{"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/fast-gpu-enabled-color-normalization-for","title":"Fast GPU-Enabled Color Normalization for Digital Pathology","arxiv_id":"1901.03088","date":"2019-01-10","proceeding":null,"authors":["Goutham Ramakrishnan","Deepak Anand","Amit Sethi"],"abstract":"Normalizing unwanted color variations due to differences in staining\nprocesses and scanner responses has been shown to aid machine learning in\ncomputational pathology. Of the several popular techniques for color\nnormalization, structure preserving color normalization (SPCN) is\nwell-motivated, convincingly tested, and published with its code base. However,\nSPCN makes occasional errors in color basis estimation leading to artifacts\nsuch as swapping the color basis vectors between stains or giving a colored\ntinge to the background with no tissue. We made several algorithmic\nimprovements to remove these artifacts. Additionally, the original SPCN code is\nnot readily usable on gigapixel whole slide images (WSIs) due to long run\ntimes, use of proprietary software platform and libraries, and its inability to\nautomatically handle WSIs. We completely rewrote the software such that it can\nautomatically handle images of any size in popular WSI formats. Our software\nutilizes GPU-acceleration and open-source libraries that are becoming\nubiquitous with the advent of deep learning. We also made several other small\nimprovements and achieved a multifold overall speedup on gigapixel images. Our\nalgorithm and software is usable right out-of-the-box by the computational\npathology community.","url_abs":"http://arxiv.org/abs/1901.03088v1","url_pdf":"http://arxiv.org/pdf/1901.03088v1.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":"fast-gpu-enabled-color-normalization-for","repo_url":"https://github.com/MEDAL-IITB/Fast_WSI_Color_Norm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"color-normalization","task_name":"Color Normalization"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"whole-slide-images","task_name":"whole slide images"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}