Cross-attention learning enables real-time nonuniform rotational distortion correction in OCT

• URL: http://arxiv.org/abs/2306.04512v2
• Date: Fri, 5 Jan 2024 06:51:15 GMT
• Title: Cross-attention learning enables real-time nonuniform rotational distortion correction in OCT
• Authors: Haoran Zhang, Jianlong Yang, Jingqian Zhang, Shiqing Zhao, Aili Zhang
• Abstract summary: Nonuniform rotational distortion (NURD) correction is vital for endoscopic optical coherence tomography ( OCT) imaging. Here we propose a cross-attention learning method for the NURD correction in OCT. Our method is inspired by the recent success of the self-attention mechanism in natural language processing and computer vision.
• Score: 15.445504413810093
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Nonuniform rotational distortion (NURD) correction is vital for endoscopic optical coherence tomography (OCT) imaging and its functional extensions, such as angiography and elastography. Current NURD correction methods require time-consuming feature tracking or cross-correlation calculations and thus sacrifice temporal resolution. Here we propose a cross-attention learning method for the NURD correction in OCT. Our method is inspired by the recent success of the self-attention mechanism in natural language processing and computer vision. By leveraging its ability to model long-range dependencies, we can directly obtain the correlation between OCT A-lines at any distance, thus accelerating the NURD correction. We develop an end-to-end stacked cross-attention network and design three types of optimization constraints. We compare our method with two traditional feature-based methods and a CNN-based method, on two publicly-available endoscopic OCT datasets and a private dataset collected on our home-built endoscopic OCT system. Our method achieved a $\sim3\times$ speedup to real time ($26\pm 3$ fps), and superior correction performance.

Related papers

• Rotational Augmented Noise2Inverse for Low-dose Computed Tomography Reconstruction [83.73429628413773]
  Supervised deep learning methods have shown the ability to remove noise in images but require accurate ground truth. We propose a novel self-supervised framework for LDCT, in which ground truth is not required for training the convolutional neural network (CNN) Numerical and experimental results show that the reconstruction accuracy of N2I with sparse views is degrading while the proposed rotational augmented Noise2Inverse (RAN2I) method keeps better image quality over a different range of sampling angles.
  arXiv  Detail & Related papers  (2023-12-19T22:40:51Z)
• INeAT: Iterative Neural Adaptive Tomography [34.84974955073465]
  Iterative Neural Adaptive Tomography (INeAT) incorporates posture optimization to counteract the influence of posture perturbations in data. We demonstrate that INeAT achieves artifact-suppressed and resolution-enhanced reconstruction in scenarios with significant pose disturbances.
  arXiv  Detail & Related papers  (2023-11-03T01:00:36Z)
• Towards Head Computed Tomography Image Reconstruction Standardization with Deep Learning Assisted Automatic Detection [5.288684776927016]
  Three-dimensional (3D) reconstruction of head Computed Tomography (CT) images elucidates the intricate spatial relationships of tissue structures. securing an optimal head CT scan without deviation is challenging in clinical settings, owing to poor positioning by technicians, patient's physical constraints, or CT scanner tilt angle restrictions. We propose an efficient automatic head CT images 3D reconstruction method, improving accuracy and repeatability, as well as diminishing manual intervention.
  arXiv  Detail & Related papers  (2023-07-31T06:58:49Z)
• 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)
• Anatomically constrained CT image translation for heterogeneous blood vessel segmentation [3.88838725116957]
  Anatomical structures in contrast-enhanced CT (ceCT) images can be challenging to segment due to variability in contrast medium diffusion. To limit the radiation dose, generative models could be used to synthesize one modality, instead of acquiring it. CycleGAN has attracted particular attention because it alleviates the need for paired data. We present an extension of CycleGAN to generate high fidelity images, with good structural consistency.
  arXiv  Detail & Related papers  (2022-10-04T16:14:49Z)
• Attentive Symmetric Autoencoder for Brain MRI Segmentation [56.02577247523737]
  We propose a novel Attentive Symmetric Auto-encoder based on Vision Transformer (ViT) for 3D brain MRI segmentation tasks. In the pre-training stage, the proposed auto-encoder pays more attention to reconstruct the informative patches according to the gradient metrics. Experimental results show that our proposed attentive symmetric auto-encoder outperforms the state-of-the-art self-supervised learning methods and medical image segmentation models.
  arXiv  Detail & Related papers  (2022-09-19T09:43:19Z)
• A Spatiotemporal Model for Precise and Efficient Fully-automatic 3D Motion Correction in OCT [10.550562752812894]
  OCT instruments image by-scanning a focused light spot across the retina, acquiring cross-sectional images to generate data. Patient eye motion during the acquisition poses unique challenges: non-rigid, distorted distortions occur, leading to gaps in data. We present a new distortion model and a corresponding fully-automatic, reference-free optimization strategy for computational robustness.
  arXiv  Detail & Related papers  (2022-09-15T11:48:53Z)
• Fluid registration between lung CT and stationary chest tomosynthesis images [23.239722016943794]
  We formulate a 3D/2D registration approach which infers a 3D deformation based on measured projections and digitally reconstructed radiographs. We demonstrate our approach for the registration between CT and stationary chest tomosynthesis (sDCT) images and show how it naturally leads to an iterative image reconstruction approach.
  arXiv  Detail & Related papers  (2022-03-06T21:51:49Z)
• Incremental Cross-view Mutual Distillation for Self-supervised Medical CT Synthesis [88.39466012709205]
  This paper builds a novel medical slice to increase the between-slice resolution. Considering that the ground-truth intermediate medical slices are always absent in clinical practice, we introduce the incremental cross-view mutual distillation strategy. Our method outperforms state-of-the-art algorithms by clear margins.
  arXiv  Detail & Related papers  (2021-12-20T03:38:37Z)
• 4D Spatio-Temporal Convolutional Networks for Object Position Estimation in OCT Volumes [69.62333053044712]
  3D convolutional neural networks (CNNs) have shown promising performance for pose estimation of a marker object using single OCT images. We extend 3D CNNs to 4D-temporal CNNs to evaluate the impact of additional temporal information for marker object tracking.
  arXiv  Detail & Related papers  (2020-07-02T12:02:20Z)
• Spatio-Temporal Deep Learning Methods for Motion Estimation Using 4D OCT Image Data [63.73263986460191]
  Localizing structures and estimating the motion of a specific target region are common problems for navigation during surgical interventions. We investigate whether using a temporal stream of OCT image volumes can improve deep learning-based motion estimation performance. Using 4D information for the model input improves performance while maintaining reasonable inference times.
  arXiv  Detail & Related papers  (2020-04-21T15:43:01Z)

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.