中文标题#
虚拟 DES 图像是否是真实图像的有效替代品?
英文标题#
Are Virtual DES Images a Valid Alternative to the Real Ones?
中文摘要#
对比增强光谱乳腺摄影(CESM)是一种成像方式,提供两种类型的图像,通常称为低能(LE)图像和双能减影(DES)图像。 在许多领域,尤其是在医学中,图像到图像的翻译技术的出现使得可以使用其他图像作为输入来人工生成图像。 在 CESM 中,将这些技术应用于从 LE 图像生成 DES 图像可能非常有益,可能会减少与高能图像采集相关的患者辐射暴露。 在本研究中,我们调查了三种用于人工生成 DES 图像(虚拟 DES)的模型:一个预训练的 U-Net 模型、一个端到端训练的 U-Net 模型以及一个 CycleGAN 模型。 我们还进行了一系列实验,以评估使用虚拟 DES 图像对 CESM 检查分类为恶性和非恶性类别的影响。 据我们所知,这是第一项评估虚拟 DES 图像对 CESM 病灶分类影响的研究。 结果表明,使用虚拟 DES 图像时,最佳性能由预训练的 U-Net 模型实现,F1 得分为 85.59%,而使用真实 DES 图像时为 90.35%。 这种差异可能是由于真实 DES 图像中的额外诊断信息,这有助于更高的分类准确性。 然而,虚拟 DES 图像生成的潜力是巨大的,未来的进步可能会缩小这一性能差距,使其达到仅依赖虚拟 DES 图像在临床上可行的水平。
英文摘要#
Contrast-enhanced spectral mammography (CESM) is an imaging modality that provides two types of images, commonly known as low-energy (LE) and dual-energy subtracted (DES) images. In many domains, particularly in medicine, the emergence of image-to-image translation techniques has enabled the artificial generation of images using other images as input. Within CESM, applying such techniques to generate DES images from LE images could be highly beneficial, potentially reducing patient exposure to radiation associated with high-energy image acquisition. In this study, we investigated three models for the artificial generation of DES images (virtual DES): a pre-trained U-Net model, a U-Net trained end-to-end model, and a CycleGAN model. We also performed a series of experiments to assess the impact of using virtual DES images on the classification of CESM examinations into malignant and non-malignant categories. To our knowledge, this is the first study to evaluate the impact of virtual DES images on CESM lesion classification. The results demonstrate that the best performance was achieved with the pre-trained U-Net model, yielding an F1 score of 85.59% when using the virtual DES images, compared to 90.35% with the real DES images. This discrepancy likely results from the additional diagnostic information in real DES images, which contributes to a higher classification accuracy. Nevertheless, the potential for virtual DES image generation is considerable and future advancements may narrow this performance gap to a level where exclusive reliance on virtual DES images becomes clinically viable.
文章页面#
PDF 获取#
抖音扫码查看更多精彩内容