ALL-PET: A Low-resource and Low-shot PET Foundation Model in Projection Domain

• URL: http://arxiv.org/abs/2509.09130v2
• Date: Tue, 16 Sep 2025 09:11:53 GMT
• Title: ALL-PET: A Low-resource and Low-shot PET Foundation Model in Projection Domain
• Authors: Bin Huang, Kang Chen, Bingxuan Li, Huafeng Liu, Qiegen Liu,
• Abstract summary: ALL-PET is a low-resource, low-shot PET foundation model operating directly in projection domain.<n>It generates over 200,000 structurally diverse training samples by projecting randomized image-domain masks into sinogram space.<n>It generalizes across tasks including low-dose reconstruction, attenuation correction, delayed-frame prediction, and tracer separation, operating efficiently with memory use under 24GB.
• Score: 33.678018449132715
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Building large-scale foundation model for PET imaging is hindered by limited access to labeled data and insufficient computational resources. To overcome data scarcity and efficiency limitations, we propose ALL-PET, a low-resource, low-shot PET foundation model operating directly in projection domain. ALL-PET leverages a latent diffusion model (LDM) with three key innovations. First, we design a Radon mask augmentation strategy (RMAS) that generates over 200,000 structurally diverse training samples by projecting randomized image-domain masks into sinogram space, significantly improving generalization with minimal data. This is extended by a dynamic multi-mask (DMM) mechanism that varies mask quantity and distribution, enhancing data diversity without added model complexity. Second, we implement positive/negative mask constraints to embed strict geometric consistency, reducing parameter burden while preserving generation quality. Third, we introduce transparent medical attention (TMA), a parameter-free, geometry-driven mechanism that enhances lesion-related regions in raw projection data. Lesion-focused attention maps are derived from coarse segmentation, covering both hypermetabolic and hypometabolic areas, and projected into sinogram space for physically consistent guidance. The system supports clinician-defined ROI adjustments, ensuring flexible, interpretable, and task-adaptive emphasis aligned with PET acquisition physics. Experimental results show that ALL-PET achieves high-quality sinogram generation using only 500 samples, with performance comparable to models trained on larger datasets. ALL-PET generalizes across tasks including low-dose reconstruction, attenuation correction, delayed-frame prediction, and tracer separation, operating efficiently with memory use under 24GB.

Related papers

• MlPET: A Localized Neural Network Approach for Probabilistic Post-Reconstruction PET Image Analysis Using Informed Priors [0.0]
  We develop and evaluate MlPET, a fast localized machine learning approach for probabilistic PET image analysis.<n>MlPET replaces computationally demanding Markov chain Monte Carlo sampling with a localized neural network trained to estimate posterior mean voxel activity from small image neighborhoods.<n>Performance was evaluated on NEMA IEC phantom data from three PET systems.
  arXiv  Detail & Related papers  (2026-01-25T22:41:50Z)
• Supervised Diffusion-Model-Based PET Image Reconstruction [44.89560992517543]
  Diffusion models (DMs) have been introduced as a regularizing prior for PET image reconstruction.<n>We propose a supervised DM-based algorithm for PET reconstruction.<n>Our method enforces the non-negativity of PET's Poisson likelihood model and accommodates the wide intensity range of PET images.
  arXiv  Detail & Related papers  (2025-06-30T16:39:50Z)
• Personalized MR-Informed Diffusion Models for 3D PET Image Reconstruction [40.722159771726375]
  We propose a simple method for generating subject-specific PET images from a dataset of PET-MR scans.<n>The images we synthesize retain information from the subject's MR scan, leading to higher resolution and the retention of anatomical features.<n>With simulated and real [$18$F]FDG datasets, we show that pre-training a personalized diffusion model with subject-specific "pseudo-PET" images improves reconstruction accuracy with low-count data.
  arXiv  Detail & Related papers  (2025-06-04T10:24:14Z)
• Two-stage deep learning framework for the restoration of incomplete-ring PET images [0.6478690173421426]
  We present a two-stage deep-learning framework that restores high-quality images from data with about 50% missing coincidences.<n>We also achieve higher inference speed, thus providing an effective solution for incomplete-ring PET imaging.
  arXiv  Detail & Related papers  (2025-04-01T14:05:32Z)
• Posterior-Mean Denoising Diffusion Model for Realistic PET Image Reconstruction [0.7366405857677227]
  Posterior-Mean Denoising Diffusion Model (PMDM-PET) is a novel approach that builds upon a recently established mathematical theory.<n>PMDM-PET first obtained posterior-mean PET predictions under minimum mean square error (MSE), then optimally transports the distribution of them to the ground-truth PET images distribution.<n> Experimental results demonstrate that PMDM-PET not only generates realistic PET images with possible minimum distortion and optimal perceptual quality but also outperforms five recent state-of-the-art (SOTA) DL baselines in both qualitative visual inspection and quantitative pixel-wise metrics.
  arXiv  Detail & Related papers  (2025-03-11T15:33:50Z)
• Diffusion Transformer Meets Random Masks: An Advanced PET Reconstruction Framework [11.726122474828065]
  In this study, we pro-pose an advanced PET reconstruction framework called Diffusion tRansformer mEets rAndom Masks (DREAM)<n>To the best of our knowledge, this is the first work to integrate mask mechanisms into both the sinogram domain and the latent space.<n> Experimental results demonstrate that DREAM not only improves the overall quality of reconstructed PET images but also preserves critical clinical details.
  arXiv  Detail & Related papers  (2025-03-11T11:50:50Z)
• Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction [88.65168366064061]
  We introduce Discrete Denoising Posterior Prediction (DDPP), a novel framework that casts the task of steering pre-trained MDMs as a problem of probabilistic inference. Our framework leads to a family of three novel objectives that are all simulation-free, and thus scalable. We substantiate our designs via wet-lab validation, where we observe transient expression of reward-optimized protein sequences.
  arXiv  Detail & Related papers  (2024-10-10T17:18:30Z)
• Diffusion Transformer Model With Compact Prior for Low-dose PET Reconstruction [7.320877150436869]
  We propose a diffusion transformer model (DTM) guided by joint compact prior (JCP) to enhance the reconstruction quality of low-dose PET imaging. DTM combines the powerful distribution mapping abilities of diffusion models with the capacity of transformers to capture long-range dependencies. Our approach not only reduces radiation exposure risks but also provides a more reliable PET imaging tool for early disease detection and patient management.
  arXiv  Detail & Related papers  (2024-07-01T03:54:43Z)
• ConPET: Continual Parameter-Efficient Tuning for Large Language Models [65.48107393731861]
  Continual learning requires continual adaptation of models to newly emerging tasks. We propose Continual. Efficient Tuning (ConPET), a generalizable paradigm for. continual task adaptation of large language models.
  arXiv  Detail & Related papers  (2023-09-26T08:52:04Z)
• ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic Diffusion Models [69.9178140563928]
  Colonoscopy analysis is essential for assisting clinical diagnosis and treatment. The scarcity of annotated data limits the effectiveness and generalization of existing methods. We propose an Adaptive Refinement Semantic Diffusion Model (ArSDM) to generate colonoscopy images that benefit the downstream tasks.
  arXiv  Detail & Related papers  (2023-09-03T07:55:46Z)
• Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction [62.29541106695824]
  This paper presents a coarse-to-fine PET reconstruction framework that consists of a coarse prediction module (CPM) and an iterative refinement module (IRM) By delegating most of the computational overhead to the CPM, the overall sampling speed of our method can be significantly improved. Two additional strategies, i.e., an auxiliary guidance strategy and a contrastive diffusion strategy, are proposed and integrated into the reconstruction process.
  arXiv  Detail & Related papers  (2023-08-20T04:10:36Z)
• TransRPPG: Remote Photoplethysmography Transformer for 3D Mask Face Presentation Attack Detection [53.98866801690342]
  3D mask face presentation attack detection (PAD) plays a vital role in securing face recognition systems from 3D mask attacks. We propose a pure r transformer (TransR) framework for learning live intrinsicness representation efficiently. Our TransR is lightweight and efficient (with only 547K parameters and 763MOPs) which is promising for mobile-level applications.
  arXiv  Detail & Related papers  (2021-04-15T12:33:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.