3D Medical Matting Dataset

3D医学图像软分割数据集是由哈尔滨工程大学智能系统科学与工程学院的研究团队创建的，专门用于医学图像的软分割研究。该数据集包含864个3D肺结节图像，这些图像来源于LIDC-IDRI数据集，经过半自动化标注过程生成。数据集的创建旨在解决3D医学图像软分割研究中数据不足的问题，通过临床评估和下游实验验证了数据集的有效性。该数据集的应用领域包括肺结节的分级和精确放射治疗，通过保留更多细节，为下游任务提供更多信息。

The 3D medical image soft segmentation dataset was created by the research team from the School of Intelligent Systems Science and Engineering, Harbin Engineering University, and is specifically dedicated to medical image soft segmentation research. This dataset contains 864 3D pulmonary nodule images sourced from the LIDC-IDRI dataset, which were generated through a semi-automated annotation process. The creation of this dataset aims to address the problem of insufficient data in 3D medical image soft segmentation research, and its effectiveness has been verified via clinical assessments and downstream experiments. The application fields of this dataset include pulmonary nodule grading and precision radiotherapy, as it preserves more details to provide additional information for downstream tasks.