Dual-Attention Frequency Fusion at Multi-Scale for Joint Segmentation and Deformable Medical Image Registration

• URL: http://arxiv.org/abs/2409.19658v1
• Date: Sun, 29 Sep 2024 11:11:04 GMT
• Title: Dual-Attention Frequency Fusion at Multi-Scale for Joint Segmentation and Deformable Medical Image Registration
• Authors: Hongchao Zhou, Shunbo Hu,
• Abstract summary: We propose a multi-task learning framework based on dual attention frequency fusion (DAFF-Net) DAFF-Net simultaneously achieves the segmentation masks and dense deformation fields in a single-step estimation. Experiments on three public 3D brain magnetic resonance imaging (MRI) datasets demonstrate that the proposed DAFF-Net and its unsupervised variant outperform state-of-the-art registration methods.
• Score: 2.6089354079273512
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deformable medical image registration is a crucial aspect of medical image analysis. In recent years, researchers have begun leveraging auxiliary tasks (such as supervised segmentation) to provide anatomical structure information for the primary registration task, addressing complex deformation challenges in medical image registration. In this work, we propose a multi-task learning framework based on multi-scale dual attention frequency fusion (DAFF-Net), which simultaneously achieves the segmentation masks and dense deformation fields in a single-step estimation. DAFF-Net consists of a global encoder, a segmentation decoder, and a coarse-to-fine pyramid registration decoder. During the registration decoding process, we design the dual attention frequency feature fusion (DAFF) module to fuse registration and segmentation features at different scales, fully leveraging the correlation between the two tasks. The DAFF module optimizes the features through global and local weighting mechanisms. During local weighting, it incorporates both high-frequency and low-frequency information to further capture the features that are critical for the registration task. With the aid of segmentation, the registration learns more precise anatomical structure information, thereby enhancing the anatomical consistency of the warped images after registration. Additionally, due to the DAFF module's outstanding ability to extract effective feature information, we extend its application to unsupervised registration. Extensive experiments on three public 3D brain magnetic resonance imaging (MRI) datasets demonstrate that the proposed DAFF-Net and its unsupervised variant outperform state-of-the-art registration methods across several evaluation metrics, demonstrating the effectiveness of our approach in deformable medical image registration.

Related papers

• LDM-Morph: Latent diffusion model guided deformable image registration [2.8195553455247317]
  We propose LDM-Morph, an unsupervised deformable registration algorithm for medical image registration. LDM-Morph integrated features extracted from the latent diffusion model (LDM) to enrich the semantic information. Extensive experiments on four public 2D cardiac image datasets show that the proposed LDM-Morph framework outperformed existing state-of-the-art CNNs- and Transformers-based registration methods.
  arXiv  Detail & Related papers  (2024-11-23T03:04:36Z)
• Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention [1.1155836879100416]
  We propose a Modality-agnostic Domain Generalizable Network (MADGNet) for medical image segmentation. MFMSA block refines the process of spatial feature extraction, particularly in capturing boundary features. E-SDM mitigates information loss in multi-task learning with deep supervision.
  arXiv  Detail & Related papers  (2024-05-10T07:34:36Z)
• SDR-Former: A Siamese Dual-Resolution Transformer for Liver Lesion Classification Using 3D Multi-Phase Imaging [59.78761085714715]
  This study proposes a novel Siamese Dual-Resolution Transformer (SDR-Former) framework for liver lesion classification. The proposed framework has been validated through comprehensive experiments on two clinical datasets. To support the scientific community, we are releasing our extensive multi-phase MR dataset for liver lesion analysis to the public.
  arXiv  Detail & Related papers  (2024-02-27T06:32:56Z)
• Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Medical Image Segmentation [49.57907601086494]
  Medical image segmentation plays a crucial role in computer-aided diagnosis. We propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised medical image (DEC-Seg)
  arXiv  Detail & Related papers  (2023-12-26T12:56:31Z)
• Self-Supervised Correction Learning for Semi-Supervised Biomedical Image Segmentation [84.58210297703714]
  We propose a self-supervised correction learning paradigm for semi-supervised biomedical image segmentation. We design a dual-task network, including a shared encoder and two independent decoders for segmentation and lesion region inpainting. Experiments on three medical image segmentation datasets for different tasks demonstrate the outstanding performance of our method.
  arXiv  Detail & Related papers  (2023-01-12T08:19:46Z)
• Joint segmentation and discontinuity-preserving deformable registration: Application to cardiac cine-MR images [74.99415008543276]
  Most deep learning-based registration methods assume that the deformation fields are smooth and continuous everywhere in the image domain. We propose a novel discontinuity-preserving image registration method to tackle this challenge, which ensures globally discontinuous and locally smooth deformation fields. A co-attention block is proposed in the segmentation component of the network to learn the structural correlations in the input images. We evaluate our method on the task of intra-subject-temporal image registration using large-scale cinematic cardiac magnetic resonance image sequences.
  arXiv  Detail & Related papers  (2022-11-24T23:45:01Z)
• ACSGRegNet: A Deep Learning-based Framework for Unsupervised Joint Affine and Diffeomorphic Registration of Lumbar Spine CT via Cross- and Self-Attention Fusion [4.068962439293273]
  This study proposes a novel end-to-end deep learning-based framework for medical image registration. ACSGRegNet integrates a cross-attention module for establishing inter-image feature correspondences and a self-attention module for intra-image anatomical structures aware. Our method achieved an average Dice of 0.963 and an average distance error of 0.321mm, which are better than the state-of-the-art (SOTA)
  arXiv  Detail & Related papers  (2022-08-04T13:13:48Z)
• SearchMorph:Multi-scale Correlation Iterative Network for Deformable Registration [2.417545540754701]
  We propose an unsupervised multi-scale correlation iterative registration network (SearchMorph) Our proposed method achieves higher registration accuracy and a lower folding point ratio than the state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-06-27T06:37:02Z)
• Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain Adaptation [61.01704175938995]
  In this paper, we propose a novel Bidirectional Global-to-Local (BiGL) adaptation framework under a UDA scheme. Specifically, a bidirectional image synthesis and segmentation module is proposed to segment the brain tumor. The proposed method outperforms several state-of-the-art unsupervised domain adaptation methods by a large margin.
  arXiv  Detail & Related papers  (2021-05-17T10:11:45Z)
• 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)
• JSSR: A Joint Synthesis, Segmentation, and Registration System for 3D Multi-Modal Image Alignment of Large-scale Pathological CT Scans [27.180136688977512]
  We propose a novel multi-task learning system, JSSR, based on an end-to-end 3D convolutional neural network. The system is optimized to satisfy the implicit constraints between different tasks in an unsupervised manner. It consistently outperforms conventional state-of-the-art multi-modal registration methods.
  arXiv  Detail & Related papers  (2020-05-25T16:30:02Z)

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.