Weakly Supervised Pathology-Informed Representation Learning for PET-Based Content Retrieval of Intra-Tumour Heterogeneity

• URL: http://arxiv.org/abs/2607.18762v1
• Date: Tue, 21 Jul 2026 06:40:14 GMT
• Title: Weakly Supervised Pathology-Informed Representation Learning for PET-Based Content Retrieval of Intra-Tumour Heterogeneity
• Abstract summary: The proposed method was designed to use H&E derived information during training while maintaining PET only inference.<n>A teacher student training strategy was used to learn the PET tumour derived voxel representations.
• Score: 0.16999906736255554
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We propose a weakly supervised 18FFDG PET representation-learning framework for content based medical image retrieval, using H&E derived information during training while preserving PET-only inference. The proposed method was designed to use H&E derived information during training while maintaining PET only inference. A teacher student training strategy was used to learn the PET tumour derived voxel representations, from which global and hotspot conditioned embeddings were generated along with maps of intra tumour heterogeneity in our oesophegeal cancer test case. A progressive ablation strategy was used to evaluate the contribution of different supervision mechanisms. Retrieval performance was assessed across cross-validation folds using metrics including mean average precision, normalised discounted cumulative gain and mean reciprocal rank. Additional analyses evaluated ablation performance, hotspot faithfulness through perturbation/deletion experiments, prototype-specific PET uptake behaviour and indirect patient level concordance between learned PET prototype classes and selected histomic features. Progressive introduction of pathology informed supervision and hotspot modelling improved PET retrieval performance compared with global PET representations and conventional PET baselines. Across the ablation ladder, PET hotspot conditioned representations consistently provided stronger retrieval than global embeddings, indicating that focusing on informative tumour subregions improved sensitivity to intra tumour heterogeneity. Histopathology concordance further showed that the learned classes were not simply high uptake PET regions; instead, they demonstrated distinct heterogeneity in 18F FDG uptake.

Related papers

• 3D CT-to-PET Translation via Latent Brownian Bridge Diffusion [2.013258778704508]
  We propose a 3D CT-to-PET translation framework based on latent Brownian Bridge Diffusion (BBDM)<n>The proposed approach improves PET signal fidelity, better preserves clinically relevant uptake patterns, and shows improved performance in preserving small-lesion metabolic activation.
  arXiv  Detail & Related papers  (2026-09-11T13:47:50Z)
• A Dual Path Framework with Hotspot Guided Fusion for Three Dimensional CT to PET Synthesis in Head and Neck Cancer [0.0]
  18F-FDG PET/CT plays a central role in staging, treatment planning, and response assessment for head and neck cancer.<n>We present a proof of concept deep learning framework for synthesizing PET like images directly from routine CT scans.
  arXiv  Detail & Related papers  (2026-07-23T20:33:50Z)
• ReMAP-PET: Beyond Visual Understanding -- Learning Region-Guided Metabolic Alignment Semantics from Brain PET [20.566933407659093]
  We propose ReMAP-PET to treat PET as structured, interpretable, and language-compatible representations.<n>Our results show that grounding PET encoders in regional metabolic semantics yields representations that are structured, interpretable, and language-compatible.
  arXiv  Detail & Related papers  (2026-06-28T19:43:03Z)
• RADIANT-PET: Reasoning-Augmented PET/CT Lesion Segmentation with Large Language Models and Reinforcement Learning [0.0]
  We present RADIANT-PET, a reasoning-augmented framework that couples a high-sensitivity voxel-level segmentation model with lesion-level large language model (LLM) adjudication.<n>Across AutoPET and an OSU test cohort, RADIANT-PET consistently outperforms strong image-only baselines.
  arXiv  Detail & Related papers  (2026-06-23T18:05:55Z)
• Improving PET/CT-Based Whole-Body Lesion Segmentation Using Prediction Uncertainty-Augmented Models [4.533732724414947]
  Lesion delineation from PET/CT imaging is clinically challenging due to subtle imaging features, confounders, and inter-reader variability.<n>Existing deep learning approaches suffer from training-relatedity, inconsistent predictions, missed lesions in high tumor-burden cases, and lack uncertainty.<n>We propose an uncertainty-aware framework for whole-body PET/CT lesion segmentation.
  arXiv  Detail & Related papers  (2026-06-08T19:49:23Z)
• Generation of Heterogeneous PET Images from Uniform Organ Activity Maps Using a Pretrained Domain-Adapted Diffusion Model [1.3918848543076061]
  Synthetic PET images are valuable for quantitative imaging workflow development, scalable virtual imaging trials, and deep learning model training.<n>This study developed a pretrained domain-adapted diffusion model for anatomy-conditioned PET synthesis from uniform organ activity maps.
  arXiv  Detail & Related papers  (2026-05-18T21:05:28Z)
• 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)
• 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)
• HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuning [55.88910947643436]
  We propose a unified framework for continual learning (CL) with pre-trained models (PTMs) and parameter-efficient tuning (PET)<n>We present Hierarchical Decomposition PET (HiDe-PET), an innovative approach that explicitly optimize the objective through incorporating task-specific and task-shared knowledge.<n>Our approach demonstrates remarkably superior performance over a broad spectrum of recent strong baselines.
  arXiv  Detail & Related papers  (2024-07-07T01:50:25Z)
• Multi-modal Evidential Fusion Network for Trustworthy PET/CT Tumor Segmentation [5.839660501978193]
  In clinical settings, the quality of PET and CT images often varies significantly, leading to uncertainty in the modality information extracted by networks.<n>We propose a novel Multi-modal Evidential Fusion Network (MEFN), which consists of two core stages: Cross-Modal Feature Learning (CFL) and Multi-modal Trustworthy Fusion (MTF)<n>Our model can provide radiologists with credible uncertainty of the segmentation results for their decision in accepting or rejecting the automatic segmentation results.
  arXiv  Detail & Related papers  (2024-06-26T13:14:24Z)
• PAD-Phys: Exploiting Physiology for Presentation Attack Detection in Face Biometrics [48.683457383784145]
  Three approaches to presentation attack detection based on r: (i) the physiological domain, (ii) the Deepfakes domain, and (iii) a new Presentation Attack domain. Results show a 21.70% decrease in average classification error rate (ACER) when the presentation attack domain is compared to the physiological and Deepfakes domains. Experiments highlight the efficiency of transfer learning in r-based models and perform well in presentation attack detection in instruments that do not allow copying of this physiological feature.
  arXiv  Detail & Related papers  (2023-10-03T15:24:15Z)
• 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)

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.