相关实验视频

Updated: Sep 10, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

有效的轻量级CNN用于B细胞急性淋巴细胞白血病的自动分类

Awaz M Abbas¹, Maiwan Bahjat Abdulrazaq¹, Adel Al-Zebari²

¹Department of Computer Science, College of Science, University of Zakho, Zakho, Kurdistan Region, Iraq.

Computational biology and chemistry

|August 22, 2025

概括

一个新的轻量级卷积神经网络 (CNN) 从周围血液涂抹图像准确地分类B细胞急性淋巴细胞白血病 (B-ALL). 这种高效的人工智能模型显示出早期临床诊断和改善患者结果的巨大潜力.

科学领域:

血液学
医学成像
人工智能

背景情况:

由于晚期诊断,B细胞急性淋巴细胞白血病 (B-ALL) 是一种快速进展的血液恶性瘤,其存活率降低.
周围血液涂抹 (PBS) 影像对初步B-ALL查至关重要,为计算机辅助诊断提供了基础.
目前的诊断方法可能昂贵且耗时,这凸显了对高效且易于使用的查工具的需求.

研究的目的:

开发一个轻量级的卷积神经网络 (CNN) 来从PBS图像中直接分类B-ALL亚型.
创建一个计算效率高的模型,避免需要预分段.
在反向剩余块中使用Squeeze-and-Excitation (SE) 模块增强特征表示.

主要方法:

设计了一种新的轻量级CNN架构,将SE模块纳入倒置剩余块.
该模型在PBS图像上进行了训练和评估,以进行B-ALL分类.
对独立数据集进行了交叉数据集验证,以评估可通用性.
使用Grad-CAM和LIME技术实现了模型的解释性.

主要成果:

拟议的CNN在初级数据集上实现了100%的准确性,精度,灵敏度,特异性,F1得分和MCC.
交叉数据集验证显示,在没有再培训的情况下,准确度高达99. 85%.
解释性方法成功突出了B-ALL的关键细胞特征.

结论:

开发的框架为自动化B-ALL分类提供了高度准确,资源高效和可解释的解决方案.
该模型的性能和通用性表明其在临床实践中用于早期诊断的强大潜力.
公开可用的代码有助于进一步研究和应用这种人工智能驱动的诊断工具.

关键词:

急性淋巴细胞白血病血液癌症进行分类卷积神经网络深度学习

更多相关视频

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

Flow Cytometry to Estimate Leukemia Stem Cells in Primary Acute Myeloid Leukemia and in Patient-derived-xenografts, at Diagnosis and Follow Up

Flow Cytometry to Estimate Leukemia Stem Cells in Primary Acute Myeloid Leukemia and in Patient-derived-xenografts, at Diagnosis and Follow Up

Published on: March 26, 2018

相关概念视频

Classification of Leukocytes

Classification of Leukocytes

Leukocytes are classified into two groups based on the presence or absence of cytoplasmic granules. Granular leukocytes, which contain granules, belong to the myeloid lineage and are divided into three subtypes: neutrophils, eosinophils, and basophils. These cells are roughly spherical and characterized by the granules in their cytoplasm.
Neutrophils are the most abundant type of granular leukocytes, comprising 50-70% of all leukocytes. They feature small, evenly distributed granules and a...