Yazar "Varela, Marta" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim
    Öğe
    LA-Net: A Multi-Task Deep Network for the Segmentation of the Left Atrium
    (Institute of Electrical and Electronics Engineers Inc., 2022) Uslu, Fatmatülzehra; Varela, Marta; Boniface, Georgia; Mahenthran, Thakshayene; Chubb, Henry; Bharath, Anil A.
    Although atrial fibrillation (AF) is the most common sustained atrial arrhythmia, treatment success for this condition remains suboptimal. Information from magnetic resonance imaging (MRI) has the potential to improve treatment efficacy, but there are currently few automatic tools for the segmentation of the atria in MR images. In the study, we propose a LA-Net, a multi-task network optimised to simultaneously generate left atrial segmentation and edge masks from MRI. LA-Net includes cross attention modules (CAMs) and enhanced decoder modules (EDMs) to purposefully select the most meaningful edge information for segmentation and smoothly incorporate it into segmentation masks at multiple-scales. We evaluate the performance of LA-Net on two MR sequences: late gadolinium enhanced (LGE) atrial MRI and atrial short axis balanced steady state free precession (bSSFP) MRI. LA-Net gives Hausdorff distances of 12.43 mm and Dice scores of 0.92 on the LGE (STACOM 2018) dataset and Hausdorff distances of 17.41 mm and Dice scores of 0.90 on the bSSFP (in-house) dataset without any post-processing, surpassing previously proposed segmentation networks, including U-Net and SEGANet. Our method allows automatic extraction of information about the LA from MR images, which can play an important role in the management of AF patients.
  • Küçük Resim Yok
    Öğe
    SA-net: A sequence aware network for the segmentation of the left atrium in cine MRI datasets
    (IEEE Computer Society, 2021) Uslu, Fatmatülzehra; Varela, Marta
    The segmentation of the left atrium (LA) in CINE MRI is a prerequisite for the calculation of LA functional parameters and may be useful when selecting treatments for atrial fibrillation patients. CINE MRI usually captures both the LA and the left ventricle. The similarities between the LA and other cardiac structures complicate the segmentation of the LA and can lead to poor performance of standard 2D segmentation networks. In this study, we present SA-Net, a deep network which implicitly discriminates LA slices from non-LA slices during segmentation, with a sequence modulator using interslice correlations in a global context. Our experiments, conducted on an in-house dataset with 4710-mm thick bSSFP MR image stacks, show that SA-Net leads to good quality segmentation of the LA, with a mean Dice score of 0.89 and a mean Jaccard index of 0.80, outperforming the U-Net.
  • Küçük Resim
    Öğe
    A Semi-Automatic Method To Segment The Left Atrium in MR Volumes With Varying Slice Numbers
    (Ieee, 2020) Uslu, Fatmatülzehra; Varela, Marta; Bharath, Anil A.
    Atrial fibrillation (AF) is the most common sustained arrhythmia and is associated with dramatic increases in mortality and morbidity. Atrial cine MR images are increasingly used in the management of this condition, but there are few specific tools to aid in the segmentation of such data. Some characteristics of atrial cine MR (thick slices, variable number of slices in a volume) preclude the direct use of traditional segmentation tools. When combined with scarcity of labelled data and similarity of the intensity and texture of the left atrium (LA) to other cardiac structures, the segmentation of the LA in CINE MRI becomes a difficult task. To deal with these challenges, we propose a semi-automatic method to segment the left atrium (LA) in MR images, which requires an initial user click per volume. The manually given location information is used to generate a chamber location map to roughly locate the LA, which is then used as an input to a deep network with slightly over 0:5 million parameters. A tracking method is introduced to pass the location information across a volume and to remove unwanted structures in segmentation maps. According to the results of our experiments conducted in an in-house MRI dataset, the proposed method outperforms the U-Net [1] with a margin of 20 mm on Hausdorff distance and 0:17 on Dice score, with limited manual interaction.