{"id":3247,"date":"2025-08-04T12:28:01","date_gmt":"2025-08-04T12:28:01","guid":{"rendered":"http:\/\/www.labren.org\/mm\/?p=3247"},"modified":"2025-08-05T12:57:36","modified_gmt":"2025-08-05T12:57:36","slug":"%f0%9f%9b%a0%ef%b8%8f-introducing-cat-sd-privacy-centric-ai-in-robotic-surgery-%f0%9f%a4%96","status":"publish","type":"post","link":"http:\/\/www.labren.org\/mm\/news\/%f0%9f%9b%a0%ef%b8%8f-introducing-cat-sd-privacy-centric-ai-in-robotic-surgery-%f0%9f%a4%96\/","title":{"rendered":"\ud83d\udee0\ufe0f Introducing CAT-SD: Privacy-Centric AI in Robotic Surgery \ud83e\udd16"},"content":{"rendered":"\n

In our recent work, “Privacy-Preserving Synthetic Continual Semantic Segmentation for Robotic Surgery”, which was published in IEEE Transactions on Medical Imaging, we propose a state-of-the-art framework for continual semantic segmentation in robotic surgery. This breakthrough addresses catastrophic forgetting in DNNs, enhancing surgical precision without compromising patient privacy.<\/p>\n\n\n\n

\ud83d\udd12 Privacy-First Synthetic Data: We’ve crafted a solution that blends open-source instrument data with synthesized backgrounds, ensuring real patient data remains confidential.<\/p>\n\n\n\n

\ud83d\udca1 Innovative Features:<\/p>\n\n\n\n

– Class-Aware Temperature Normalization (CAT) to prevent forgetting of previously learned tasks.<\/p>\n\n\n\n

– Multi-Scale Shifted-Feature Distillation (SD) to preserve spatial relationships for robust feature learning.<\/p>\n\n\n\n

Check the paper at https:\/\/lnkd.in\/eTy8KAC5<\/p>\n\n\n\n

Code is also available at https:\/\/lnkd.in\/eMzNs2Be<\/p>\n\n\n\n

Co-authors: Mengya Xu<\/a>, Mobarakol Islam<\/a>, Long Bai<\/a>, Hongliang Ren<\/a><\/p>\n\n\n\n

\"No<\/figure>\n\n\n\n
\"No<\/figure>\n\n\n\n
\"No<\/figure>\n\n\n\n
\"No<\/figure>\n","protected":false},"excerpt":{"rendered":"

In our recent work, “Privacy-Preserving Synthetic Continual Semantic Segmentation for Robotic Surgery”, which was published in IEEE Transactions on Medical Imaging, we propose a state-of-the-art framework for continual semantic segmentation in robotic surgery. This breakthrough addresses catastrophic forgetting in DNNs, enhancing surgical precision without compromising patient privacy. \ud83d\udd12 Privacy-First Synthetic\u2026 Continue reading<\/a><\/p>\n","protected":false},"author":17,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ngg_post_thumbnail":0,"footnotes":""},"categories":[4],"tags":[119,120,118],"class_list":["post-3247","post","type-post","status-publish","format-standard","hentry","category-news","tag-continuallearning","tag-roboticsurgery","tag-surgicalai"],"_links":{"self":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts\/3247","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/users\/17"}],"replies":[{"embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/comments?post=3247"}],"version-history":[{"count":1,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts\/3247\/revisions"}],"predecessor-version":[{"id":3248,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts\/3247\/revisions\/3248"}],"wp:attachment":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/media?parent=3247"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/categories?post=3247"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/tags?post=3247"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}