Virtual Interpolation Images of Tumor Development and Growth on Breast Ultrasound Image Synthesis With Deep Convolutional Generative Adversarial Networks
Virtual Interpolation Images of Tumor Development and Growth on Breast Ultrasound Image Synthesis With Deep Convolutional Generative Adversarial Networks
复制标题
DOI：
10.1002/jum.15376
复制
发表时间：
2020-06-27
影响因子：
2.3
通讯作者：
Tateishi, Ukihide
中科院分区：
文献类型：
--
作者：
Fujioka, Tomoyuki;Kubota, Kazunori;Tateishi, Ukihide
目的利用深度卷积生成对抗性网络(DCGAN)生成逼真的合成乳腺超声图像和表达肿瘤的虚拟内插图像。方法对528例良性乳腺肿块、529例恶性乳腺肿块和583例正常乳腺的超声图像进行回顾性筛选，用DCGAN分别生成20幅合成图像。通过改变输入向量的值，生成了15幅虚拟的肿瘤内插图像。共有60幅合成图像和20幅虚拟内插图像由2名读者进行评估，他们按5分制(1分，非常好；5分，非常差)对它们进行评分，然后回答合成图像是良性、恶性还是正常。结果合成图像总体质量平均为3.05分，虚拟插补图像真实感平均为2.53分。读者对生成的图像进行了分类，正确答对率为92.5%。结论DCGAN可生成每个病变组织的高质量合成乳腺超声图像，并具有创建逼真的肿瘤发展的虚拟内插图像的潜力。
Objectives We sought to generate realistic synthetic breast ultrasound images and express virtual interpolation images of tumors using a deep convolutional generative adversarial network (DCGAN). Methods After retrospective selection of breast ultrasound images of 528 benign masses, 529 malignant masses, and 583 normal breasts, 20 synthesized images of each were generated by the DCGAN. Fifteen virtual interpolation images of tumors were generated by changing the value of the input vector. A total of 60 synthesized images and 20 virtual interpolation images were evaluated by 2 readers, who scored them on a 5-point scale (1, very good; to 5, very poor) and then answered whether the synthesized image was benign, malignant, or normal. Results The mean score of overall quality for synthesized images was 3.05, and that of the reality of virtual interpolation images was 2.53. The readers classified the generated images with a correct answer rate of 92.5%. Conclusions A DCGAN can generate high-quality synthetic breast ultrasound images of each pathologic tissue and has the potential to create realistic virtual interpolation images of tumor development.