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：
- 训练集：271例内耳CT扫描数据，用于模型的优化与训练。
- 验证集：70例内耳CT扫描数据，用于外部验证。
- 经优化训练后的U-Net架构深度学习模型权重。
- 针对上述两个数据集完成的全部人工分割标注结果。
- 模型针对上述两个数据集生成的全部经后处理的自动分割结果。

所有CT扫描数据均配有对应的自动与手动分割结果，且命名完全一致。例如："Validation CT-scans"文件夹中的CT扫描数据"TDMvalext001"，对应"Validation manual segmentation"文件夹中的手动分割标注"TDMvalext001"，以及"Validation automated segmentation"文件夹中的自动分割结果"TDMvalext001_PRED"。