BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix

25 Apr 2022  ·  ShengJie Liu, Chuang Zhu, Feng Xu, Xinyu Jia, Zhongyue Shi, Mulan Jin ·

The evaluation of human epidermal growth factor receptor 2 (HER2) expression is essential to formulate a precise treatment for breast cancer. The routine evaluation of HER2 is conducted with immunohistochemical techniques (IHC), which is very expensive. Therefore, for the first time, we propose a breast cancer immunohistochemical (BCI) benchmark attempting to synthesize IHC data directly with the paired hematoxylin and eosin (HE) stained images. The dataset contains 4870 registered image pairs, covering a variety of HER2 expression levels. Based on BCI, as a minor contribution, we further build a pyramid pix2pix image generation method, which achieves better HE to IHC translation results than the other current popular algorithms. Extensive experiments demonstrate that BCI poses new challenges to the existing image translation research. Besides, BCI also opens the door for future pathology studies in HER2 expression evaluation based on the synthesized IHC images. BCI dataset can be downloaded from https://bupt-ai-cz.github.io/BCI.

PDF Abstract


Introduced in the Paper:


Used in the Paper:


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image-to-Image Translation BCI cycleGAN Average PSNR 16.203 # 4
SSIM 0.373 # 4
Image-to-Image Translation BCI pix2pixHD Average PSNR 19.634 # 2
SSIM 0.471 # 2
Image-to-Image Translation BCI pix2pix Average PSNR 19.328 # 3
SSIM 0.440 # 3
Image-to-Image Translation BCI pyramidpix2pix Average PSNR 21.160 # 1
SSIM 0.477 # 1
Image-to-Image Translation LLVIP pyramidpix2pix PSNR 12.191 # 1
SSIM 0.278 # 1
Image-to-Image Translation LLVIP cycleGAN PSNR 11.22 # 2
SSIM 0.214 # 3
Image-to-Image Translation LLVIP pix2pixHD PSNR 11.156 # 3
SSIM 0.228 # 2