{"id":1180651,"date":"2026-08-03T08:09:24","date_gmt":"2026-08-03T15:09:24","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/gigapath-flash-and-gigatime-flash-efficient-pathology-foundation-models-for-whole-slide-and-tumor-microenvironment-analysis\/"},"modified":"2026-08-05T16:04:08","modified_gmt":"2026-08-05T23:04:08","slug":"gigapath-flash-and-gigatime-flash-efficient-pathology-foundation-models-for-whole-slide-and-tumor-microenvironment-analysis","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/gigapath-flash-and-gigatime-flash-efficient-pathology-foundation-models-for-whole-slide-and-tumor-microenvironment-analysis\/","title":{"rendered":"GigaPath-Flash and GigaTIME-Flash: Efficient Pathology Foundation Models for Whole-Slide and Tumor Microenvironment Analysis"},"content":{"rendered":"\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Foundation models have emerged as a driving force in computational pathology, with the potential to transform cancer diagnosis, prognosis, and treatment selection by learning transferable representations from large-scale histopathology data. A growing landscape of pathology foundation models now spans diverse data sources, architectures, and downstream applications. However, most pretrained models operate only at the image-tile level, use restrictive licenses, and remain computationally expensive, limiting large-scale slide-level clinical and research use. Here, we introduce GigaPath-Flash and GigaTIME-Flash, efficient models for whole-slide pathology AI and spatial proteomics prediction. GigaPath-Flash combines a 22M-parameter ViT-S tile encoder with a 21M-parameter LongNet slide encoder, both pretrained on large-scale real-world histopathology data. Its compact tile encoder is distilled from the billion-parameter GigaPath (ViT-g) teacher and shared by both models. GigaPath-Flash retains 97% of GigaPath&#8217;s average slide-level performance with 50x less compute. GigaTIME-Flash extends this backbone to predict the tumor immune microenvironment directly from routine H&E images. It surpasses the original CNN-based GigaTIME in prediction quality while running 6x faster and using 8x less GPU memory. Together with GigaPath and GigaTIME, these models form an open-weight, Apache-2.0-licensed family pretrained on large-scale real-world clinical data. By releasing all models and weights, we provide accessible building blocks for computational pathology, immuno-oncology, and precision health.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Foundation models have emerged as a driving force in computational pathology, with the potential to transform cancer diagnosis, prognosis, and treatment selection by learning transferable representations from large-scale histopathology data. A growing landscape of pathology foundation models now spans diverse data sources, architectures, and downstream applications. However, most pretrained models operate only at the image-tile [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":[{"type":"user_nicename","value":"Naoto Usuyama","user_id":"38670"},{"type":"user_nicename","value":"Jeya Maria Jose Valanarasu","user_id":"43491"},{"type":"text","value":"Sicong Yao","user_id":0},{"type":"text","value":"Hanwen Xu","user_id":0},{"type":"text","value":"Jaspreet Bagga","user_id":0},{"type":"user_nicename","value":"Guanghui Qin","user_id":"43527"},{"type":"text","value":"Robert E. Kramer","user_id":0},{"type":"user_nicename","value":"Cliff Wong","user_id":"38508"},{"type":"text","value":"Soohee Lee","user_id":0},{"type":"text","value":"Hao Qiu","user_id":0},{"type":"text","value":"T. Zhao","user_id":0},{"type":"text","value":"Racheli Ben Shimol","user_id":0},{"type":"text","value":"Angela Crabtree","user_id":0},{"type":"text","value":"K. Matlock","user_id":0},{"type":"text","value":"Eduardo Alejandro Lozano Garcia","user_id":0},{"type":"user_nicename","value":"Naiteek Sangani","user_id":"43887"},{"type":"user_nicename","value":"Alberto Santamaria-Pang","user_id":"43863"},{"type":"user_nicename","value":"Jason Entenmann","user_id":"42453"},{"type":"text","value":"Alexandra Q. Bartlett","user_id":0},{"type":"text","value":"Bill J. Wright","user_id":0},{"type":"text","value":"Bernard A. Fox","user_id":0},{"type":"text","value":"B. Piening","user_id":0},{"type":"user_nicename","value":"Sheng Zhang","user_id":"39087"},{"type":"text","value":"Sheng Wang","user_id":0},{"type":"user_nicename","value":"Tristan Naumann","user_id":"37929"},{"type":"text","value":"Carlo Bifulco","user_id":0},{"type":"user_nicename","value":"Hoifung Poon","user_id":"32016"}],"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"arXiv","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"","msr_doi":"","msr_arxiv_id":"2607.18218","msr_mag_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_release_tracker_id":"","msr_highlight_type":"","msr_date_display_format":"","msr_main_download_label":"","msr_external_link_label":"","msr_doi_label":"","msr_published_date":"2026-07-20","msr_startdate":"","msr_presentation_date":"","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_year":2026,"msr_month":7,"msr_day":20,"msr_microsoftintellectualproperty":false,"msr_pub_id":"31e69c8203b56ab6ad06a62f2e316e4dd016de8a","msr_publication_uploader":[{"type":"url","title":"https:\/\/arxiv.org\/abs\/2607.18218","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_original_fields_of_study":[],"msr_s2_paper_id":"31e69c8203b56ab6ad06a62f2e316e4dd016de8a","msr_s2_pdf_url":"","msr_citation_count_updated":"","msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":16,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[{"provider":"s2","id":"31e69c8203b56ab6ad06a62f2e316e4dd016de8a"},{"provider":"arxiv","id":"2607.18218"},{"provider":"corpusid","id":"290378319"}],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13562,13553],"msr-publication-type":[270373],"msr-publisher":[],"msr-publication-cta":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[256039,246691,263185],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1180651","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-computer-vision","msr-research-area-medical-health-genomics","msr-locale-en_us","msr-field-of-study-artifcial-intelligence","msr-field-of-study-computer-science","msr-field-of-study-computer-vision-and-pattern-recognition"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2026-07-20","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"arXiv","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":0,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","title":"https:\/\/arxiv.org\/abs\/2607.18218","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"31e69c8203b56ab6ad06a62f2e316e4dd016de8a","msr_influential_citations":0,"msr_reference_count":16,"msr_arxiv_id":"2607.18218","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"user_nicename","value":"Naoto Usuyama","user_id":38670,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Naoto Usuyama"},{"type":"user_nicename","value":"Jeya Maria Jose Valanarasu","user_id":43491,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jeya Maria Jose Valanarasu"},{"type":"text","value":"Sicong Yao","user_id":0,"rest_url":false},{"type":"text","value":"Hanwen Xu","user_id":0,"rest_url":false},{"type":"text","value":"Jaspreet Bagga","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Guanghui Qin","user_id":43527,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Guanghui Qin"},{"type":"text","value":"Robert E. Kramer","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Cliff Wong","user_id":38508,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Cliff Wong"},{"type":"text","value":"Soohee Lee","user_id":0,"rest_url":false},{"type":"text","value":"Hao Qiu","user_id":0,"rest_url":false},{"type":"text","value":"T. Zhao","user_id":0,"rest_url":false},{"type":"text","value":"Racheli Ben Shimol","user_id":0,"rest_url":false},{"type":"text","value":"Angela Crabtree","user_id":0,"rest_url":false},{"type":"text","value":"K. Matlock","user_id":0,"rest_url":false},{"type":"text","value":"Eduardo Alejandro Lozano Garcia","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Naiteek Sangani","user_id":43887,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Naiteek Sangani"},{"type":"user_nicename","value":"Alberto Santamaria-Pang","user_id":43863,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Alberto Santamaria-Pang"},{"type":"user_nicename","value":"Jason Entenmann","user_id":42453,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jason Entenmann"},{"type":"text","value":"Alexandra Q. Bartlett","user_id":0,"rest_url":false},{"type":"text","value":"Bill J. Wright","user_id":0,"rest_url":false},{"type":"text","value":"Bernard A. Fox","user_id":0,"rest_url":false},{"type":"text","value":"B. Piening","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Sheng Zhang","user_id":39087,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Sheng Zhang"},{"type":"text","value":"Sheng Wang","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Tristan Naumann","user_id":37929,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Tristan Naumann"},{"type":"text","value":"Carlo Bifulco","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Hoifung Poon","user_id":32016,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Hoifung Poon"}],"msr_impact_theme":[],"msr_research_lab":[849856],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"misc","related_content":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1180651","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":3,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1180651\/revisions"}],"predecessor-version":[{"id":1180908,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1180651\/revisions\/1180908"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1180651"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1180651"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1180651"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1180651"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1180651"},{"taxonomy":"msr-publication-cta","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-cta?post=1180651"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1180651"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1180651"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1180651"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1180651"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1180651"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1180651"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1180651"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1180651"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}