CT TRAINING AND VALIDATION SERIES FOR 3D AUTOMATED SEGMENTATION OF INNER EAR USING U-NET ARCHITECTURE DEEP-LEARNING MODEL

This data set contains: - Training dataset: 271 CT-scans of innerearsused for optimization and training of the model. - Validation dataset: 70 CT-scans of innerearsused for external validation. - U-net architecture deep-learningmodel'sweightafteroptimized training. - All manual segmentations performed for bothdatasets. - All post-processedautomated segmentations performed by the model for bothdatasets. All CT-scans are related to matchingautomated and manual segmentations and have been namedidentically. Example : CT-scan “TDMvalext001“ in folder “Validation CT-scans" isrelated to “TDMvalext001” manual segmentation in folder “Validation manual segmentation”, and to “TDMvalext001_PRED” in folder “Validation automated segmentation”.

本数据集包含以下内容：
- 训练数据集：用于模型优化与训练的271例内耳CT扫描（CT-scan）影像。
- 验证数据集：用于外部验证的70例内耳CT扫描影像。
- 经优化训练后的U-Net（U-net）架构深度学习模型权重。
- 两份数据集对应的全部手动分割标注结果。
- 模型为两份数据集生成的全部后处理自动分割结果。
所有CT扫描影像均与匹配的自动、手动分割结果一一对应，且命名完全一致。示例：「验证CT扫描」文件夹中的CT扫描影像"TDMvalext001"，对应「验证手动分割标注」文件夹中的"TDMvalext001"手动分割结果，同时对应「验证自动分割结果」文件夹中的"TDMvalext001_PRED"。