CDPM-Align: Multi-Scale Guidance-Aligned Diffusion Pretraining for Robust Few-Shot Anatomical Landmark Detection

• URL: http://arxiv.org/abs/2606.04898v1
• Date: Wed, 03 Jun 2026 13:59:42 GMT
• Title: CDPM-Align: Multi-Scale Guidance-Aligned Diffusion Pretraining for Robust Few-Shot Anatomical Landmark Detection
• Abstract summary: CDPM-align is a multi-scale guidance-aligned conditional diffusion pre-training for anatomical landmark detection.<n>We employ three popular heterogeneous small-scale benchmark datasets for representation learning via conditional generative pre-training.<n>Our results confirm that generative pre-training enables the model to learn a robust representation.
• Score: 7.205733158614911
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Anatomical landmark detection is a fundamental task in medical image analysis supporting a wide range of diagnostic and interventional workflows. Although recent methods have achieved sub-millimetric localisation, accuracy alone is not sufficient for clinical deployment, requiring reliability and robustness in prediction. Despite its clinical relevance, the impact of representation learning in this context is still underexplored. In this work, we introduce CDPM-align, a multi-scale guidance-aligned conditional diffusion pre-training for anatomical landmark detection. Our experimental setup focuses on a few images and a few annotation regimes. Specifically, we employ three popular heterogeneous small-scale benchmark datasets for representation learning via conditional generative pre-training. Furthermore, we consider low-annotation scenarios for the downstream task of landmark detection, with 10 and 25 annotated images, reflecting realistic trade-offs between clinical effort and resource constraints for annotations. Our results confirm that generative pre-training enables the model to learn a robust representation. This improves both accuracy and uncertainty on the downstream tasks, advancing towards safe and efficient clinical deployment.

Related papers

• Rethinking Medical Landmark Localization with Prototype Learning-based Progressive Offset Correction [9.30702458761404]
  We propose a parameter-economic model, PPOC-LL, which leverages Prototype learning-based Progressive Offset Correction for Landmark localization.<n>Our contribution is three-fold. First, to drive coarse-to-fine landmark optimization, we introduce a multi-scale dynamic perception strategy for patch-level feature pyramid modeling. Second, to effectively handle anatomically similar patterns, we design a similarity-driven prototype learning mechanism that captures informative local semantics for robust offset prediction. Last, to stabilize the model learning and improve the overall performance, we incorporate a novel error-aware reliability regularization via tolerance-based balancing.
  arXiv  Detail & Related papers  (2026-08-10T06:49:16Z)
• Uncertainty-aware Medical Diagnostic Phrase Identification and Grounding [72.18719355481052]
  We introduce a novel task called Medical Report Grounding (MRG)<n>MRG aims to directly identify diagnostic phrases and their corresponding grounding boxes from medical reports in an end-to-end manner.<n>We propose uMedGround, a robust and reliable framework that leverages a multimodal large language model to predict diagnostic phrases.
  arXiv  Detail & Related papers  (2024-04-10T07:41:35Z)
• Deployment of Image Analysis Algorithms under Prevalence Shifts [6.373765910269204]
  Domain gaps are among the most relevant roadblocks in the clinical translation of machine learning (ML)-based solutions for medical image analysis. We propose a workflow for prevalence-aware image classification that uses estimated deployment prevalences to adjust a trained classifier to a new environment.
  arXiv  Detail & Related papers  (2023-03-22T13:16:37Z)
• Real-time landmark detection for precise endoscopic submucosal dissection via shape-aware relation network [51.44506007844284]
  We propose a shape-aware relation network for accurate and real-time landmark detection in endoscopic submucosal dissection surgery. We first devise an algorithm to automatically generate relation keypoint heatmaps, which intuitively represent the prior knowledge of spatial relations among landmarks. We then develop two complementary regularization schemes to progressively incorporate the prior knowledge into the training process.
  arXiv  Detail & Related papers  (2021-11-08T07:57:30Z)
• A Deep Learning Approach to Predicting Collateral Flow in Stroke Patients Using Radiomic Features from Perfusion Images [58.17507437526425]
  Collateral circulation results from specialized anastomotic channels which provide oxygenated blood to regions with compromised blood flow. The actual grading is mostly done through manual inspection of the acquired images. We present a deep learning approach to predicting collateral flow grading in stroke patients based on radiomic features extracted from MR perfusion data.
  arXiv  Detail & Related papers  (2021-10-24T18:58:40Z)
• On the Practicality of Deterministic Epistemic Uncertainty [106.06571981780591]
  deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution data. It remains unclear whether DUMs are well calibrated and can seamlessly scale to real-world applications.
  arXiv  Detail & Related papers  (2021-07-01T17:59:07Z)
• Learn Fine-grained Adaptive Loss for Multiple Anatomical Landmark Detection in Medical Images [15.7026400415269]
  We propose a novel learning-to-learn framework for landmark detection. Our proposed framework is general and shows the potential to improve the efficiency of anatomical landmark detection.
  arXiv  Detail & Related papers  (2021-05-19T13:39:18Z)
• Cascaded Robust Learning at Imperfect Labels for Chest X-ray Segmentation [61.09321488002978]
  We present a novel cascaded robust learning framework for chest X-ray segmentation with imperfect annotation. Our model consists of three independent network, which can effectively learn useful information from the peer networks. Our methods could achieve a significant improvement on the accuracy in segmentation tasks compared to the previous methods.
  arXiv  Detail & Related papers  (2021-04-05T15:50:16Z)
• Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding [60.89561661441736]
  We propose a novel method for few-shot medical image segmentation. We construct our few-shot image segmentor using a deep convolutional network trained episodically. We enhance discriminability of deep embedding to encourage clustering of the feature domains of the same class.
  arXiv  Detail & Related papers  (2020-12-10T04:01:07Z)
• Cross-Task Representation Learning for Anatomical Landmark Detection [20.079451546446712]
  We propose to regularize the knowledge transfer across source and target tasks through cross-task representation learning. The proposed method is demonstrated for extracting facial anatomical landmarks which facilitate the diagnosis of fetal alcohol syndrome. We present two approaches for the proposed representation learning by constraining either final or intermediate model features on the target model.
  arXiv  Detail & Related papers  (2020-09-28T21:22:49Z)
• Localization of Critical Findings in Chest X-Ray without Local Annotations Using Multi-Instance Learning [0.0]
  deep learning models commonly suffer from a lack of explainability. Deep learning models require locally annotated training data in form of pixel level labels or bounding box coordinates. In this work, we address these shortcomings with an interpretable DL algorithm based on multi-instance learning.
  arXiv  Detail & Related papers  (2020-01-23T21:29:14Z)

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.