In the diagnosis of neurodegenerative disorders, F-18 fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) is used for its ability to detect functional changes at early stages of disease process. However, anatomical information from another modality (CT or MRI) is still needed to properly interpret and localize the radiotracer uptake due to its low spatial resolution. Lack of structural information limits segmentation and accurate quantification of the ¹⁸F-FDG PET/CT. The correct segmentation of the brain compartment in ¹⁸F-FDG PET/CT will enable the quantitative analysis of the ¹⁸F-FDG PET/CT scan alone. In this paper, we propose a method to segment white matter in ¹⁸F-FDG PET/CT images using generative adversarial network (GAN). The segmentation result of GAN model was evaluated using evaluation parameters such as dice, AUC-PR, precision, and recall. It was also compared with other deep learning methods. As a result, the proposed method achieves superior segmentation accuracy and reliability compared with other deep learning methods.

在神经退行性疾病的诊断中，F-18 氟脱氧葡萄糖正电子发射断层扫描/计算机断层扫描 ( ¹⁸ F-FDG PET/CT) 因其能够检测疾病过程早期阶段的功能变化而被使用。然而，由于空间分辨率低，仍然需要来自另一种方式（CT 或 MRI）的解剖信息来正确解释和定位放射性示踪剂摄取。缺乏结构信息限制了¹⁸ F-FDG PET/CT 的分割和准确量化。在¹⁸ F-FDG PET/CT 中正确分割脑隔室将能够单独对¹⁸ F-FDG PET/CT 扫描进行定量分析。在本文中，我们提出了一种在^{18 个区域中}分割白质的方法使用生成对抗网络 (GAN) 的 F-FDG PET/CT 图像。使用骰子、AUC-PR、精度、召回率等评价参数对GAN模型的分割结果进行评价。它还与其他深度学习方法进行了比较。因此，与其他深度学习方法相比，所提出的方法实现了卓越的分割精度和可靠性。