Atrial Scar Segmentation via Potential Learning in the Graph-Cut Framework

Li, Lei; Yang, Guang; Wu, Fuping; Wong, Tom; Mohiaddin, Raad H.; Firmin, David; Keegan, Jenny; Xu, Lingchao; Zhuang, Xiahai

doi:10.1007/978-3-030-12029-0_17

Cited by 5 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent advancements in deep learning techniques have made neural networks the primary tool for image segmentation. A study by Li et al [15] proposed a method that combines CNN with graph-cut by using convolutional networks to derive weights for the graph-cut edges, treating the patch as a node centred on the atrial edge. This approach dramatically improves segmentation accuracy, especially when dealing with two targets that exhibit apparent data imbalance.…”

Section: Releated Work 21 Scar Segmentationmentioning

confidence: 99%

Edge and dense attention U-net for atrial scar segmentation in LGE-MRI

Li,

Liu,

et al. 2024

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

The segmentation of atrial scars in LGE-MRI images has huge potential value for clinical diagnosis and subsequent treatment. In clinical practice, atrial scars are usually manually calibrated by experienced experts, which is time-consuming and prone to errors. However, automatic segmentation also faces difficulties due to myocardial scars' small size and variable shape. The present study introduces a dual branch network, incorporating edge attention, and deep supervision strategy. Edge attention is introduced to fully utilize the spatial relationship between the scar and the atrium. Besides, dense attention is embedded in bottom layer to solve feature disappearance. At the same time, deep supervision accelerates the convergence of the model and improves segmentation accuracy. The experiments were conducted on the 2022 atrial and scar segmentation challenge dataset. The results demonstrate that the proposed method has achieved superior performance.

show abstract

Section: Releated Work 21 Scar Segmentationmentioning

confidence: 99%

Edge and dense attention U-net for atrial scar segmentation in LGE-MRI

Li,

Liu,

et al. 2024

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

show abstract

“…Li et al . [16] proposed a hybrid approach that combined a graph-cuts framework with CNNs for automatic scar segmentation, and extended their work with a multi-scale CNN to learn local and global features simultaneously. Chen et al .…”

Section: Related Workmentioning

confidence: 99%

“…Yang et al [15] used superpixel over-segmentation for feature extraction and a supervised classification step via stacked sparse autoencoders for LA scar segmentation. Li et al [16] proposed a hybrid approach that combined a graph-cuts framework with CNNs for automatic scar segmentation, and extended their work with a multi-scale CNN to learn local and global features simultaneously. Chen et al [17] used multi-task learning for simultaneous LA and scar segmentation, but did not explicitly learn the spatial relationship between the two regions.…”

Section: Related Workmentioning

confidence: 99%

FK-means: automatic atrial fibrosis segmentation using fractal-guided K-means clustering with Voronoi-clipping feature extraction of anatomical structures

Firouznia,

Henningsson,

Carlhäll

2023

Interface Focus.

View full text Add to dashboard Cite

Assessment of left atrial (LA) fibrosis from late gadolinium enhancement (LGE) magnetic resonance imaging (MRI) adds to the management of patients with atrial fibrillation. However, accurate assessment of fibrosis in the LA wall remains challenging. Excluding anatomical structures in the LA proximity using clipping techniques can reduce misclassification of LA fibrosis. A novel FK-means approach for combined automatic clipping and automatic fibrosis segmentation was developed. This approach combines a feature-based Voronoi diagram with a hierarchical 3D K-means fractal-based method. The proposed automatic Voronoi clipping method was applied on LGE-MRI data and achieved a Dice score of 0.75, similar to the score obtained by a deep learning method (3D UNet) for clipping (0.74). The automatic fibrosis segmentation method, which uses the Voronoi clipping method, achieved a Dice score of 0.76. This outperformed a 3D UNet method for clipping and fibrosis classification, which had a Dice score of 0.69. Moreover, the proposed automatic fibrosis segmentation method achieved a Dice score of 0.90, using manual clipping of anatomical structures. The findings suggest that the automatic FK-means analysis approach enables reliable LA fibrosis segmentation and that clipping of anatomical structures in the atrial proximity can add to the assessment of atrial fibrosis.

show abstract

“…However, they only used handcrafted intensity features, which consisted of limited information. In contrast, Li et al (2018b) proposed a hybrid approach utilizing a graph-cuts framework combined with CNNs to predict edge weights of the graph for automatic scar segmentation. They extended their work by introducing multi-scale CNN (MS-CNN) to learn local and global features simultaneously (Li et al, 2020b).…”

Section: La Scar Segmentation and Quantificationmentioning

confidence: 99%

“…However, as mentioned in Section 4.2.2 volume overlap measures (such as Dice) could be highly sensitive to the mismatch of small structures (namely scars here), so in instances it will impose disproportionate penalties on the algorithm. To mitigate the effect of small size of scars, Li et al (2020b) proposed to project the appearance of scars onto the LA surface for both ground truth and automatic segmentation results, and then calculate the Dice scores of scars on the projected LA surface instead of on the 3D volume (Wu et al, 2018;Li et al, 2018bLi et al, , 2020b. Furthermore, Li et al (2020b,a) computed the generalized Dice (GDice) of scars from the projected LA surface for more interpretation.…”

Section: La Scar Measuresmentioning

confidence: 99%

Medical Image Analysis on Left Atrial LGE MRI for Atrial Fibrillation Studies: A Review

Li¹,

Zimmer²,

Schnabel³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Late gadolinium enhancement magnetic resonance imaging (LGE MRI) is commonly used to visualize and quantify left atrial (LA) scars. The position and extent of scars provide important information of the pathophysiology and progression of atrial fibrillation (AF). Hence, LA scar segmentation and quantification from LGE MRI can be useful in computerassisted diagnosis and treatment stratification of AF patients. Since manual delineation can be time-consuming and subject to intra-and inter-expert variability, automating this computing is highly desired, which nevertheless is still challenging and under-researched.This paper aims to provide a systematic review on computing methods for LA cavity, wall, scar and ablation gap segmentation and quantification from LGE MRI, and the related literature for AF studies. Specifically, we first summarize AF-related imaging techniques, particularly LGE MRI. Then, we review the methodologies of the four computing tasks in detail, and summarize the validation strategies applied in each task. Finally, the possible future developments are outlined, with a brief survey on the potential clinical applications of the aforementioned methods. The review shows that the research into this topic is still in early stages. Although several methods have been proposed, especially for LA segmentation, there is still large scope for further algorithmic developments due to performance issues related to the high variability of enhancement appearance and differences in image acquisition.

show abstract

Atrial Scar Segmentation via Potential Learning in the Graph-Cut Framework

Cited by 5 publications

References 14 publications

Edge and dense attention U-net for atrial scar segmentation in LGE-MRI

Edge and dense attention U-net for atrial scar segmentation in LGE-MRI

FK-means: automatic atrial fibrosis segmentation using fractal-guided K-means clustering with Voronoi-clipping feature extraction of anatomical structures

Medical Image Analysis on Left Atrial LGE MRI for Atrial Fibrillation Studies: A Review

Contact Info

Product

Resources

About