本研究采用受控框架评估固定架构下的预处理流水线和优化器,旨在确定经典预处理如何影响优化器和卷积神经网络(CNN)在脑肿瘤分类中的应用。
Access restricted. Please log in or start a trial to view this content.
Access restricted. Please log in or start a trial to view this content.
Access restricted. Please log in or start a trial to view this content.
Access restricted. Please log in or start a trial to view this content.
Access restricted. Please log in or start a trial to view this content.
| Name | Company | Catalog Number | Comments |
|---|---|---|---|
| API 包装器 | 克拉斯 | 2.13.1(RRID:SCR_016345) | CNN架构与培训的高级API |
| 归因工具 | Grad-CAM 实现 | 自定义(通过Keras) | CNN注意力的视觉解释 |
| BR35H脑肿瘤MRI数据集 | 卡格尔 | https://www.kaggle.com/ahmedhamada0/brain-tumor-detection | 分类用标记MRI图像来源及nbsp; |
| 脑肿瘤数据集 | 超溶菌 | https://docs.ultralytics.com/datasets/detect/brain-tumor/ | |
| 深度学习库 | 张量流 | 2.15.0 (RRID:SCR_018345) | CNN模型实现的后端 |
| 图像处理 | OpenCV | 4.8.0 (RRID:SCR_015526) | 预处理:灰度、模糊、阈值、形态 |
| 编程语言 | 蟒蛇 | 3.10.12 (RRID:SCR_008394) | 所有实验的执行环境 |
| 可视化 | Matplotlib | 3.8.0 (RRID:SCR_008624) | 损耗曲线绘制与Grad-CAM叠加 |
Access restricted. Please log in or start a trial to view this content.
Request permission to reuse the text or figures of this JoVE article
Request Permission