<a href=\"https://cdn-uploads.huggingface.co/production/uploads/638a2bdb34cf0480e9abd6a4/GQX8_b66oggMAMlpoDyDH.png\" rel=\"nofollow\"><img src=\"https://cdn-uploads.huggingface.co/production/uploads/638a2bdb34cf0480e9abd6a4/GQX8_b66oggMAMlpoDyDH.png\" alt=\"framework\"></a></p>\n","updatedAt":"2026-06-10T07:07:52.978Z","author":{"_id":"638a2bdb34cf0480e9abd6a4","avatarUrl":"/avatars/70e84c5c188688db8b29455061a410a1.svg","fullname":"Zhiwen Yang","name":"upyzwup","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":0,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.4021143317222595},"editors":["upyzwup"],"editorAvatarUrls":["/avatars/70e84c5c188688db8b29455061a410a1.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.11032","authors":[{"_id":"6a28dbd9e7d78ea7587e54b7","name":"Zhiwen Yang","hidden":false},{"_id":"6a28dbd9e7d78ea7587e54b8","name":"Jiayin Li","hidden":false},{"_id":"6a28dbd9e7d78ea7587e54b9","name":"Hao Lu","hidden":false},{"_id":"6a28dbd9e7d78ea7587e54ba","name":"Hui Zhang","hidden":false},{"_id":"6a28dbd9e7d78ea7587e54bb","name":"Zihua Wang","hidden":false},{"_id":"6a28dbd9e7d78ea7587e54bc","name":"Bingzheng Wei","hidden":false},{"_id":"6a28dbd9e7d78ea7587e54bd","name":"Yan Xu","hidden":false}],"publishedAt":"2026-06-09T00:00:00.000Z","submittedOnDailyAt":"2026-06-10T00:00:00.000Z","title":"U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training","submittedOnDailyBy":{"_id":"638a2bdb34cf0480e9abd6a4","avatarUrl":"/avatars/70e84c5c188688db8b29455061a410a1.svg","isPro":false,"fullname":"Zhiwen Yang","user":"upyzwup","type":"user","name":"upyzwup"},"summary":"Existing deep learning models for Positron Emission Tomography (PET) image denoising often suffer from severe performance degradation under distribution shifts, fundamentally restricting their robust clinical deployment. This lack of generalization stems from the conventional paradigm of fixed-parameter models that cannot adapt to variations in test data (e.g., dose levels or scanner types) after training. To overcome this limitation and achieve robust generalization, we introduce U-TTT, a novel U-shaped model that integrates Test-Time Training (TTT) layers to dynamically adjust model parameters during inference through self-supervision, thereby adapting to the specific characteristics of each test instance. Furthermore, to comprehensively capture the complex degradations of 3D PET data, U-TTT features a dual-domain adaptation mechanism comprising a Spatial Test-Time Training (S-TTT) layer and a Frequency Test-Time Training (F-TTT) layer. The S-TTT layer captures and corrects spatial structural degradations, while the F-TTT layer suppresses global noise spectra and restores delicate high-frequency details. Extensive experiments demonstrate that U-TTT achieves state-of-the-art PET denoising performance and exhibits superior generalization under challenging distribution shifts, including both unseen dose levels and unseen scanners. Our code will be available at https://github.com/Yaziwel/U-TTT.","upvotes":4,"discussionId":"6a28dbd9e7d78ea7587e54be","githubRepo":"https://github.com/Yaziwel/U-TTT","githubRepoAddedBy":"user","ai_summary":"A novel U-shaped deep learning model with test-time training layers and dual-domain adaptation mechanisms achieves robust PET image denoising under distribution shifts.","ai_keywords":["Positron Emission Tomography","denoising","distribution shifts","fixed-parameter models","Test-Time Training","self-supervision","U-shaped model","dual-domain adaptation","Spatial Test-Time Training","Frequency Test-Time Training","spatial structural degradations","global noise spectra","high-frequency details"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","githubStars":2},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"638a2bdb34cf0480e9abd6a4","avatarUrl":"/avatars/70e84c5c188688db8b29455061a410a1.svg","isPro":false,"fullname":"Zhiwen Yang","user":"upyzwup","type":"user"},{"_id":"668d4893891640bf32158d25","avatarUrl":"/avatars/4d7b283739d28b81e3d60238b595260d.svg","isPro":false,"fullname":"Hao Lu","user":"LH2002","type":"user"},{"_id":"69072c56fbacae33889abb54","avatarUrl":"/avatars/e52e1fe8f11f1e939986dcec92f1ba92.svg","isPro":false,"fullname":"Li Jiayin","user":"LiJiayin9898","type":"user"},{"_id":"663f9abd9cb0add00bcd806a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/663f9abd9cb0add00bcd806a/Fq_MGUdRcfYlNnTPLVt7i.png","isPro":false,"fullname":"Zichun25BUAA","user":"zichun101","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.11032.md"}">
U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training
Abstract
A novel U-shaped deep learning model with test-time training layers and dual-domain adaptation mechanisms achieves robust PET image denoising under distribution shifts.
Existing deep learning models for Positron Emission Tomography (PET) image denoising often suffer from severe performance degradation under distribution shifts, fundamentally restricting their robust clinical deployment. This lack of generalization stems from the conventional paradigm of fixed-parameter models that cannot adapt to variations in test data (e.g., dose levels or scanner types) after training. To overcome this limitation and achieve robust generalization, we introduce U-TTT, a novel U-shaped model that integrates Test-Time Training (TTT) layers to dynamically adjust model parameters during inference through self-supervision, thereby adapting to the specific characteristics of each test instance. Furthermore, to comprehensively capture the complex degradations of 3D PET data, U-TTT features a dual-domain adaptation mechanism comprising a Spatial Test-Time Training (S-TTT) layer and a Frequency Test-Time Training (F-TTT) layer. The S-TTT layer captures and corrects spatial structural degradations, while the F-TTT layer suppresses global noise spectra and restores delicate high-frequency details. Extensive experiments demonstrate that U-TTT achieves state-of-the-art PET denoising performance and exhibits superior generalization under challenging distribution shifts, including both unseen dose levels and unseen scanners. Our code will be available at https://github.com/Yaziwel/U-TTT.
Community
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2606.11032 in a model README.md to link it from this page.
Cite arxiv.org/abs/2606.11032 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2606.11032 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.