MSWS Network + Boundary2Patches (LAScarQS2022)

Queen Mary University of London (Khan et al.)

Cardiac MRI

Filter catalog by Modality:
Cardiac MRI

Cardiac chamber segmentation

Filter catalog by Disease / Trait:
Structural Heart & Cardiomyopathy

LGE scar burden

Filter catalog by Disease / Trait:
Structural Heart & Cardiomyopathy

Segmentation

Filter catalog by Task Type:
Segmentation & Detection

CNN (3D)

Filter catalog by Architecture:
Convolutional (CNN)

PyTorch

Filter catalog by Framework:
PyTorch

code View code

Model weights not public. Contact creators for more information.

Two-stage pipeline that segments the left atrium and quantifies atrial scar tissue from 3D late-gadolinium-enhancement cardiac MRI, supporting atrial-fibrillation ablation planning. A Multi-Scale Weight Sharing network first delineates the atrial cavity, then a boundary-patch method segments scar tissue around the detected wall. Developed at Queen Mary University of London for the LAScarQS 2022 MICCAI/STACOM segmentation challenge.

memory Specifications

description Publication

Sequential Segmentation of the Left Atrium and Atrial Scars Using a Multi-scale Weight Sharing Network and Boundary-Based Processing open_in_new

2022 · original paper

database Training & evaluation data

LAScarQS 2022 open_in_new

train

Task 1: 60 3D LGE-MRI volumes with LA cavity + scar annotations. Task 2: 130 3D LGE-MRI volumes with LA cavity annotations only, from 4 clinical centres.

science Capabilities & performance

LA cavity segmentation (Task 1)

Segmentation Cardiac chamber segmentation

0.938 Dice LAScarQS 2022 (Task 1, validation) · internal

LA scar segmentation (Task 1)

Segmentation LGE scar burden

0.558 Dice LAScarQS 2022 (Task 1, validation) · internal

LA cavity segmentation (Task 2)