一个基于基因病理图像的多类脑瘤分级系统,使用混合YOLO和RESNET网络
Naira Elazab1, Wael A Gab-Allah1, Mohammed Elmogy2
1Information Technology Department, Faculty of Computers and Information, Mansoura University, Mansoura, 35516, Egypt.
Scientific reports
|February 25, 2024
概括
这项研究引入了一种混合深度学习模型,将YOLOv5和ResNet50结合起来,以从组织病理图像中准确分类质瘤. 该模型有效地定位瘤并预测等级,优于现有方法.
科学领域:
- 计算病理学计算病理学
- 人工智能在瘤学中的应用
- 神经瘤学成像分析分析
背景情况:
- 准确的质瘤分类和分级对于患者的预后和治疗计划至关重要.
- 数字病理学和深度学习 (DL) 在脑瘤分析方面提供了潜在的进步.
- 现有的DL方法用于脑瘤诊断可以增强,以改善局部化和分级.
研究的目的:
- 开发和验证一种新的混合DL技术,用于精确的瘤定位和使用组织病理学图像预测质瘤分级.
- 将YOLOv5用于瘤检测和ResNet50用于特征提取集成到一个统一的框架内.
- 提高质瘤分类的准确性和可靠性,以改善临床决策.
主要方法:
- 开发了一种混合DL模型,将YOLOv5用于瘤定位/分类和ResNet50用于特征提取.
- 使用极端梯度增强分类器,根据提取的特征估计质瘤等级.
- 该模型在癌症基因组图谱数据集上进行了训练和评估.
主要成果:
- 混合模型在从组织病理学图像中识别脑瘤方面表现出很高的性能.
- 获得了97.2%的准确度,97.8%的精度,98.6%的灵敏度和97%的子系数,用于分类四种质瘤等级.
- 该模型在区分低度质瘤 (LGG) II和LGG III方面产生了重大影响,其表现优于现有方法.
结论:
- 拟议的混合YOLOv5-ResNet50模型为数字病理学中的质瘤分级提供了强大而准确的方法.
- 这种技术增强了瘤定位和预测分级,为临床实践提供了宝贵的见解.
- 该模型的卓越性能表明,自动化质瘤分类和分级系统的实质性进步.
相关概念视频
01:26Classification of Systems-I
742
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:
742
01:31Classification of Systems-II
651
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,
651