Video Experimental Relacionado
Updated: Jan 29, 2026
08:31
Murine Model of Leukemia Relapse to Induction Chemotherapy for Acute Lymphoblastic Leukemia
Published on: October 17, 2025
619
Desmitificación de las Decisiones de Aprendizaje Profundo en el Diagnóstico de Leucemia Utilizando IA Explicable
Shahd H Altalhi1, Salha M Alzahrani1
1Department of Computer Science, College of Computers and Information Technology, Taif University, Taif 21944, Saudi Arabia.
Diagnostics (Basel, Switzerland)
|January 28, 2026
Resumen
Este estudio presenta un pipeline de IA que utiliza aprendizaje profundo e IA explicable (XAI) para el diagnóstico preciso de leucemia a partir de imágenes celulares. La IA logró una alta precisión, identificando características celulares clave para obtener resultados fiables.
Sus antecedentes:
- El diagnóstico convencional de leucemia se basa en la interpretación experta de frotis de sangre periférica y evaluaciones de médula ósea.
- Estos métodos enfrentan desafíos debido a la variabilidad biológica y de imagen, lo que requiere herramientas de diagnóstico avanzadas.
- Las técnicas moleculares existentes, como LDI-PCR, citogenética molecular y array-CGH, complementan el diagnóstico pero son complejas.
Objetivo del estudio:
- Desarrollar y validar un pipeline de IA para el diagnóstico de leucemia preciso e interpretable.
- Integrar Redes Neuronales Convolucionales (CNN) e IA Explicable (XAI) para una justificación diagnóstica transparente.
- Establecer un conjunto de datos de referencia completo para evaluar modelos de IA en la clasificación de leucemia.
Principales métodos:
- Se curó un conjunto de datos de referencia unificado de 66.550 imágenes que cubren varios tipos de leucemia (LLA, LMA, LLC, LMC) y controles sanos.
- Se ajustaron y evaluaron múltiples arquitecturas de CNN (DenseNet-121, MobileNetV2, etc.) utilizando métricas de precisión y puntuación F1.
- Se emplearon técnicas de IA Explicable (LIME, Grad-Cam) para proporcionar una justificación transparente de las decisiones diagnósticas de la IA.
Principales resultados:
- MobileNetV2 logró una precisión/F1 del 97,9 % en la tarea de clasificación de leucemia de cinco clases.
- DenseNet-121 también demostró un alto rendimiento con una puntuación F1 del 97,66 %, mostrando fuertes explicaciones centradas en el núcleo.
- Los análisis de XAI localizaron con éxito la morfología celular crítica, alineando la saliencia del modelo con los indicadores clínicos.
Conclusiones:
- El pipeline de IA propuesto, que integra CNN y XAI, logra una precisión de vanguardia en el diagnóstico de leucemia.
- Los métodos de IA Explicable proporcionan una interpretabilidad crucial, corroborando los hallazgos diagnósticos con relevancia clínica.
- Este enfoque ofrece una alternativa más precisa y transparente a los flujos de trabajo de diagnóstico convencionales para neoplasias hematológicas.
Videos de Conceptos Relacionados
01:20Decision Making
947
Decision-making is a fundamental cognitive process that involves evaluating alternatives and selecting among them. This process can range from simple choices, such as deciding what to wear, to complex decisions, like choosing a major in college or a career path. The complexity of the decision often dictates the approach we use, which can be broadly categorized into two types: automatic and controlled decision-making.
Automatic decision-making is fast, intuitive, and relies on gut feelings...
Automatic decision-making is fast, intuitive, and relies on gut feelings...
947
01:09Decision Making: P-value Method
6.9K
The process of hypothesis testing based on the P-value method includes calculating the P- value using the sample data and interpreting it.
First, a specific claim about the population parameter is proposed. The claim is based on the research question and is stated in a simple form. Further, an opposing statement to the claim is also stated. These statements can act as null and alternative hypotheses: a null hypothesis would be a neutral statement while the alternative hypothesis can...
First, a specific claim about the population parameter is proposed. The claim is based on the research question and is stated in a simple form. Further, an opposing statement to the claim is also stated. These statements can act as null and alternative hypotheses: a null hypothesis would be a neutral statement while the alternative hypothesis can...
6.9K
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
01:14Decision Making: Traditional Method
5.4K
The process of hypothesis testing based on the traditional method includes calculating the critical value, testing the value of the test statistic using the sample data, and interpreting these values.
First, a specific claim about the population parameter is decided based on the research question and is stated in a simple form. Further, an opposing statement to this claim is also stated. These statements can act as null and alternative hypotheses, out of which a null hypothesis would be a...
First, a specific claim about the population parameter is decided based on the research question and is stated in a simple form. Further, an opposing statement to this claim is also stated. These statements can act as null and alternative hypotheses, out of which a null hypothesis would be a...
5.4K
01:27Associative Learning
1.3K
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
1.3K
01:22Purposive Learning
470
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
470