Our research is dedicated to advancing machine learning and deep learning models for accurately segmenting the left atrium, epicardial fat, and fibrosis in CT and MRI scans. This initiative aims to enhance diagnostic accuracy and optimize treatment planning in cardiovascular healthcare.
Marjan Firouznia
Principal Research Engineer
I am a postdoc researcher at CMIV, specializes in precise segmentation of the left atrium, epicardial fat, and fibrosis using CT and MRI.
Advancing Machine Learning Models for LA Fat and Fibrosis Segmentation
About me
CV
Employment
- 2022 Postdoc, Linkoping University in Sweden
- 2020-2021 Postdoctoral Researcher, Amirkabir University of Technology, Iran
- 2019-2020 Research Associate, Case Western Reserve University, Ohio, USA
- 2018-2019 Assistant Professor, Isfahan University, Iran
- 2017 Research Visit, Calabria University, Italy
Educational Background
- 2012-2017 Ph.D. of Electrical Engineering, Amirkabir University of Technology
- 2008 –2011 M.Sc. of Computer Engineering, Azad University of Qazvin
- 2003-2007 B.Sc. of Computer Engineering, Azad University of Najafabad
Publications
2025
Head-to-Head Comparison between MRI and CT in the Evaluation of Volume and Quality of Epicardial Adipose Tissue
RADIOLOGY-CARDIOTHORACIC IMAGING, Vol. 7, Article e240531
(Article in journal)
https://dx.doi.org/10.1148/ryct.240531
Poincare guided geometric UNet for left atrial epicardial adipose tissue segmentation in Dixon MRI images
Scientific Reports, Vol. 15, Article 25549
(Article in journal)
https://dx.doi.org/10.1038/s41598-025-10110-1
2023
Dataset and code for "FK-means: Automatic Atrial Fibrosis Segmentation using Fractal-guided K-means Clustering with Voronoi-Clipping Feature Extraction of Anatomical Structures": FKmeans for fibrosis segmentation
(Data set)
https://dx.doi.org/10.48360/m803-yp37
FK-means: automatic atrial fibrosis segmentation using fractal-guided K-means clustering with Voronoi-clipping feature extraction of anatomical structures
Interface Focus, Dataset and code for "FK-means: Automatic Atrial Fibrosis Segmentation using Fractal-guided K-means Clustering with Voronoi-Clipping Feature Extraction of Anatomical Structures": FKmeans for fibrosis segmentation, Vol. 13, Article 20230033
(Article in journal)
https://dx.doi.org/10.1098/rsfs.2023.0033
