MUST-PET: MUltimodal Self-supervised learning across Tracers for whole-body PET/CT-based lesion segmentation

• URL: http://arxiv.org/abs/2608.19666v1
• Date: Thu, 20 Aug 2026 06:02:54 GMT
• Title: MUST-PET: MUltimodal Self-supervised learning across Tracers for whole-body PET/CT-based lesion segmentation
• Abstract summary: MUST-PET is a multimodal, multi-tracer SSL framework for generalizable whole-body PET-CT lesion segmentation.<n>It reduces reconstruction error, improves lesion segmentation over training from scratch, and performs well with limited labeled data.
• Score: 2.779944317864993
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning-based whole-body PET-CT lesion segmentation can support cancer staging, treatment planning, and response assessment, but generalization is limited by scarce annotations and domain shifts. Self-supervised learning (SSL) can address these challenges but remains underexplored in pan-cancer, multi-tracer PET-CT. In this work, we propose MUST-PET (MUltimodal Self-Supervised learning across Tracers), a multimodal, multi-tracer SSL framework for generalizable whole-body PET-CT lesion segmentation. MUST-PET is trained and validated on a diverse, multi-institutional collection of pan-cancer PET-CT scans acquired with FDG and prostate-specific membrane antigen (PSMA)-targeted radiotracers. MUST-PET uses context-aware masked reconstruction, where one modality is partially masked and reconstructed using complementary information from both PET and CT. The pretrained model is subsequently fine-tuned with labeled samples and evaluated for reconstruction quality, lesion segmentation, label efficiency, and generalizability across independent held-out datasets. MUST-PET reduces reconstruction error, improves lesion segmentation over training from scratch, and performs well with limited labeled data and on unseen external datasets, demonstrating the potential of multi-tracer SSL for label-efficient, generalizable whole-body PET-CT. segmentation.

Related papers

• An Open Multi-Center Whole-Body FDG PET/CT Foundation Model for Tumor Segmentation [9.922425508121012]
  We present an open-source, multi-center, whole-body FDG PET/CT foundation model utilizing 4,997 harmonized scans from four public datasets.<n>Our framework employs hierarchical UNet-shaped backbones with early channel-wise concatenation, enabling anatomical and metabolic features to interact.<n>It provides a robust, open-source basis for advancing automated oncologic imaging.
  arXiv  Detail & Related papers  (2026-05-20T23:59:50Z)
• The autoPET3 Challenge: Automated Lesion Segmentation in Whole-Body PET/CT $\unicode{x2013}$ Multitracer Multicenter Generalization [67.92281859568168]
  We report the design and results of the third autoPET challenge (MICCAI 2024)<n>It benchmarked automated lesion segmentation in whole-body PET/CT under a compositional generalization setting.<n>The top-ranked algorithm achieved a mean DSC of 0.66, FNV of 3.18 mL, and FPV of 2.78 mL across all four test conditions.
  arXiv  Detail & Related papers  (2026-05-07T07:07:09Z)
• Developing Foundation Models for Universal Segmentation from 3D Whole-Body Positron Emission Tomography [36.14746684754266]
  We build the largest and most comprehensive PET dataset to date, comprising 11041 3D whole-body PET scans with 59831 segmentation masks for model development.<n>We present SegAnyPET, an innovative foundational model with general-purpose applicability to diverse segmentation tasks.
  arXiv  Detail & Related papers  (2026-03-12T07:41:28Z)
• Unveiling and Bridging the Functional Perception Gap in MLLMs: Atomic Visual Alignment and Hierarchical Evaluation via PET-Bench [48.60251555171943]
  Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in tasks such as abnormality detection and report generation for anatomical modalities.<n>In this work, we quantify a fundamental functional perception gap: the inability of current vision encoders to decode functional tracer biodistribution independent of morphological priors.<n>We introduce PET-Bench, the first large-scale functional imaging benchmark comprising 52,308 hierarchical QA pairs from 9,732 multi-site, multi-tracer PET studies.<n>Our results demonstrate that AVA effectively bridges the perception gap, transforming CoT from a source of hallucination into a robust inference tool and improving diagnostic
  arXiv  Detail & Related papers  (2026-01-06T05:58:50Z)
• 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)
• Developing a PET/CT Foundation Model for Cross-Modal Anatomical and Functional Imaging [39.59895695500171]
  We introduce the Cross-Fraternal Twin Masked Autoencoder (FratMAE), a novel framework that effectively integrates whole-body anatomical and functional information.<n>FratMAE captures intricate cross-modal relationships and global uptake patterns, achieving superior performance on downstream tasks.
  arXiv  Detail & Related papers  (2025-03-04T17:49:07Z)
• AutoPET III Challenge: Tumor Lesion Segmentation using ResEnc-Model Ensemble [1.3467243219009812]
  We trained a 3D Residual encoder U-Net within the no new U-Net framework to generalize the performance of automatic lesion segmentation. We leveraged test-time augmentations and other post-processing techniques to enhance tumor lesion segmentation. Our team currently hold the top position in the Auto-PET III challenge and outperformed the challenge baseline model in the preliminary test set with Dice score of 0.9627.
  arXiv  Detail & Related papers  (2024-09-19T20:18:39Z)
• Autopet III challenge: Incorporating anatomical knowledge into nnUNet for lesion segmentation in PET/CT [4.376648893167674]
  The autoPET III Challenge focuses on advancing automated segmentation of tumor lesions in PET/CT images. We developed a classifier that identifies the tracer of the given PET/CT based on the Maximum Intensity Projection of the PET scan. Our final submission achieves cross-validation Dice scores of 76.90% and 61.33% for the publicly available FDG and PSMA datasets.
  arXiv  Detail & Related papers  (2024-09-18T17:16:57Z)
• From FDG to PSMA: A Hitchhiker's Guide to Multitracer, Multicenter Lesion Segmentation in PET/CT Imaging [0.9384264274298444]
  We present our solution for the autoPET III challenge, targeting multitracer, multicenter generalization using the nnU-Net framework with the ResEncL architecture. Key techniques include misalignment data augmentation and multi-modal pretraining across CT, MR, and PET datasets. Compared to the default nnU-Net, which achieved a Dice score of 57.61, our model significantly improved performance with a Dice score of 68.40, alongside a reduction in false positive (FPvol: 7.82) and false negative (FNvol: 10.35) volumes.
  arXiv  Detail & Related papers  (2024-09-14T16:39:17Z)
• Two-Phase Multi-Dose-Level PET Image Reconstruction with Dose Level Awareness [43.45142393436787]
  We design a novel two-phase multi-dose-level PET reconstruction algorithm with dose level awareness. The pre-training phase is devised to explore both fine-grained discriminative features and effective semantic representation. The SPET prediction phase adopts a coarse prediction network utilizing pre-learned dose level prior to generate preliminary result.
  arXiv  Detail & Related papers  (2024-04-02T01:57:08Z)
• 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)
• A Unified Continual Learning Framework with General Parameter-Efficient Tuning [56.250772378174446]
  "Pre-training $rightarrow$ downstream adaptation" presents both new opportunities and challenges for Continual Learning. We position prompting as one instantiation of PET, and propose a unified CL framework, dubbed as Learning-Accumulation-Ensemble (LAE) PET, e.g., using Adapter, LoRA, or Prefix, can adapt a pre-trained model to downstream tasks with fewer parameters and resources.
  arXiv  Detail & Related papers  (2023-03-17T15:52:45Z)
• Multimodal Spatial Attention Module for Targeting Multimodal PET-CT Lung Tumor Segmentation [11.622615048002567]
  Multimodal spatial attention module (MSAM) learns to emphasize regions related to tumors. MSAM can be applied to common backbone architectures and trained end-to-end.
  arXiv  Detail & Related papers  (2020-07-29T10:27:22Z)

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.