相关实验视频

Updated: May 17, 2025

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

研究和优化白细胞分类方法基于深度学习和富里埃图形显微镜的基础上

Mingjing Li¹, Junshuai Wang¹, Shu Fang¹

¹College of Electronic Information Engineering, Changchun University, Changchun 130022, China.

Sensors (Basel, Switzerland)

|May 14, 2025

概括

这项研究引入了CCE-YOLOv7,这是使用深度学习对白细胞 (WBC) 进行分类的增强算法. 这种新方法显著提高了自动化血液病理学诊断的准确性和效率.

科学领域:

医学成像分析分析医学成像分析
计算病理学计算病理学
人工智能在诊断中的应用

背景情况:

传统的白血细胞 (WBC) 分类方法在受体场和上下文信息利用方面存在局限性,影响诊断准确性.
血液病理学和临床诊断在很大程度上依赖于准确的WBC分类来识别疾病和患者管理.

研究的目的:

开发一个增强的WBC分类算法,CCE-YOLOv7,通过提高检测准确性和模型效率来克服传统方法的局限性.
利用深度学习,特别是YOLOv7框架,使用新型架构组件来实现卓越的特征表示和分类性能.

主要方法:

拟议的CCE-YOLOv7集成了一个新的Conv2Former骨干,用于联合本地和全球特征提取.
集成的内容意识重组特征 (CARAFE) 上采样和高效多尺度注意力 (EMA) 模块,用于增强特征地图和融合.
使用软非最大抑制 (Soft-NMS) 来改善重叠细胞的处理,减少分类错误.

主要成果:

CCE-YOLOv7在WBC图像数据集上实现了89.3%的检测准确度,比基线YOLOv7.7有7.8%的改进.
与YOLOv7.7相比,该模型表现出更高的效率,减少了200万个参数和5.7 GFLOP的计算复杂性.
CCE-YOLOv7在精度方面超过了YOLOv84.1%,并且提供了比YOLOv11.11更好的计算效率.

结论:

CCE-YOLOv7为自动化WBC分类提供了一个强大,准确和计算效率高的解决方案.
该算法的精度和效率的改进表明,在血液病理学中实时临床应用的巨大潜力.
该研究强调了将卷积和变压器架构与先进的注意力和特征融合机制相结合的有效性,用于医疗图像分析.

关键词:

卡拉菲 (CARAFE) 提升了样本的数量.欧洲药物管理局的机制里埃图形显微镜的福里埃图形显微镜软-NMS 是一个软的NMS.这就是YOLOv7的意义.白细胞分类白细胞分类

更多相关视频

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

Controlled Microfluidic Environment for Dynamic Investigation of Red Blood Cell Aggregation

Controlled Microfluidic Environment for Dynamic Investigation of Red Blood Cell Aggregation

Published on: June 4, 2015

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...