卷积神经网络的性能用于使用磁共振成像对脑瘤的分类
Daniel Reyes1,2, Javier Sánchez2
1Dr. Stetter ITQ S.L.U., Parque Científico Tecnológico, Las Palmas de Gran Canaria, 35017, Spain.
Heliyon
|February 14, 2024
概括
这项研究比较了大脑瘤分类的深度学习模型,发现像MobileNet和EfficientNet这样的模型可以实现高精度 (高达98.7%) 和卓越的效率. 通过微调转移学习通常会产生最好的结果.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 计算神经科学是一种神经科学.
背景情况:
- 由于瘤异质性,脑瘤的分类是复杂的.
- 深度学习显示了准确的瘤检测和分类的前景.
- 缺乏深度学习技术用于脑瘤分类的标准化比较.
研究的目的:
- 分析和比较各种卷积神经网络 (CNN) 的性能,用于脑瘤分类.
- 评估不同的深度学习架构,包括自定义的CNN,VGG,ResNet,EfficientNet和ConvNeXt.
- 评估培训策略 (如转移学习和微调) 对分类准确性的影响.
主要方法:
- 利用了两个磁共振成像 (MRI) 数据集,包括3000多张质瘤,脑膜瘤,垂体瘤和健康组织的图像.
- 实现并比较一个自定义的CNN,VGG,ResNet,EfficientNet和ConvNeXt架构.
- 评估模型使用从零开始的训练,数据增强,转移学习和微调,优化训练和验证集上的超参数.
主要成果:
- 几个CNN实现了高精度,最好的模型达到98.7%.
- 平均精度因瘤类型而异:质瘤 (94.3%),脑膜瘤 (93.8%),垂体瘤 (97.9%) 和非瘤图像 (95.3%).
- 移动网络和EfficientNet在准确性和计算复杂性方面表现出卓越的性能,训练时间快,图像吞吐量高.
结论:
- 深度学习模型,特别是像MobileNet和EfficientNet这样的高效架构,对于使用MRI数据进行脑瘤分类非常有效.
- 转移学习与微调相结合是最大限度地提高分类准确性的最有效策略.
- 虽然数据增强并没有持续提高准确性,但高效的模型提供了高性能和计算可行性的平衡.
相关概念视频
Brain Imaging
229
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
229
Magnetic Resonance Imaging
5.2K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
5.2K


