DPL: Spatial-Conditioned Diffusion Prototype Enhancement for One-Shot Medical Segmentation

• URL: http://arxiv.org/abs/2510.12159v1
• Date: Tue, 14 Oct 2025 05:28:58 GMT
• Title: DPL: Spatial-Conditioned Diffusion Prototype Enhancement for One-Shot Medical Segmentation
• Authors: Ziyuan Gao, Philippe Morel,
• Abstract summary: One-shot medical image segmentation faces fundamental challenges in prototype representation due to limited annotated data and anatomical variability across patients.<n>Traditional prototype-based methods rely on deterministic averaging of support features, creating brittle representations that fail to capture intra-class diversity essential for robust generalization.<n>This work introduces Diffusion Prototype Learning, a novel framework that reformulates prototype construction through diffusion-based feature space exploration.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: One-shot medical image segmentation faces fundamental challenges in prototype representation due to limited annotated data and significant anatomical variability across patients. Traditional prototype-based methods rely on deterministic averaging of support features, creating brittle representations that fail to capture intra-class diversity essential for robust generalization. This work introduces Diffusion Prototype Learning (DPL), a novel framework that reformulates prototype construction through diffusion-based feature space exploration. DPL models one-shot prototypes as learnable probability distributions, enabling controlled generation of diverse yet semantically coherent prototype variants from minimal labeled data. The framework operates through three core innovations: (1) a diffusion-based prototype enhancement module that transforms single support prototypes into diverse variant sets via forward-reverse diffusion processes, (2) a spatial-aware conditioning mechanism that leverages geometric properties derived from prototype feature statistics, and (3) a conservative fusion strategy that preserves prototype fidelity while maximizing representational diversity. DPL ensures training-inference consistency by using the same diffusion enhancement and fusion pipeline in both phases. This process generates enhanced prototypes that serve as the final representations for similarity calculations, while the diffusion process itself acts as a regularizer. Extensive experiments on abdominal MRI and CT datasets demonstrate significant improvements respectively, establishing new state-of-the-art performance in one-shot medical image segmentation.

Related papers

• Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Image Segmentation [66.82598255715696]
  Federated learning enables multiple medical institutions to train a global model without sharing data.<n>Current approaches primarily focus on final-layer features, overlooking critical multi-level cues.<n>We propose FedBCS to bridge feature representation gaps via domain-invariant contextual prototypes alignment.
  arXiv  Detail & Related papers  (2025-11-14T04:15:34Z)
• Few to Big: Prototype Expansion Network via Diffusion Learner for Point Cloud Few-shot Semantic Segmentation [12.971351926107289]
  Prototype Expansion Network (PENet) is a framework that constructs big-capacity prototypes from two annotated feature sources.<n>PENet significantly outperforms state-of-the-art methods across various few-shot settings.
  arXiv  Detail & Related papers  (2025-09-16T09:29:46Z)
• FedProtoKD: Dual Knowledge Distillation with Adaptive Class-wise Prototype Margin for Heterogeneous Federated Learning [18.44030373279699]
  Prototype-based Heterogeneous Federated Learning (HFL) methods emerge as a promising solution to address statistical heterogeneity and privacy challenges.<n>We propose FedProtoKD in a Heterogeneous Federated Learning setting, using an enhanced dual-knowledge distillation mechanism to improve the system performance with clients' logits and prototype representation.<n>FedProtoKD achieved average improvements of 1.13% up to 34.13% accuracy across various settings and significantly outperforms existing state-of-the-art HFL methods.
  arXiv  Detail & Related papers  (2025-08-26T13:14:29Z)
• UniSegDiff: Boosting Unified Lesion Segmentation via a Staged Diffusion Model [53.34835793648352]
  We propose UniSegDiff, a novel diffusion model framework for lesion segmentation.<n>UniSegDiff addresses lesion segmentation in a unified manner across multiple modalities and organs.<n> Comprehensive experimental results demonstrate that UniSegDiff significantly outperforms previous state-of-the-art (SOTA) approaches.
  arXiv  Detail & Related papers  (2025-07-24T12:33:10Z)
• Probabilistic Prototype Calibration of Vision-Language Models for Generalized Few-shot Semantic Segmentation [75.18058114915327]
  Generalized Few-Shot Semanticnative (GFSS) aims to extend a segmentation model to novel classes with only a few annotated examples.<n>We propose FewCLIP, a probabilistic prototype calibration framework over multi-modal prototypes from the pretrained CLIP.<n>We show FewCLIP significantly outperforms state-of-the-art approaches across both GFSS and class-incremental setting.
  arXiv  Detail & Related papers  (2025-06-28T18:36:22Z)
• Tied Prototype Model for Few-Shot Medical Image Segmentation [9.455265838231252]
  We propose a principled reformulation of ADNet with tied prototype locations for foreground and background distributions.<n>Building on its probabilistic foundation, TPM naturally extends to multiple prototypes and multi-class segmentation.<n>We leverage naturally occurring class priors to define an ideal target for adaptive thresholds.
  arXiv  Detail & Related papers  (2025-06-27T10:33:55Z)
• Mind the Gap Between Prototypes and Images in Cross-domain Finetuning [64.97317635355124]
  We propose a contrastive prototype-image adaptation (CoPA) to adapt different transformations respectively for prototypes and images. Experiments on Meta-Dataset demonstrate that CoPA achieves the state-of-the-art performance more efficiently.
  arXiv  Detail & Related papers  (2024-10-16T11:42:11Z)
• CriDiff: Criss-cross Injection Diffusion Framework via Generative Pre-train for Prostate Segmentation [60.61972883059688]
  CriDiff is a two-stage feature injecting framework with a Crisscross Injection Strategy (CIS) and a Generative Pre-train (GP) approach for prostate segmentation. To effectively learn multi-level of edge features and non-edge features, we proposed two parallel conditioners in the CIS. The GP approach eases the inconsistency between the images features and the diffusion model without adding additional parameters.
  arXiv  Detail & Related papers  (2024-06-20T10:46:50Z)
• Mixed Prototype Consistency Learning for Semi-supervised Medical Image Segmentation [0.0]
  We propose the Mixed Prototype Consistency Learning (MPCL) framework, which includes a Mean Teacher and an auxiliary network. The Mean Teacher generates prototypes for labeled and unlabeled data, while the auxiliary network produces additional prototypes for mixed data processed by CutMix. High-quality global prototypes for each class are formed by fusing two enhanced prototypes, optimizing the distribution of hidden embeddings used in consistency learning.
  arXiv  Detail & Related papers  (2024-04-16T16:51:12Z)
• Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformer [20.115149216170327]
  Region-enhanced Prototypical Transformer (RPT) is a few-shot learning-based method to mitigate the effects of large intra-class diversity/bias. By stacking BaT blocks, the proposed RPT can iteratively optimize generated regional prototypes and finally produce rectified and more accurate global prototypes.
  arXiv  Detail & Related papers  (2023-09-09T15:39:38Z)
• Ambiguous Medical Image Segmentation using Diffusion Models [60.378180265885945]
  We introduce a single diffusion model-based approach that produces multiple plausible outputs by learning a distribution over group insights. Our proposed model generates a distribution of segmentation masks by leveraging the inherent sampling process of diffusion. Comprehensive results show that our proposed approach outperforms existing state-of-the-art ambiguous segmentation networks.
  arXiv  Detail & Related papers  (2023-04-10T17:58:22Z)

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.