Anatomy-Aware Low-Dose CT Denoising via Pretrained Vision Models and Semantic-Guided Contrastive Learning

• URL: http://arxiv.org/abs/2508.07788v1
• Date: Mon, 11 Aug 2025 09:17:12 GMT
• Title: Anatomy-Aware Low-Dose CT Denoising via Pretrained Vision Models and Semantic-Guided Contrastive Learning
• Authors: Runze Wang, Zeli Chen, Zhiyun Song, Wei Fang, Jiajin Zhang, Danyang Tu, Yuxing Tang, Minfeng Xu, Xianghua Ye, Le Lu, Dakai Jin,
• Abstract summary: We propose ALDEN, an anatomy-aware LDCT denoising method that integrates semantic features of pretrained vision models with adversarial and contrastive learning.<n>Specifically, we introduce an anatomy-aware discriminator that dynamically fuses hierarchical semantic features from reference normal-dose CT (NDCT) via cross-attention mechanisms.<n>In addition, we propose a semantic-guided contrastive learning module that enforces anatomical consistency by contrasting PVM-derived features from LDCT, denoised CT and NDCT, preserving tissue-specific patterns through positive pairs and suppressing artifacts via dual negative pairs.
• Score: 12.975922919920393
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To reduce radiation exposure and improve the diagnostic efficacy of low-dose computed tomography (LDCT), numerous deep learning-based denoising methods have been developed to mitigate noise and artifacts. However, most of these approaches ignore the anatomical semantics of human tissues, which may potentially result in suboptimal denoising outcomes. To address this problem, we propose ALDEN, an anatomy-aware LDCT denoising method that integrates semantic features of pretrained vision models (PVMs) with adversarial and contrastive learning. Specifically, we introduce an anatomy-aware discriminator that dynamically fuses hierarchical semantic features from reference normal-dose CT (NDCT) via cross-attention mechanisms, enabling tissue-specific realism evaluation in the discriminator. In addition, we propose a semantic-guided contrastive learning module that enforces anatomical consistency by contrasting PVM-derived features from LDCT, denoised CT and NDCT, preserving tissue-specific patterns through positive pairs and suppressing artifacts via dual negative pairs. Extensive experiments conducted on two LDCT denoising datasets reveal that ALDEN achieves the state-of-the-art performance, offering superior anatomy preservation and substantially reducing over-smoothing issue of previous work. Further validation on a downstream multi-organ segmentation task (encompassing 117 anatomical structures) affirms the model's ability to maintain anatomical awareness.

Related papers

• Structure-constrained Language-informed Diffusion Model for Unpaired Low-dose Computed Tomography Angiography Reconstruction [72.80209358480424]
  overdose of iodinated contrast media (ICM) can cause kidney damage and life-threatening allergic reactions.<n>Deep learning methods can generate CT images of normal-dose ICM from low-dose ICM, reducing the required dose.<n>We propose a Structure-constrained Language-informed Diffusion Model (SLDM) that integrates structural synergy and spatial intelligence.
  arXiv  Detail & Related papers  (2026-01-28T06:54:06Z)
• D-PerceptCT: Deep Perceptual Enhancement for Low-Dose CT Images [3.982360641359205]
  Low Dose Computed Tomography (LDCT) is widely used as an imaging solution to aid diagnosis and other clinical tasks.<n>This comes at the price of a deterioration in image quality due to the low dose of radiation used to reduce the risk of secondary cancer development.<n>We introduce D-PerceptCT, a novel architecture inspired by key principles of the Human Visual System (HVS) to enhance LDCT images.
  arXiv  Detail & Related papers  (2025-11-18T14:14:59Z)
• FoundDiff: Foundational Diffusion Model for Generalizable Low-Dose CT Denoising [55.04342933312839]
  We propose FoundDiff, a foundational diffusion model for unified and generalizable low-dose computed tomography (CT) denoising.<n>FoundDiff employs a two-stage strategy: (i) dose-anatomy perception and (ii) adaptive denoising.<n>First, we develop a dose- and anatomy-aware contrastive language image pre-training model (DA-CLIP) to achieve robust dose and anatomy perception.<n>Second, we design a dose- and anatomy-aware diffusion model (DA-Diff) to perform adaptive and generalizable denoising.
  arXiv  Detail & Related papers  (2025-08-24T11:03:56Z)
• Direct Dual-Energy CT Material Decomposition using Model-based Denoising Diffusion Model [105.95160543743984]
  We propose a deep learning procedure called Dual-Energy Decomposition Model-based Diffusion (DEcomp-MoD) for quantitative material decomposition.<n>We show that DEcomp-MoD outperform state-of-the-art unsupervised score-based model and supervised deep learning networks.
  arXiv  Detail & Related papers  (2025-07-24T01:00:06Z)
• Neurovascular Segmentation in sOCT with Deep Learning and Synthetic Training Data [4.5276169699857505]
  This study demonstrates a synthesis engine for neurovascular segmentation in serial-section optical coherence tomography images. Our approach comprises two phases: label synthesis and label-to-image transformation. We demonstrate the efficacy of the former by comparing it to several more realistic sets of training labels, and the latter by an ablation study of synthetic noise and artifact models.
  arXiv  Detail & Related papers  (2024-07-01T16:09:07Z)
• WIA-LD2ND: Wavelet-based Image Alignment for Self-supervised Low-Dose CT Denoising [74.14134385961775]
  We introduce a novel self-supervised CT image denoising method called WIA-LD2ND, only using NDCT data. WIA-LD2ND comprises two modules: Wavelet-based Image Alignment (WIA) and Frequency-Aware Multi-scale Loss (FAM)
  arXiv  Detail & Related papers  (2024-03-18T11:20:11Z)
• Self-supervised OCT Image Denoising with Slice-to-Slice Registration and Reconstruction [5.972377737617966]
  Learning-based self-supervised methods for structure-preserving noise reduction have demonstrated superior performance over traditional methods. We introduce a new end-to-end self-supervised learning framework specifically tailored for OCT image denoising.
  arXiv  Detail & Related papers  (2023-11-26T02:45:16Z)
• ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising [23.274928463320986]
  We propose a novel Anatomy-aware Supervised CONtrastive learning framework, termed ASCON, to explore the anatomical semantics for low-dose CT denoising. Our ASCON provides anatomical interpretability for low-dose CT denoising for the first time.
  arXiv  Detail & Related papers  (2023-07-23T04:36:05Z)
• Deep learning network to correct axial and coronal eye motion in 3D OCT retinal imaging [65.47834983591957]
  We propose deep learning based neural networks to correct axial and coronal motion artifacts in OCT based on a single scan. The experimental result shows that the proposed method can effectively correct motion artifacts and achieve smaller error than other methods.
  arXiv  Detail & Related papers  (2023-05-27T03:55:19Z)
• The role of noise in denoising models for anomaly detection in medical images [62.0532151156057]
  Pathological brain lesions exhibit diverse appearance in brain images. Unsupervised anomaly detection approaches have been proposed using only normal data for training. We show that optimization of the spatial resolution and magnitude of the noise improves the performance of different model training regimes.
  arXiv  Detail & Related papers  (2023-01-19T21:39:38Z)
• Self-supervised Physics-based Denoising for Computed Tomography [2.2758845733923687]
  Computed Tomography (CT) imposes risk on the patients due to its inherent X-ray radiation. Lowering the radiation dose reduces the health risks but leads to noisier measurements, which decreases the tissue contrast and causes artifacts in CT images. Modern deep learning noise suppression methods alleviate the challenge but require low-noise-high-noise CT image pairs for training. We introduce a new self-supervised approach for CT denoising Noise2NoiseTD-ANM that can be trained without the high-dose CT projection ground truth images.
  arXiv  Detail & Related papers  (2022-11-01T20:58:50Z)
• InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal Artifact Reduction in CT Images [53.4351366246531]
  We construct a novel interpretable dual domain network, termed InDuDoNet+, into which CT imaging process is finely embedded. We analyze the CT values among different tissues, and merge the prior observations into a prior network for our InDuDoNet+, which significantly improve its generalization performance.
  arXiv  Detail & Related papers  (2021-12-23T15:52:37Z)

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.