AATCT-IDS

AATCT-IDS是由东北大学医学与生物信息工程学院显微图像与医学图像分析组创建的腹部脂肪CT图像数据集，包含300名受试者的13,732张原始CT切片。该数据集用于图像去噪、语义分割和放射组学评估，通过手动标注3,213张切片中的皮下和内脏脂肪区域，以验证去噪方法、训练语义分割模型和研究放射组学。数据集的创建过程涉及从DICOM文件中提取图像数据，进行格式转换和标注，最终用于多种深度学习和机器学习算法的训练和验证。AATCT-IDS的应用领域包括提高临床诊断的效率和准确性，帮助医生和患者进行临床实践。

AATCT-IDS is an abdominal fat CT imaging dataset developed by the Microscopic and Medical Image Analysis Group, College of Medicine and Bioinformatics Engineering, Northeastern University. It comprises 13,732 raw CT slices from 300 individual subjects. This dataset is intended for applications including image denoising, semantic segmentation, and radiomics assessment. Specifically, 3,213 slices have been manually annotated with regions of subcutaneous and visceral fat, which supports the validation of denoising approaches, training of semantic segmentation models, and radiomics investigations. The construction of this dataset entails extracting image data from DICOM files, performing format conversion and annotation, and ultimately enables the training and validation of a wide range of deep learning and machine learning algorithms. The application scope of AATCT-IDS covers improving the efficiency and accuracy of clinical diagnosis, as well as assisting clinicians and patients in carrying out clinical practice.