{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bci-breast-cancer-immunohistochemical-image","title":"BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix","arxiv_id":"2204.11425","date":"2022-04-25","proceeding":null,"authors":["ShengJie Liu","Chuang Zhu","Feng Xu","Xinyu Jia","Zhongyue Shi","Mulan Jin"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2204.11425v2","url_pdf":"https://arxiv.org/pdf/2204.11425v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bci-breast-cancer-immunohistochemical-image","repo_url":"https://github.com/bupt-ai-cz/BCI","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"breast-cancer-detection","task_name":"Breast Cancer Detection"},{"task_slug":"breast-cancer-histology-image-classification","task_name":"Breast Cancer Histology Image Classification"},{"task_slug":"classification-of-breast-cancer-histology","task_name":"Classification Of Breast Cancer Histology Images"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"medical-diagnosis","task_name":"Medical Diagnosis"},{"task_slug":"medical-image-generation","task_name":"Medical Image Generation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"patchgan","method_name":"PatchGAN"},{"method_slug":"pix2pix","method_name":"Pix2Pix"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"}],"datasets_introduced":[{"slug":"bci","name":"BCI","full_name":"Breast Cancer Immunohistochemical Image Generation"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-to-image-translation-on-bci","task":"Image-to-Image Translation","dataset":"BCI","model":"pyramidpix2pix","rank_in_archive_order":1,"of":4,"metrics":{"Average PSNR":"21.160","SSIM":"0.477"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-bci","task":"Image-to-Image Translation","dataset":"BCI","model":"pix2pixHD","rank_in_archive_order":2,"of":4,"metrics":{"Average PSNR":"19.634","SSIM":"0.471"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-bci","task":"Image-to-Image Translation","dataset":"BCI","model":"pix2pix","rank_in_archive_order":3,"of":4,"metrics":{"Average PSNR":"19.328","SSIM":"0.440"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-bci","task":"Image-to-Image Translation","dataset":"BCI","model":"cycleGAN","rank_in_archive_order":4,"of":4,"metrics":{"Average PSNR":"16.203","SSIM":"0.373"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-flir","task":"Image-to-Image Translation","dataset":"FLIR","model":"BCI","rank_in_archive_order":3,"of":4,"metrics":{"PSNR":"11.14","SSIM":"0.21"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-llvip","task":"Image-to-Image Translation","dataset":"LLVIP","model":"pyramidpix2pix","rank_in_archive_order":1,"of":4,"metrics":{"PSNR":"12.191","SSIM":"0.278"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-llvip","task":"Image-to-Image Translation","dataset":"LLVIP","model":"cycleGAN","rank_in_archive_order":2,"of":4,"metrics":{"PSNR":"11.22","SSIM":"0.214"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-llvip","task":"Image-to-Image Translation","dataset":"LLVIP","model":"pix2pixHD","rank_in_archive_order":3,"of":4,"metrics":{"PSNR":"11.156","SSIM":"0.228"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2204.11425","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}