HARU-Net: Hybrid Attention Residual U-Net for Edge-Preserving Denoising in Cone-Beam Computed Tomography

• URL: http://arxiv.org/abs/2602.22544v1
• Date: Thu, 26 Feb 2026 02:36:34 GMT
• Title: HARU-Net: Hybrid Attention Residual U-Net for Edge-Preserving Denoising in Cone-Beam Computed Tomography
• Abstract summary: We propose a novel Hybrid Attention Residual U-Net (HARU-Net) for high-quality denoising of Cone-beam computed tomography (CBCT) data.<n>HARU-Net consistently outperforms state-of-the-art (SOTA) methods including SwinIR and Uformer, achieving the highest PSNR (37.52 dB), highest SSIM (0.9557), and lowest GMSD (0.1084)<n>This effective and clinically reliable CBCT denoising is achieved at a computational cost significantly lower than that of the SOTA methods.
• Score: 0.4583541422554718
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cone-beam computed tomography (CBCT) is widely used in dental and maxillofacial imaging, but low-dose acquisition introduces strong, spatially varying noise that degrades soft-tissue visibility and obscures fine anatomical structures. Classical denoising methods struggle to suppress noise in CBCT while preserving edges. Although deep learning-based approaches offer high-fidelity restoration, their use in CBCT denoising is limited by the scarcity of high-resolution CBCT data for supervised training. To address this research gap, we propose a novel Hybrid Attention Residual U-Net (HARU-Net) for high-quality denoising of CBCT data, trained on a cadaver dataset of human hemimandibles acquired using a high-resolution protocol of the 3D Accuitomo 170 (J. Morita, Kyoto, Japan) CBCT system. The novel contribution of this approach is the integration of three complementary architectural components: (i) a hybrid attention transformer block (HAB) embedded within each skip connection to selectively emphasize salient anatomical features, (ii) a residual hybrid attention transformer group (RHAG) at the bottleneck to strengthen global contextual modeling and long-range feature interactions, and (iii) residual learning convolutional blocks to facilitate deeper, more stable feature extraction throughout the network. HARU-Net consistently outperforms state-of-the-art (SOTA) methods including SwinIR and Uformer, achieving the highest PSNR (37.52 dB), highest SSIM (0.9557), and lowest GMSD (0.1084). This effective and clinically reliable CBCT denoising is achieved at a computational cost significantly lower than that of the SOTA methods, offering a practical advancement toward improving diagnostic quality in low-dose CBCT imaging.

Related papers

• Unsupervised Metal Artifact Reduction in Dental CBCT using Fine-tuned Cycle-Consistent Adversarial Networks [0.0]
  Metal artifacts generated by dental implants significantly degrade cone-beam computed tomography (CBCT) volumes.<n>An unsupervised deep learning framework has been proposed for Metal Artifact Reduction (MAR) utilizing a Cycle-Consistent Adversarial Network (CycleGAN) optimized for high-fidelity restoration.<n>The architecture integrates U-Net-based generators and PatchGAN discriminators, specifically tuned to mitigate generative hallucinations and preserve morphological integrity.
  arXiv  Detail & Related papers  (2026-07-23T06:55:02Z)
• DeVAR: Low-Dose CT Denoising via Visual Autoregressive Modeling [14.938419722549575]
  Low-dose CT (LDCT) protocols reduce radiation risks but inevitably suffer from severe noise and artifacts that compromise diagnostic accuracy.<n>We propose a novel generative framework that applies visual autore modeling to LDCT denoising for the first time.<n>Our hybrid NDCT decoder seamlessly integrates continuous and discrete latents to reconstruct high-fidelity, detail-preserved images.
  arXiv  Detail & Related papers  (2026-06-26T09:55:37Z)
• DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction [42.4365911571903]
  We propose DiffNR, a novel framework that enhances NR optimization with diffusion priors.<n>At its core is SliceFixer, a single-step diffusion model designed to correct artifacts in degraded slices.<n>In experiments, DiffNR improves PSNR by 3.99 dB on average, generalizes well across domains, and maintains efficient optimization.
  arXiv  Detail & Related papers  (2026-04-23T10:27:54Z)
• Revisiting Global Token Mixing in Task-Dependent MRI Restoration: Insights from Minimal Gated CNN Baselines [43.505945728449774]
  Global token mixing has become a popular model design choice for MRI restoration.<n>We ask whether global token mixing is actually beneficial in each individual task across three representative settings.<n>For accelerated MRI reconstruction, the minimal unrolled gated-CNN baseline is already highly competitive.<n>For super-resolution, where low-frequency k-space data are largely preserved by the controlled low-pass degradation, local gated models remain competitive.<n>For denoising with pronounced spatially heteroscedastic noise, token-mixing models achieve the strongest overall performance.
  arXiv  Detail & Related papers  (2026-03-02T04:57:52Z)
• Multi-Stage Residual-Aware Unsupervised Deep Learning Framework for Consistent Ultrasound Strain Elastography [0.9698885636466451]
  Ultrasound Strain Elastography (USE) is a powerful non-invasive imaging technique for assessing tissue mechanical properties.<n>We propose MUSSE-Net, a residual-aware, multi-stage unsupervised sequential deep learning framework for robust and consistent strain estimation.<n> MUSSE-Net achieves state-of-the-art performance with a target SNR of 24.54, background SNR of 132.76, CNR of 59.81, and elastographic SNR of 9.73 on simulation data.
  arXiv  Detail & Related papers  (2025-11-19T17:22:25Z)
• CASR-Net: An Image Processing-focused Deep Learning-based Coronary Artery Segmentation and Refinement Network for X-ray Coronary Angiogram [9.788176765955534]
  Coronary artery disease (CAD) is critical for reducing mortality and improving patient treatment planning.<n>We present the Coronary Artery and Refinement Network (CASR-Net), a three-stage pipeline comprising image preprocessing, segmentation, and refinement.
  arXiv  Detail & Related papers  (2025-10-31T09:40:29Z)
• Enhancing ECG Classification Robustness with Lightweight Unsupervised Anomaly Detection Filters [39.9470953186283]
  Continuous electrocardiogram (ECG) monitoring via wearables offers significant potential for early cardiovascular disease (CVD) detection.<n> deploying deep learning models for automated analysis in resource-constrained environments faces reliability challenges due to Out-of-Distribution data.<n>This paper explores Unsupervised Anomaly Detection (UAD) as an independent, upstream filtering mechanism to improve robustness.
  arXiv  Detail & Related papers  (2025-10-30T13:54:37Z)
• CLARAE: Clarity Preserving Reconstruction AutoEncoder for Denoising and Rhythm Classification of Intracardiac Electrograms [37.042025337065816]
  CLARAE is a one-dimensional encoder-decoder designed for atrial EGMs.<n>It achieves both high-fidelity reconstruction and a compact 64-dimensional latent representation.
  arXiv  Detail & Related papers  (2025-09-28T20:39:21Z)
• EqDiff-CT: Equivariant Conditional Diffusion model for CT Image Synthesis from CBCT [43.92108185590778]
  Cone-beam computed tomography (CBCT) is widely used for imageguided radiotherapy (IGRT)<n>We propose a novel diffusion-based conditional generative model, coined EqDiff-CT, to synthesize high-quality CT images from CBCT.
  arXiv  Detail & Related papers  (2025-09-26T05:51:59Z)
• SQUWA: Signal Quality Aware DNN Architecture for Enhanced Accuracy in Atrial Fibrillation Detection from Noisy PPG Signals [37.788535094404644]
  Atrial fibrillation (AF) significantly increases the risk of stroke, heart disease, and mortality. Photoplethysmography ( PPG) signals are susceptible to corruption from motion artifacts and other factors often encountered in ambulatory settings. We propose a novel deep learning model, designed to learn how to retain accurate predictions from partially corrupted PPG.
  arXiv  Detail & Related papers  (2024-04-15T01:07:08Z)
• Brain Imaging-to-Graph Generation using Adversarial Hierarchical Diffusion Models for MCI Causality Analysis [44.45598796591008]
  Brain imaging-to-graph generation (BIGG) framework is proposed to map functional magnetic resonance imaging (fMRI) into effective connectivity for mild cognitive impairment analysis. The hierarchical transformers in the generator are designed to estimate the noise at multiple scales. Evaluations of the ADNI dataset demonstrate the feasibility and efficacy of the proposed model.
  arXiv  Detail & Related papers  (2023-05-18T06:54:56Z)
• Trainable Joint Bilateral Filters for Enhanced Prediction Stability in Low-dose CT [7.879949714759592]
  Low-dose computed tomography (CT) denoising algorithms aim to enable reduced patient dose in routine CT acquisitions. Deep learning(DL)-based methods were introduced, outperforming conventional denoising algorithms on this task due to their high model capacity. We propose a hybrid denoising approach consisting of a set of trainable joint bilateral filters (JBFs) combined with a convolutional DL-based denoising network.
  arXiv  Detail & Related papers  (2022-07-15T09:30:32Z)
• Retinal OCT Denoising with Pseudo-Multimodal Fusion Network [0.41998444721319206]
  We propose a learning-based method that exploits information from the single-frame noisy B-scan and a pseudo-modality that is created with the aid of the self-fusion method. Our method can effectively suppress the speckle noise and enhance the contrast between retina layers while the overall structure and small blood vessels are preserved.
  arXiv  Detail & Related papers  (2021-07-09T08:00:20Z)
• Low-Dose CT Denoising Using a Structure-Preserving Kernel Prediction Network [10.09577595969254]
  CNN-based approaches treat all regions of the CT image equally and can be inefficient when fine-grained structures coexist with non-uniformly distributed noises. We propose a Structure-preserving Kernel Prediction Network (StructKPN) that combines the kernel prediction network with a structure-aware loss function. Our approach achieved superior performance on both synthetic and non-synthetic datasets, and better preserves structures that are highly desired in clinical screening and low-dose protocol optimization.
  arXiv  Detail & Related papers  (2021-05-31T07:42:21Z)
• ADRN: Attention-based Deep Residual Network for Hyperspectral Image Denoising [52.01041506447195]
  We propose an attention-based deep residual network to learn a mapping from noisy HSI to the clean one. Experimental results demonstrate that our proposed ADRN scheme outperforms the state-of-the-art methods both in quantitative and visual evaluations.
  arXiv  Detail & Related papers  (2020-03-04T08:36:27Z)

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.