Download PDFOpen PDF in browser

Deep Learning Models for Left Atrial Segmentation in MRI

EasyChair Preprint 11574

5 pagesDate: December 19, 2023

Abstract

The left atrium (LA) segmentation is a crucial and essential procedure in the field of cardiac imaging due to its significance in cardiovascular health and its role in diagnosing heart conditions. Magnetic resonance imaging (MRI) is a non-invasive medical imaging technique that has become indispensable in the cardiovascular field, especially for visualizing and evaluating atrial myopathy. In recent years, deep learning has emerged as the approach with the highest adoption rate for segmenting cardiac images. For the purpose of segmenting the left atrium from MRI images, we applied three Unet variation architectures to compare the optimal one, and we experimented with dice and cross-entropy loss.

Keyphrases: Cardiac MRI, Segmentation, U-Net, deep learning, left atrial

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@booklet{EasyChair:11574,
  author    = {Meriem Triki and Mohammed Ammar},
  title     = {Deep Learning Models for Left Atrial Segmentation in MRI},
  howpublished = {EasyChair Preprint 11574},
  year      = {EasyChair, 2023}}
Download PDFOpen PDF in browser