validación de los modelos U-Net, nnU-Net y FuseNet, con validación externa para su generalización.
Principales resultados:
- FuseNet superó a los métodos basados en Atlas y U-Net en la segmentación de la subestructura vertebral para ambos grupos de edad (P<0,05).
- FuseNet demostró altos valores de coeficiente de similitud de dados (DSC) (>0,8) para la mayoría de las subestructuras y logró el tiempo de corrección manual más corto.
- nnU-Net mostró un buen rendimiento de segmentación, mientras que FuseNet mejoró la precisión de segmentación cerebral a través de la fusión dinámica de características multimodal.
Conclusiones:
- nnU-Net es una herramienta viable para lograr una buena segmentación automática de las subestructuras del meduloblastoma.
- FuseNet ofrece una mayor precisión de segmentación cerebral y una eficiencia de corrección superior, por lo que es una herramienta prometedora para la planificación de la radioterapia pediátrica.
Palabras clave:
segmentación automatizada de la segmentación.El medulloblastoma es un tumor de la médula.red neuronal convolucional multimodal de red neuronal convolucional multimodal es una red neuronal convolucional de red neuronal multimodal es una red neuronal convolucional es una red neuronal convolucional es una red neuronalradioterapia pediátrica para niños y niñas.la subestructura de la subestructura.
Videos de Conceptos Relacionados
01:26Higher Mental Functions of Brain: Learning and Memory
2.1K
Memory is one of the most vital higher mental functions of the brain. Memory is closely related to learning because it enables us to retain information and experiences from our past to use them in our present life. It also helps us to remember facts, events, and skills, such as riding a bike or swimming. There are two types of memory — declarative memory, which involves memorizing facts or events, and procedural memory, which enables us to remember how to do something like writing or...
2.1K
01:27Muscles of the Vertebral Column
3.3K
The back muscles that lie deep into the thoracolumbar fascia are called intrinsic or true back muscles. These muscles are divided into four layers: superficial, intermediate, deep, and deepest layers.
Superficial Layer:
The superficial layer consists primarily of the splenius muscles, which include the splenius capitis and splenius cervicis. These muscles are mainly responsible for the head and cervical spine movements, including extension, rotation, and lateral bending. The splenius capitis...
Superficial Layer:
The superficial layer consists primarily of the splenius muscles, which include the splenius capitis and splenius cervicis. These muscles are mainly responsible for the head and cervical spine movements, including extension, rotation, and lateral bending. The splenius capitis...
3.3K
01:12Trial and Error and Algorithm
429
A problem-solving strategy is a plan of action used to find a solution. Different strategies have distinct action plans. Trial and error involves trying different solutions until one works. For instance, to fix a broken printer, you might check ink levels, ensure the paper tray isn't jammed, and verify the printer's connection to your laptop. This method can be time-consuming but is commonly used. Thomas Edison, for example, used trial and error to find a suitable filament for the light...
429
01:28Articulations of the Vertebral Column
3.2K
In addition to being held together by the intervertebral discs, adjacent vertebrae also articulate with each other at synovial joints formed between the superior and inferior articular processes called zygapophysial joints (facet joints). These are plane joints that provide for only limited motions between the vertebrae. The orientation of the articular processes at these joints varies in different regions of the vertebral column and serves to determine the types of motions available in each...
3.2K
01:16Vertebral Column: Regions and Curvature
6.2K
The vertebral column or spine is a flexible column that supports the head, neck, and body and allows for their movements. It also protects the spinal cord.
Regions of the Vertebral Column
In an adult, the spine is subdivided into five regions: the cervical, the thoracic, the lumbar, the sacral, and the coccygeal region. The spine initially develops as a series of 33 vertebrae; after 20 years of age, the nine bones in the sacral region, five sacral, and four coccygeal bones fuse to form...
Regions of the Vertebral Column
In an adult, the spine is subdivided into five regions: the cervical, the thoracic, the lumbar, the sacral, and the coccygeal region. The spine initially develops as a series of 33 vertebrae; after 20 years of age, the nine bones in the sacral region, five sacral, and four coccygeal bones fuse to form...
6.2K
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