Key result
UNET model with inception modules outperforms baseline for LV endocardium segmentation, achieving ~93% Dice score.
Why the study?
Left ventricle endocardium segmentation is a major task in diagnosing heart conditions, but improved deep learning methods are needed for efficient segmentation on MRI images.
Does an improved UNET model with inception modules improve left ventricle endocardium segmentation accuracy in MRI images compared to baseline UNET?
Does an improved UNET model with inception modules improve left ventricle endocardium segmentation accuracy in MRI images compared to baseline UNET?
Absolute Event Rate: 93.34% vs 90.26%
An improved UNET architecture incorporating inception modules achieves high accuracy (Dice score 93.34%) in segmenting the left ventricle endocardium from short-axis CMR images.
The automatic diagnosis of cardiovascular diseases has received much attention in the deep learning field. In this context, the segmentation of the left ventricle endocardium constitutes a major task in diagnosing heart conditions such as health failure and hypertrophic cardiomyopathy. The objective of this paper is to propose a "deep convolution network" for segmenting the internal cavity of the left ventricle (endocardium) using MRI images. In particular, we design an improved UNET model which handles additional inception modules for efficiently segmenting the internal cavity of the left ventricle. Our approach has been validated on the Sunnybrook Cardiac Data (SCD) dataset and has showed promising results in terms of precision. More specifically, the improved UNET largely outperforms the baseline UNET model and many existing state-of-the-art methods.
No takes yet. Share an insight, caveat, or question.
Bekkouche et al. (2023) studied Left ventricle segmentation (n=45). Improved UNET with inception modules vs. Baseline UNET was evaluated on Dice similarity coefficient on the test set. The improved UNET model with inception modules achieved a Dice similarity coefficient of 93.34% for left ventricle endocardium segmentation, outperforming the baseline UNET model.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: