Multi-Scale Feature Fusion with Image-Driven Spatial Integration for Left Atrium Segmentation from Cardiac MRI Images
- URL: http://arxiv.org/abs/2502.06615v1
- Date: Mon, 10 Feb 2025 16:12:46 GMT
- Title: Multi-Scale Feature Fusion with Image-Driven Spatial Integration for Left Atrium Segmentation from Cardiac MRI Images
- Authors: Bipasha Kundu, Zixin Yang, Richard Simon, Cristian Linte,
- Abstract summary: We propose a framework that integrates DINOv2 as an encoder with a UNet-style decoder, incorporating multi-scale feature fusion and input image integration.
We validate our approach on the LAScarQS 2022 dataset and demonstrate improved performance with a 92.3% Dice and 84.1% IoU score for giant architecture.
- Score: 0.0
- License:
- Abstract: Accurate segmentation of the left atrium (LA) from late gadolinium-enhanced magnetic resonance imaging plays a vital role in visualizing diseased atrial structures, enabling the diagnosis and management of cardiovascular diseases. It is particularly essential for planning treatment with ablation therapy, a key intervention for atrial fibrillation (AF). However, manual segmentation is time-intensive and prone to inter-observer variability, underscoring the need for automated solutions. Class-agnostic foundation models like DINOv2 have demonstrated remarkable feature extraction capabilities in vision tasks. However, their lack of domain specificity and task-specific adaptation can reduce spatial resolution during feature extraction, impacting the capture of fine anatomical detail in medical imaging. To address this limitation, we propose a segmentation framework that integrates DINOv2 as an encoder with a UNet-style decoder, incorporating multi-scale feature fusion and input image integration to enhance segmentation accuracy. The learnable weighting mechanism dynamically prioritizes hierarchical features from different encoder blocks of the foundation model, optimizing feature selection for task relevance. Additionally, the input image is reintroduced during the decoding stage to preserve high-resolution spatial details, addressing limitations of downsampling in the encoder. We validate our approach on the LAScarQS 2022 dataset and demonstrate improved performance with a 92.3% Dice and 84.1% IoU score for giant architecture compared to the nnUNet baseline model. These findings emphasize the efficacy of our approach in advancing the field of automated left atrium segmentation from cardiac MRI.
Related papers
- Motion-enhancement to Echocardiography Segmentation via Inserting a Temporal Attention Module: An Efficient, Adaptable, and Scalable Approach [4.923733944174007]
We present a novel, computation-efficient alternative where a temporal attention module extracts feature interactions multiple times.
The module can be seamlessly integrated into a wide range of existing CNN- or Transformer-based networks.
Our results confirm TAM's robustness, scalability, and generalizability across diverse datasets and backbones.
arXiv Detail & Related papers (2025-01-24T21:35:24Z) - Perspective+ Unet: Enhancing Segmentation with Bi-Path Fusion and Efficient Non-Local Attention for Superior Receptive Fields [19.71033340093199]
We propose a novel architecture, Perspective+ Unet, to overcome limitations in medical image segmentation.
The framework incorporates an efficient non-local transformer block, named ENLTB, which utilizes kernel function approximation for effective long-range dependency capture.
Experimental results on the ACDC and datasets demonstrate the effectiveness of our proposed Perspective+ Unet.
arXiv Detail & Related papers (2024-06-20T07:17:39Z) - CathFlow: Self-Supervised Segmentation of Catheters in Interventional Ultrasound Using Optical Flow and Transformers [66.15847237150909]
We introduce a self-supervised deep learning architecture to segment catheters in longitudinal ultrasound images.
The network architecture builds upon AiAReSeg, a segmentation transformer built with the Attention in Attention mechanism.
We validated our model on a test dataset, consisting of unseen synthetic data and images collected from silicon aorta phantoms.
arXiv Detail & Related papers (2024-03-21T15:13:36Z) - 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) - 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) - High Quality Segmentation for Ultra High-resolution Images [72.97958314291648]
We propose the Continuous Refinement Model for the ultra high-resolution segmentation refinement task.
Our proposed method is fast and effective on image segmentation refinement.
arXiv Detail & Related papers (2021-11-29T11:53:06Z) - Segmentation of Cardiac Structures via Successive Subspace Learning with
Saab Transform from Cine MRI [29.894633364282555]
We propose a machine learning model, successive subspace learning with the subspace approximation with adjusted bias (Saab) transform, for accurate and efficient segmentation from cine MRI.
Our framework performed better than state-of-the-art U-Net models with 200$times$ fewer parameters in the left ventricle, right ventricle, and myocardium.
arXiv Detail & Related papers (2021-07-22T14:50:48Z) - Joint Motion Correction and Super Resolution for Cardiac Segmentation
via Latent Optimisation [18.887520377396925]
We propose a novel latent optimisation framework that jointly performs motion correction and super resolution for cardiac image segmentations.
Experiments on two cardiac MR datasets show that the proposed framework achieves high performance, comparable to state-of-the-art super-resolution approaches.
arXiv Detail & Related papers (2021-07-08T15:14:00Z) - Weakly-supervised Learning For Catheter Segmentation in 3D Frustum
Ultrasound [74.22397862400177]
We propose a novel Frustum ultrasound based catheter segmentation method.
The proposed method achieved the state-of-the-art performance with an efficiency of 0.25 second per volume.
arXiv Detail & Related papers (2020-10-19T13:56:22Z) - Unsupervised Instance Segmentation in Microscopy Images via Panoptic
Domain Adaptation and Task Re-weighting [86.33696045574692]
We propose a Cycle Consistency Panoptic Domain Adaptive Mask R-CNN (CyC-PDAM) architecture for unsupervised nuclei segmentation in histopathology images.
We first propose a nuclei inpainting mechanism to remove the auxiliary generated objects in the synthesized images.
Secondly, a semantic branch with a domain discriminator is designed to achieve panoptic-level domain adaptation.
arXiv Detail & Related papers (2020-05-05T11:08:26Z)
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.