Open AccessPosted Content
Joint Left Atrial Segmentation and Scar Quantification Based on a DNN with Spatial Encoding and Shape Attention
TLDR
An end-to-end deep neural network (DNN) which can simultaneously segment the left atrial (LA) cavity and quantify LA scars and a shape attention (SA) mechanism is embedded into a two-task network to perform the joint LA segmentation and scar quantification.Abstract:
We propose an end-to-end deep neural network (DNN) which can simultaneously segment the left atrial (LA) cavity and quantify LA scars The framework incorporates the continuous spatial information of the target by introducing a spatially encoded (SE) loss based on the distance transform map Compared to conventional binary label based loss, the proposed SE loss can reduce noisy patches in the resulting segmentation, which is commonly seen for deep learning-based methods To fully utilize the inherent spatial relationship between LA and LA scars, we further propose a shape attention (SA) mechanism through an explicit surface projection to build an end-to-end-trainable model Specifically, the SA scheme is embedded into a two-task network to perform the joint LA segmentation and scar quantification Moreover, the proposed method can alleviate the severe class-imbalance problem when detecting small and discrete targets like scars We evaluated the proposed framework on 60 LGE MRI data from the MICCAI2018 LA challenge For LA segmentation, the proposed method reduced the mean Hausdorff distance from 364 mm to 200 mm compared to the 3D basic U-Net using the binary cross-entropy loss For scar quantification, the method was compared with the results or algorithms reported in the literature and demonstrated better performanceread more
Citations
More filters
Journal ArticleDOI
AtrialJSQnet: A New Framework for Joint Segmentation and Quantification of Left Atrium and Scars Incorporating Spatial and Shape Information
Lei Li,Lei Li,Lei Li,Merve Güner Oytun,Veronika A. Zimmer,Veronika A. Zimmer,Julia A. Schnabel,Julia A. Schnabel,Xiahai Zhuang +8 more
TL;DR: Wang et al. as mentioned in this paper proposed a shape attention mechanism via an implicit surface projection to utilize the inherent correlation between LA cavity and scars, which achieved competitive performance over the state-of-the-art.
Posted Content
AtrialJSQnet: A New Framework for Joint Segmentation and Quantification of Left Atrium and Scars Incorporating Spatial and Shape Information
Lei Li,Lei Li,Lei Li,Veronika A. Zimmer,Veronika A. Zimmer,Julia A. Schnabel,Julia A. Schnabel,Xiahai Zhuang +7 more
TL;DR: A mechanism of shape attention via an implicit surface projection to utilize the inherent correlation between LA cavity and scars is proposed and embedded into a multi-task architecture to perform joint LA segmentation and scar quantification.
Journal ArticleDOI
AWSnet: An Auto-weighted Supervision Attention Network for Myocardial Scar and Edema Segmentation in Multi-sequence Cardiac Magnetic Resonance Images
Kai-Ni Wang,Xin Yang,Juzheng Miao,Li Li,Jing Yao,Ping Zhou,Wufeng Xue,Guang-Quan Zhou,Xiahai Zhuang,Dong Ni +9 more
TL;DR: In this paper , a coarse-to-fine framework is proposed to boost the small myocardial pathology region segmentation with shape prior knowledge, where the coarse segmentation model identifies the left ventricle myocardia structure as a shape prior, and the fine segmentation models integrates a pixel-wise attention strategy with an auto-weighted supervision model to learn and extract salient pathological structures from the multi-sequence CMR data.
Posted Content
Multi-Modality Pathology Segmentation Framework: Application to Cardiac Magnetic Resonance Images
TL;DR: This work presents an automatic cascade pathology segmentation framework based on multi-modality CMR images that aims to segment the anatomical structure where the pathology may exist, and it can provide a spatial prior for the pathological region segmentation.
Posted Content
Recognition and standardization of cardiac MRI orientation via multi-tasking learning and deep neural networks
Ke Zhang,Xiahai Zhuang +1 more
TL;DR: This paper proposes a framework to categorize the orientation for recognition and standardization via deep neural networks, and embeds the orientation recognition network in a Cardiac MRI Orientation Adjust Tool, i.e., CMRadjustNet.
References
More filters
Journal ArticleDOI
Worldwide Epidemiology of Atrial Fibrillation: A Global Burden of Disease 2010 Study
Sumeet S. Chugh,Rasmus Havmoeller,Kumar Narayanan,David Singh,Michiel Rienstra,Emelia J. Benjamin,Richard F. Gillum,Younghoon Kim,John H. McAnulty,Zhi Jie Zheng,Mohammad H. Forouzanfar,Mohsen Naghavi,George A. Mensah,Majid Ezzati,Christopher J L Murray +14 more
TL;DR: Evidence of progressive increases in overall burden, incidence, prevalence, and AF-associated mortality between 1990 and 2010 is provided, with significant public health implications.
Journal ArticleDOI
Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
Konstantinos Kamnitsas,Christian Ledig,Virginia F. J. Newcombe,Joanna P. Simpson,Andrew D. Kane,David K. Menon,Daniel Rueckert,Ben Glocker +7 more
TL;DR: An efficient and effective dense training scheme which joins the processing of adjacent image patches into one pass through the network while automatically adapting to the inherent class imbalance present in the data, and improves on the state-of-the‐art for all three applications.
Book ChapterDOI
Uncertainty-Aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
TL;DR: A novel uncertainty-aware semi-supervised framework for left atrium segmentation from 3D MR images that can effectively leverage the unlabeled data by encouraging consistent predictions of the same input under different perturbations.
Journal ArticleDOI
Evaluation of current algorithms for segmentation of scar tissue from late Gadolinium enhancement cardiovascular magnetic resonance of the left atrium: an open-access grand challenge
Rashed Karim,R. James Housden,Mayuragoban Balasubramaniam,Zhong Chen,Daniel J. Perry,Ayesha Uddin,Yosra Al-Beyatti,Ebrahim Palkhi,Prince Acheampong,Samantha Obom,Anja Hennemuth,Yingli Lu,Wenjia Bai,Wenzhe Shi,Yi Gao,H. O. Peitgen,Perry Radau,Reza Razavi,Allen Tannenbaum,Daniel Rueckert,Josh Cates,Tobias Schaeffter,Dana C. Peters,Dana C. Peters,Rob S. MacLeod,Kawal Rhode +25 more
TL;DR: A standardised evaluation benchmarking framework for algorithms segmenting fibrosis and scar from LGE CMR images is presented and it is concluded that currently no algorithm is deemed clearly better than others.
Journal ArticleDOI
Fully Automatic Left Atrium Segmentation From Late Gadolinium Enhanced Magnetic Resonance Imaging Using a Dual Fully Convolutional Neural Network
TL;DR: This work has developed AtriaNet, a 16-layer convolutional neural network (CNN) that was tested on the largest known data set for LA segmentation, and to the best of the knowledge, it is the most robust approach that has ever been developed for segmenting LGE-MRIs.