Video Experimental Relacionado
Updated: Sep 10, 2025

12:22
Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT
Published on: August 4, 2018
8.6K
Metaaprendizaje con actualización de consultas sin etiquetas y aprendizaje de consistencia para la clasificación de
IEEE transactions on bio-medical engineering
|August 25, 2025
Resumen
Este estudio introduce un nuevo algoritmo de metaaprendizaje para la clasificación de imágenes de tomografía de coherencia óptica (OCT) de pocos disparos, mejorando el diagnóstico de enfermedades raras. El método mejora la generalización del modelo con datos limitados.
Área de la Ciencia:
- Oftalmología
- Imágenes médicas
- Inteligencia artificial
Sus antecedentes:
- Las redes neuronales profundas (DNN) son vitales para el diagnóstico de enfermedades comunes de la retina mediante tomografía de coherencia óptica (OCT).
- El diagnóstico de enfermedades raras de la retina con DNNs es un desafío debido a la insuficiencia de datos de entrenamiento.
- El aprendizaje de pocos disparos basado en metaaprendizaje ofrece una solución para escenarios con escasez de datos.
Objetivo del estudio:
- Desarrollar un nuevo algoritmo para la clasificación de imágenes OCT de pocas tomas.
- Abordar el reto de diagnosticar enfermedades raras con datos limitados de los PTU.
- Mejorar las capacidades de generalización de los modelos de aprendizaje profundo para el diagnóstico de enfermedades raras.
Principales métodos:
- Un algoritmo de metaaprendizaje ajusta los modelos previamente entrenados para la generalización de tareas.
- El aprendizaje no supervisado en los datos de consulta se integra en el metaaprendizaje.
- El aprendizaje de consistencia de conjuntos cruzados minimiza las discrepancias entre los datos de soporte y consulta.
- La mezcla de datos genera muestras virtuales para aumentar la diversidad de datos.
Principales resultados:
- El método propuesto logró una mayor precisión de clasificación que las técnicas de aprendizaje de pocos disparos existentes en un conjunto de datos de los PTU.
- Los experimentos con un conjunto de datos de imágenes histológicas demostraron un rendimiento superior, confirmando la generalización.
- El algoritmo utiliza efectivamente datos limitados y descubre información oculta.
Conclusiones:
- Las estrategias desarrolladas mejoran el rendimiento del modelo al maximizar la utilidad de los datos limitados.
- El nuevo enfoque muestra un valor significativo para la capacitación de modelos de aprendizaje profundo en el diagnóstico de enfermedades raras.
- Este método mejora la generalización del modelo a tareas no vistas anteriormente.
Videos de Conceptos Relacionados
Classification of Systems-II
240
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
240
Classification of Systems-I
296
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
296
Imaging Biological Samples with Optical Microscopy
5.3K
Optical microscopy uses optic principles to provide detailed images of samples. Antonie van Leeuwenhoek designed the first compound optical microscope in the 17th century to visualize blood cells, bacteria, and yeast cells. In 1830, Joseph Jackson Lister created an essentially modern light microscope. The 20th century saw the development of microscopes with enhanced magnification and resolution.
In optical microscopy, the specimen to be viewed is placed on a glass slide and clipped on the stage...
In optical microscopy, the specimen to be viewed is placed on a glass slide and clipped on the stage...
5.3K
Aggregates Classification
381
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
381
Force Classification
1.6K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.6K
Improving Translational Accuracy
11.9K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.9K

