Publication result detail

Deep-learning based automatic determination of cardiac planes in survey MRI data

JURČA, J.; HARABIŠ, V.; JAKUBÍČEK, R.; HOLEČEK, T.; NEMČEKOVÁ, P.; OUŘEDNÍČEK, P.; CHMELÍK, J.

Original Title

Deep-learning based automatic determination of cardiac planes in survey MRI data

English Title

Deep-learning based automatic determination of cardiac planes in survey MRI data

Type

Paper in proceedings (conference paper)

Original Abstract

Inference of the radiological planes of the heart in MRI is a crucial step for valid data acquisition to examine the structure and function of the human heart in detail. In this paper, we present a deep learning model for automatic inference of the radiological plane of the heart from 3D survey sequences. The proposed neural network is based on the V-Net~\cite{vnet} architecture that has been developed to perform inference on the radiological positions of the hearts. The network is designed to take a 3D image as input and generate a regressed heatmap of probable plane positions as output. The results show that the proposed method is feasible for automatic geometry planning. It has the potential to increase the efficiency of medical imaging. The presented networks show that they can locate cardiac landmarks even from data with anisotropic voxels. It can improve the accuracy and speed of diagnosis, allowing for faster and more effective treatment.

English abstract

Inference of the radiological planes of the heart in MRI is a crucial step for valid data acquisition to examine the structure and function of the human heart in detail. In this paper, we present a deep learning model for automatic inference of the radiological plane of the heart from 3D survey sequences. The proposed neural network is based on the V-Net~\cite{vnet} architecture that has been developed to perform inference on the radiological positions of the hearts. The network is designed to take a 3D image as input and generate a regressed heatmap of probable plane positions as output. The results show that the proposed method is feasible for automatic geometry planning. It has the potential to increase the efficiency of medical imaging. The presented networks show that they can locate cardiac landmarks even from data with anisotropic voxels. It can improve the accuracy and speed of diagnosis, allowing for faster and more effective treatment.

Keywords

heart axis determination, regression, deep-learning, MRI

Key words in English

heart axis determination, regression, deep-learning, MRI

Authors

JURČA, J.; HARABIŠ, V.; JAKUBÍČEK, R.; HOLEČEK, T.; NEMČEKOVÁ, P.; OUŘEDNÍČEK, P.; CHMELÍK, J.

RIV year

2025

Released

04.01.2024

Publisher

Springer

Location

Cham

ISBN

978-3-031-49061-3

Book

MEDICON’23 and CMBEBIH’23

Edition

93

ISBN

1680-0737

Periodical

IFMBE Proceedings

Volume

93

State

French Republic

Pages from

285

Pages to

292

Pages count

8

URL

https://link.springer.com/chapter/10.1007/978-3-031-49062-0_31

BibTex

@inproceedings{BUT185645,
  author="Jan {Jurča} and Vratislav {Harabiš} and Roman {Jakubíček} and Tomáš {Holeček} and Petra {Nemčeková} and Petr {Ouředníček} and Jiří {Chmelík}",
  title="Deep-learning based automatic determination of cardiac planes in survey MRI data",
  booktitle="MEDICON’23 and CMBEBIH’23",
  year="2024",
  series="93",
  journal="IFMBE Proceedings",
  volume="93",
  number="1",
  pages="285--292",
  publisher="Springer",
  address="Cham",
  doi="10.1007/978-3-031-49062-0\{_}31",
  isbn="978-3-031-49061-3",
  issn="1680-0737",
  url="https://link.springer.com/chapter/10.1007/978-3-031-49062-0_31"
}