相关实验视频

Updated: Jun 17, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

ResNeXt-CC:一个基于跨层深度特征融合的新型网络,用于白细胞分类

Yang Luo¹, Ying Xu², Changbin Wang¹

¹School of Artificial Intelligence, Anshan Normal University, Anshan, 114007, Liaoning, China.

Scientific reports

|August 8, 2024

概括

这项研究介绍了ResNeXt-CC,这是一种新的深度学习网络,用于在细胞病理图像中对白细胞进行分类. 该方法显著提高了白血病检测的诊断准确性,优于现有的分类技术.

科学领域:

医学图像分析医学图像分析
计算病理学计算病理学
医疗保健中的人工智能

背景情况:

准确的白细胞诊断对于白血病的评估至关重要.
完全卷积网络在医学图像分类方面表现有前途.
现有的方法需要提高精确的细胞病理图像分析.

研究的目的:

提出ResNeXt-CC,一个先进的深度学习网络用于白细胞分类.
用细胞病理图像提高白血病诊断的准确性和效率.
为应对医疗图像分类中的阶级不平衡和特征提取方面的挑战.

主要方法:

图像从RGB转换为HSV颜色空间,用于详细的特征提取.
开发一个跨层深度特征聚变模块,以增强歧视性信息.
集成ECANet模块以改进特征提取和修改软max与中央损失函数来处理类不平衡.

主要成果:

与ResNet-50,Inception-V3,Densenet121,VGG16,Cross ViT,Token-to-Token ViT,Deep ViT和简单的ViT相比,ResNeXt-CC在C-NMC 2019数据集上表现出了优异的表现. 这就是为什么ResNeXt-CC在C-NMC 2019数据集上表现出了优异的表现.
实现了从5.5到20.43%的精度改进.
在F1得分 (3.6-23.56%),AUROC (3.5-25.71%) 和特异性 (8.1-36.98%) 中观察到显著的增长.

结论:

拟议的ResNeXt-CC网络在自动化白细胞分类方面取得了重大进展.
集成HSV颜色空间,特征融合,注意力机制和专业损失功能的集成有效地提高了诊断性能.
这种方法通过改进的细胞病理图像分析,为改善白血病诊断提供了强大的解决方案.

关键词:

失去中心的中心损失.颜色空间转换的变化跨层深度特征聚变模块 (CFFM) 的使用软最大限度损失 (softmax) 的损失.白细胞的分类白细胞的分类

更多相关视频

Preparation of Whole Bone Marrow for Mass Cytometry Analysis of Neutrophil-lineage Cells

Preparation of Whole Bone Marrow for Mass Cytometry Analysis of Neutrophil-lineage Cells

Published on: June 19, 2019

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

相关概念视频

Flow Cytometry

Flow Cytometry

The development of flow cytometry techniques began in 1934 with initial attempts by Andrew Moldavan, a bacteriologist who counted the cells in a flowing capillary system. Moldavan pumped cells through a capillary tube focused under a microscope for visualization. The invention of photometry allowed the measurement of differentially-stained cells, and Louis Kamentsky developed the first multiparameter flow cytometer in 1965 to identify and count the cancer cells in cervical tissue specimens.
In...

Differentiation of Common Myeloid Progenitor Cells

Differentiation of Common Myeloid Progenitor Cells

Common myeloid progenitors (CMPs) are oligopotent cells that can differentiate into granulocytes and macrophages. Granulocytes and macrophages are essential for protecting the body against bacterial, viral, or fungal infections. They migrate from the bone marrow into the circulating blood to reach specific tissue sites where they differentiate and help in immune surveillance. However, they survive only for a few days and must be continuously made available to the organism to maintain a robust...

Classification of Neurotransmitters

Classification of Neurotransmitters

Neurotransmitters play a crucial role in the communication between neurons in the autonomic nervous system. Neurons in the autonomic nervous system can be cholinergic or adrenergic depending on the neurotransmitters synthesized. Cholinergic neurons use acetylcholine as their primary neurotransmitter. This includes all the preganglionic fibers of the sympathetic and pre- and postganglionic fibers of the parasympathetic nervous systems. In addition, neurons of the somatic nervous system also use...