Unpaired MR-CT Brain Dataset for Unsupervised Image Translation

The Magnetic Resonance - Computed Tomography (MR-CT) Jordan University Hospital (JUH) dataset has been collected after receiving Institutional Review Board (IRB) approval of the hospital and consent forms have been obtained from all patients. All procedures has been carried out in accordance with The Code of Ethics of the World Medical Association (Declaration of Helsinki).

The dataset consists of 2D image slices extracted using the RadiAnt DICOM viewer software. The extracted images are transformed to DICOM image data format with a resolution of 256x256 pixels. There are a total of 179 2D axial image slices referring to 20 patient volumes (90 MR and 89 CT 2D axial image slices). The dataset contains MR and CT brain tumour images with corresponding segmentation masks. The MR images of each patient were acquired with a 5.00mm T Siemens Verio 3T using a T2-weighted without contrast agent, 3 Fat sat pulses (FS), 2500-4000 TR, 20-30 TE, and 90/180 flip angle. The CT images were acquired with Siemens Somatom scanner with 2.46mGY.cm dose length, 130KV voltage, 113-327 mAs tube current, topogram acquisition protocol, 64 dual source, one projection, and slice thickness of 7.0mm. Smooth and sharp filters have been applied to the CT images. The MR scans have a resolution of 0.7x0.6x5 mm^3, while the CT scans have a resolution of 0.6x0.6x7 mm^3.

More information and the application of the dataset can be found in the following research paper:

Alaa Abu-Srhan; Israa Almallahi; Mohammad Abushariah; Waleed Mahafza; Omar S. Al-Kadi. Paired-Unpaired Unsupervised Attention Guided GAN with Transfer Learning for Bidirectional Brain MR-CT Synthesis. Comput. Biol. Med. 136, 2021. doi: https://doi.org/10.1016/j.compbiomed.2021.104763.

约旦大学医院（Jordan University Hospital, JUH）的磁共振-计算机断层扫描（Magnetic Resonance-Computed Tomography, MR-CT）数据集，是在获得医院机构审查委员会（Institutional Review Board, IRB）批准后收集的，且已获取所有患者的知情同意书。所有操作均严格遵循世界医学协会《赫尔辛基宣言》的伦理准则。

该数据集通过RadiAnt DICOM（医学数字成像与通信，Digital Imaging and Communications in Medicine）查看器软件提取二维图像切片，并将提取的图像转换为分辨率为256×256像素的DICOM图像格式。数据集总计包含179张二维轴向图像切片，对应20例患者的影像数据，其中90张磁共振成像切片、89张计算机断层扫描轴向切片。本数据集包含脑肿瘤的磁共振与计算机断层扫描图像及对应的分割掩码。

每位患者的磁共振图像采用西门子Verio 3T磁共振扫描仪采集，序列为5.00mm层厚的T2加权非增强序列，搭配3次脂肪饱和（Fat sat, FS）脉冲，重复时间（Repetition Time, TR）为2500~4000ms，回波时间（Echo Time, TE）为20~30ms，翻转角为90°/180°。计算机断层扫描图像采用西门子Somatom扫描仪采集，剂量长度乘积为2.46mGy·cm，管电压为130kV，管电流为113~327mAs，采用定位像采集协议，配备64排双源探测器，单次投影，层厚为7.0mm。已对计算机断层扫描图像应用平滑滤波与锐利滤波算法。磁共振扫描的体素分辨率为0.7×0.6×5 mm³，计算机断层扫描的体素分辨率为0.6×0.6×7 mm³。

有关该数据集的更多信息与应用场景，可参阅以下研究论文：
Alaa Abu-Srhan、Israa Almallahi、Mohammad Abushariah、Waleed Mahafza、Omar S. Al-Kadi. 结合迁移学习的配对-非配对无监督注意力引导生成对抗网络（Generative Adversarial Network, GAN）用于双向脑MR-CT图像合成. 《计算机生物学与医学（Computers in Biology and Medicine）》，136卷，2021年. doi: https://doi.org/10.1016/j.compbiomed.2021.104763.

搜集汇总

背景与挑战

背景概述

该数据集是一个专门用于无监督图像翻译的未配对脑部MR-CT数据集，包含来自20名患者的179张2D轴向图像切片（90张MR和89张CT），每张图像均配有分割掩模。图像分辨率为256x256像素，以DICOM格式存储，采集自约旦大学医院，并遵循严格的伦理规范，适用于脑肿瘤图像合成和分割研究。