A Persistent Homology-Based Topological Loss for CNN-Based Multiclass Segmentation of CMR-Reference-Cited by-同舟云学术

A Persistent Homology-Based Topological Loss for CNN-Based Multiclass Segmentation of CMR

Published:2023-01 Issue:1 Volume:42 Page:3-14
ISSN:0278-0062
Container-title:IEEE Transactions on Medical Imaging
language:
Short-container-title:IEEE Trans. Med. Imaging

Author:

Byrne Nick¹,Clough James R.¹,Valverde Israel¹,Montana Giovanni²^ORCID,King Andrew P.¹^ORCID

Affiliation:

1. School of BMEIS, KCL, London, U.K.

2. Warwick Manufacturing Group, University of Warwick, Coventry, U.K.

Funder

Engineering and Physical Sciences Research Council (EPSRC) Programme

Wellcome Trust Innovative Engineering for Health

Wellcome EPSRC Centre for Medical Engineering, School of Biomedical Engineering and Imaging Sciences (BMEIS), King’s College London

National Institute for Health and Care Research (NIHR) Biomedical Research Centre at Guys and St Thomas NHS Foundation Trust (GSTT) and King’s College London

NIHR through the Doctoral Research Fellow

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Computer Science Applications,Radiological and Ultrasound Technology,Software

Link

http://xplorestaging.ieee.org/ielx7/42/10003062/09872052.pdf?arnumber=9872052

Reference42 articles.

1. Automated cardiovascular magnetic resonance image analysis with fully convolutional networks

2. Explicit Topological Priors for Deep-Learning Based Image Segmentation Using Persistent Homology

3. Evaluation of algorithms for Multi-Modality Whole Heart Segmentation: An open-access grand challenge

4. Deep small bowel segmentation with cylindrical topological constraints;yeon shin;arXiv 2007 08674,2020

5. Uncertainty quantification in CNN-based surface prediction using shape priors;tóthová;Shape in Medical Imaging ShapeMI 2018,2018

Cited by 8 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Anatomically plausible segmentations: Explicitly preserving topology through prior deformations;Medical Image Analysis;2024-10

2. Projected pooling loss for red nucleus segmentation with soft topology constraints;Journal of Medical Imaging;2024-07-09

3. Mutual learning with reliable pseudo label for semi-supervised medical image segmentation;Medical Image Analysis;2024-05

4. PEA-Net: A progressive edge information aggregation network for vessel segmentation;Computers in Biology and Medicine;2024-02

5. Three-dimensional topology-based analysis segments volumetric and spatiotemporal fluorescence microscopy;Biological Imaging;2023-12-14