CT-PET Dataset
收藏资源简介:
CT-PET数据集是由越南河内科学与技术大学和日本名古屋大学等机构创建的,是目前最大的CT-PET配对图像数据集,包含2,028,628对CT和PET图像。数据集涵盖了广泛的解剖区域,从头部到上大腿区域,图像以DICOM格式存储,包含详细的元数据。数据集的创建旨在支持CT到PET图像翻译模型的训练和评估,特别是在癌症诊断和治疗监测方面。通过结合领域知识,如注意力图和衰减图,数据集的应用旨在提高PET图像生成的准确性和诊断信息的质量。
The CT-PET dataset was created by institutions including Hanoi University of Science and Technology in Vietnam and Nagoya University in Japan. It is currently the largest paired CT-PET image dataset, containing 2,028,628 pairs of CT and PET images. The dataset covers a wide range of anatomical regions from the head to the upper thigh, with all images stored in DICOM format and accompanied by detailed metadata. The dataset was developed to support the training and evaluation of CT-to-PET image translation models, particularly for cancer diagnosis and treatment monitoring. By incorporating domain-specific knowledge such as attention maps and attenuation maps, the application of this dataset aims to improve the accuracy of PET image generation and the quality of diagnostic information.
CT to PET Translation: A Large-scale Dataset and Domain-Knowledge-Guided Diffusion Approach
数据集概述
- 数据集名称: CT/PET Dataset
- 数据集规模: 包含2,028,628对PET-CT图像
- 数据集示例: 请参考
CTPET_DATASET文件夹查看数据集样本
数据准备
- 数据路径格式: yaml your_dataset_path/train/A # 训练参考 your_dataset_path/train/B # 训练真实值 your_dataset_path/val/A # 验证参考 your_dataset_path/val/B # 验证真实值 your_dataset_path/test/A # 测试参考 your_dataset_path/test/B # 测试真实值
引用
-
论文引用:
@inproceedings{nguyen2025CPDM, title = {CT to PET Translation: A Large-scale Dataset and Domain-Knowledge-Guided Diffusion Approach}, author = {Nguyen, Dac Thai and Nguyen, Trung Thanh and Nguyen, Huu Tien and Nguyen, Thanh Trung and Pham, Huy Hieu and Nguyen, Thanh Hung and Truong, Thao Nguyen and Nguyen, Phi Le}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision}, year = {2025}, }




