Cardiac MRI Image Segmentation for Left Ventricle and Right Ventricle using Deep Learning

TL;DR

This study compares deep learning models for segmenting left and right ventricles in cardiac MRI images, focusing on their accuracy and ability to generalize across diverse datasets.

Contribution

It evaluates three models across multiple datasets, highlighting the importance of data augmentation and training strategies for model generalizability.

Findings

3-D U-Net outperformed other models in segmentation accuracy.

Data augmentation improved model robustness across datasets.

Models trained on diverse data showed better generalization.

Abstract

The goal of this project is to use magnetic resonance imaging (MRI) data to provide an end-to-end analytics pipeline for left and right ventricle (LV and RV) segmentation. Another aim of the project is to find a model that would be generalizable across medical imaging datasets. We utilized a variety of models, datasets, and tests to determine which one is well suited to this purpose. Specifically, we implemented three models (2-D U-Net, 3-D U-Net, and DenseNet), and evaluated them on four datasets (Automated Cardiac Diagnosis Challenge, MICCAI 2009 LV, Sunnybrook Cardiac Data, MICCAI 2012 RV). While maintaining a consistent preprocessing strategy, we tested the performance of each model when trained on data from the same dataset as the test data, and when trained on data from a different dataset than the test dataset. Data augmentation was also used to increase the adaptability of the models. The results were compared to determine performance and generalizability.