Joint Left Atrial Segmentation and Scar Quantification Based on a DNN with Spatial Encoding and Shape Attention

• URL: http://arxiv.org/abs/2006.13011v1
• Date: Tue, 23 Jun 2020 13:55:29 GMT
• Title: Joint Left Atrial Segmentation and Scar Quantification Based on a DNN with Spatial Encoding and Shape Attention
• Authors: Lei Li, Xin Weng, Julia A. Schnabel, Xiahai Zhuang
• Abstract summary: We propose an end-to-end deep neural network (DNN) which can simultaneously segment the left atrial (LA) cavity and quantify LA scars. The proposed framework incorporates the continuous spatial information of the target by introducing a spatially encoded (SE) loss. For LA segmentation, the proposed method reduced the mean Hausdorff distance from 36.4 mm to 20.0 mm compared to the 3D basic U-Net.
• Score: 21.310508988246937
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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 36.4 mm to 20.0 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 performance.

Related papers

• Automatically Segment the Left Atrium and Scars from LGE-MRIs Using a Boundary-focused nnU-Net [8.27752923297381]
  We propose to automatically segment LA cavity and quantify LA scars with late gadolinium enhancement Magnetic Resonance Imagings (LGE-MRIs) Specifically, a focus on LA boundary pixels is achieved during training, which provides a more accurate boundary prediction. Experiments on the LAScarQS 2022 dataset demonstrated our model's superior performance on the LA cavity and LA scar segmentation.
  arXiv  Detail & Related papers  (2023-04-27T10:05:37Z)
• Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images [55.83984261827332]
  In this paper, we propose a novel reliable multi-scale wavelet-enhanced transformer network. We develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module. Our proposed method achieves better segmentation accuracy with a high degree of reliability as compared to other state-of-the-art segmentation approaches.
  arXiv  Detail & Related papers  (2022-12-01T07:32:56Z)
• TC-Net: Triple Context Network for Automated Stroke Lesion Segmentation [0.5482532589225552]
  We propose a new network, Triple Context Network (TC-Net), with the capture of spatial contextual information as the core. Our network is evaluated on the open dataset ATLAS, achieving the highest score of 0.594, Hausdorff distance of 27.005 mm, and average symmetry surface distance of 7.137 mm.
  arXiv  Detail & Related papers  (2022-02-28T11:12:16Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• Residual Moment Loss for Medical Image Segmentation [56.72261489147506]
  Location information is proven to benefit the deep learning models on capturing the manifold structure of target objects. Most existing methods encode the location information in an implicit way, for the network to learn. We propose a novel loss function, namely residual moment (RM) loss, to explicitly embed the location information of segmentation targets.
  arXiv  Detail & Related papers  (2021-06-27T09:31:49Z)
• JAS-GAN: Generative Adversarial Network Based Joint Atrium and Scar Segmentations on Unbalanced Atrial Targets [11.507811388835348]
  We propose an inter-cascade generative adversarial network, namely JAS-GAN, to segment the unbalanced atrial targets. Jas-GAN investigates an adaptive attention cascade to automatically correlate the segmentation tasks of the unbalanced atrial targets. It mainly forces the estimated joint distribution of LA and atrial scars to match the real ones.
  arXiv  Detail & Related papers  (2021-05-01T12:33:02Z)
• 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)
• DONet: Dual Objective Networks for Skin Lesion Segmentation [77.9806410198298]
  We propose a simple yet effective framework, named Dual Objective Networks (DONet), to improve the skin lesion segmentation. Our DONet adopts two symmetric decoders to produce different predictions for approaching different objectives. To address the challenge of large variety of lesion scales and shapes in dermoscopic images, we additionally propose a recurrent context encoding module (RCEM)
  arXiv  Detail & Related papers  (2020-08-19T06:02:46Z)
• AtrialJSQnet: A New Framework for Joint Segmentation and Quantification of Left Atrium and Scars Incorporating Spatial and Shape Information [22.162571400010467]
  Left atrial (LA) and atrial scar segmentation from late gadolinium enhanced magnetic resonance imaging (LGE MRI) is an important task in clinical practice. Previous methods normally solved the two tasks independently and ignored the intrinsic spatial relationship between LA and scars. We develop a new framework, namely AtrialJSQnet, where LA segmentation, scar projection onto the LA surface, and scar quantification are performed simultaneously in an end-to-end style.
  arXiv  Detail & Related papers  (2020-08-11T14:44:19Z)
• DSU-net: Dense SegU-net for automatic head-and-neck tumor segmentation in MR images [30.747375849126925]
  We propose a Dense SegU-net (DSU-net) framework for automatic nasopharyngeal carcinoma (NPC) segmentation in MRI. To combat the potential vanishing-gradient problem, we introduce dense blocks which can facilitate feature propagation and reuse. Our proposed architecture outperforms the existing state-of-the-art segmentation networks.
  arXiv  Detail & Related papers  (2020-06-11T09:33:41Z)
• MetricUNet: Synergistic Image- and Voxel-Level Learning for Precise CT Prostate Segmentation via Online Sampling [66.01558025094333]
  We propose a two-stage framework, with the first stage to quickly localize the prostate region and the second stage to precisely segment the prostate. We introduce a novel online metric learning module through voxel-wise sampling in the multi-task network. Our method can effectively learn more representative voxel-level features compared with the conventional learning methods with cross-entropy or Dice loss.
  arXiv  Detail & Related papers  (2020-05-15T10:37:02Z)

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.