+高级检索
基于MD-CGAN的脑部肿瘤图像生成方法研究
DOI:
作者:
作者单位:

作者简介:

通讯作者:

基金项目:


Research on Brain Tumor Image Generation Method Based on MD-CGAN
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    深度学习已广泛用于脑部磁共振(MR)图像分析中,但脑部肿瘤MR图像样本不足 会严重影响深度学习模型的性能 . 提出基于多鉴别器循环一致性生成对抗网络(MD-CGAN) 的样本生成方法 . 利用所提出的 MD-CGAN 生成脑部肿瘤病理区域图像,将生成的脑部肿瘤 病理区域图像覆盖脑部正常图像子区域,合成得到脑部肿瘤MR图像. MD-CGAN引入的双对 抗损失避免了模型崩塌问题的产生,引入的循环一致性损失函数可以保证脑部正常子区域图 像生成脑部肿瘤病理区域图像,从而使得MD-CGAN生成的图像具有高质量和多样性. 以FID 值作为评价指标,利用本文提出的MD-CGAN与近几年较经典的生成网络生成脑部肿瘤病理 区域图像并计算FID值. 实验结果表明,本文所提出网络的FID值比SAGAN、StyleGAN和Style? GAN2的值分别低26.43%、21.91%、12.78%. 为进一步验证本文方法的有效性,利用生成的脑部 肿瘤图像扩充样本,并依托扩充前后的样本集进行脑部肿瘤分割网络训练. 实验表明,样本扩 充后的分割网络性能更优异. 本文方法生成的脑部肿瘤MR图像质量高、多样性强,这些样本可 代替真实样本参与模型的训练,从而有效解决脑部肿瘤MR图像训练样本不足的问题.

    Abstract:

    The samples are insufficient due to the difficulty of obtaining real brain tumor MR images, which se? riously affects the performance of deep learning models. Therefore, a sample generation method based on the Multiple Discriminator Cycle-consistent Generative Adversarial Network (MD-CGAN) is proposed in this paper. Firstly, the MD-CGAN model is used to generate brain tumor pathological region images, and then these pathological region im? ages are overlaid with the normal sub-regions of brain images to synthesize brain tumor MR images. Among them, the double adversarial loss introduced by MD-CGAN avoids the problem of model collapse, and the cycle consistency loss function introduced can ensure that the normal brain sub-region images generate the pathological region images of brain tumors, so that the images generated by MD-CGAN have high quality and diversity. Taking the Fréchet In? ception Distance(FID) as the evaluation index, the MD-CGAN proposed in this paper and the more classic generative networks in recent years are used to generate the images of brain tumor pathological regions and calculate the FID value. The experimental results show that the FID of our MD-CGAN is 26.43%, 21.91%, and 12.78% lower than those of SAGAN, StyleGAN, and StyleGAN2, respectively. To further demonstrate the effectiveness of our proposed method, we use the generated brain tumor images to expand the training set and then train the segmentation models on this expanded dataset. The experimental results show that the performance of segmentation networks trained on the expanded dataset is better. Based on the above experimental results, it can be concluded that the brain tumor MR images generated by our proposed method have high quality and rich diversity. These samples can be used to expand the training set and effectively solve the problem that brain tumor MR images are insufficient.

    参考文献
    相似文献
    引证文献
文章指标
  • PDF下载次数:
  • HTML阅读次数:
  • 摘要点击次数:
  • 引用次数:
引用本文

何敏 ,邱圆 ,易小平 ,郭畅宇 .基于MD-CGAN的脑部肿瘤图像生成方法研究[J].湖南大学学报:自然科学版,2022,49(8):179~185

复制
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2022-09-07
  • 出版日期:
版权声明:稿件一经被本刊录用,即视为作者将版权授予本刊,本刊有权根据工作需要,允许合作的数据库、新媒体平台及其他媒体进行二次转载、推介、下载和传播,如有异议,请在来稿中声明。
关闭