A Survey on Left Ventricle Segmentation Techniques in Cardiac Short Axis MRI

Irshad, Mehreen; Sharif, Muhammad; Yasmin, Mussarat; Khan, Arbab Wajid Ullah

doi:10.2174/1573405613666170117124934

Cited by 8 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Though the problem of heart chamber segmentation has been tackled a number of times, automatic segmentation of the right ventricle in particular is still a challenge. [10][11][12] Other studies have approached this problem using similar methods as the one presented, but many share the same dataset of healthy adult patients, and still others use a dataset containing only a few patients. [13][14][15][16][17] Our dataset is unique in not only its larger size, but also its inclusion of children and adolescents as well as adults, all of whom present with cardiac pathology.…”

Section: Resultsmentioning

confidence: 99%

Fully automated segmentation of the right ventricle in patients with repaired Tetralogy of Fallot using U-Net

Tran

Halicek

Dormer

et al. 2020

Medical Imaging 2020: Biomedical Applications in Molecular, Structural, and Functional Imaging

View full text Add to dashboard Cite

Cardiac magnetic resonance (CMR) imaging is considered the standard imaging modality for volumetric analysis of the right ventricle (RV), an especially important practice in the evaluation of heart structure and function in patients with repaired Tetralogy of Fallot (rTOF). In clinical practice, however, this requires time-consuming manual delineation of the RV endocardium in multiple 2-dimensional (2D) slices at multiple phases of the cardiac cycle. In this work, we employed a U-Net based 2D convolutional neural network (CNN) classifier in the fully automatic segmentation of the RV blood pool. Our dataset was comprised of 5,729 short-axis cine CMR slices taken from 100 individuals with rTOF. Training of our CNN model was performed on images from 50 individuals while validation was performed on images from 10 individuals. Segmentation results were evaluated by Dice similarity coefficient (DSC) and Hausdorff distance (HD). Use of the CNN model on our testing group of 40 individuals yielded a median DSC of 90% and a median 95 th percentile HD of 5.1 mm, demonstrating good performance in these metrics when compared to literature results. Our preliminary results suggest that our deep learning-based method can be effective in automating RV segmentation.

show abstract

Section: Resultsmentioning

confidence: 99%

Fully automated segmentation of the right ventricle in patients with repaired Tetralogy of Fallot using U-Net

Tran

Halicek

Dormer

et al. 2020

Medical Imaging 2020: Biomedical Applications in Molecular, Structural, and Functional Imaging

View full text Add to dashboard Cite

show abstract

“…Among the techniques used in comparison Table 6, some are utilizing traditional image handling techniques as (Hu et al, 2014) showing the average dice matrix of 91% using local binary fitting model and dynamic programming techniques. Similarly, (Irshad et al, 2018) Proposed method is equipped for elimination of manual LV segmentation and for empowering the utilization of segmentation algorithms that are previously used. In the future, deep learning can be utilized for this process.…”

Section: Results Comparison Of Proposed Work With Existing Techniquesmentioning

confidence: 99%

Discrete light sheet microscopic segmentation of left ventricle using morphological tuning and active contours

Irshad

Sharif

Yasmin

et al. 2021

Microscopy Res & Technique

Self Cite

View full text Add to dashboard Cite

show abstract

“…Within this sub-section, we put forward a comparative study of segmentation methods that will be enhanced by synthesis tables, for each one of the above-cited categories. The classification will be strongly guided by the works presented in [7] [24] [25]. Based on their experimental conditions, segmentation methods belonging to the first and the second categories are synthesized respectively in Among the different presented algorithms, the one that meets our needs will be chosen according to qualitative and quantitative criteria based on each algorithm score.…”

Section: Comparative Studymentioning

confidence: 99%

Left ventricular segmentation based on a parallel watershed transformation towards an accurate heart function evaluation

Mahmoudi

Ameur

Ammari

et al. 2020

IET Image Processing

View full text Add to dashboard Cite

Magnetic Resonance Imaging (MRI) has emerged as the golden reference for cardiac examination. This modality allows the assessment of human cardiovascular morphology, functioning, and perfusion. Although a couple of challenging issues, such as the cardiac MR image's features and the large variability of images among several patients, still influences the cardiac cavities' segmentation and needs to be carried out. In this paper, we have profoundly reviewed and fully compared semi-automated segmentation methods performed on cardiac Cine-MR short-axis images for the evaluation of the left ventricular functions. However, the number of parameters handled by the synthesized works is limited if not null. For the sake of ensuring the highest coverage of the LV parameters computing, we have introduced a parallel watershedbased approach to segment the left ventricular allowing hence the computation of six parameters (End-Diastolic Volume, End-Systolic Volume, Ejection Fraction, Cardiac output, Stroke Volume and Left Ventricular Mass). An algorithm is associated with main considered measurements. The experimental results that were obtained through studying twenty patients' MRI data base, demonstrate the accuracy of our approach for estimating real values of the maximal set of parameters thanks to a faithful segmentation of the myocardium.

show abstract

A Survey on Left Ventricle Segmentation Techniques in Cardiac Short Axis MRI

Cited by 8 publications

References 0 publications

Fully automated segmentation of the right ventricle in patients with repaired Tetralogy of Fallot using U-Net

Fully automated segmentation of the right ventricle in patients with repaired Tetralogy of Fallot using U-Net

Discrete light sheet microscopic segmentation of left ventricle using morphological tuning and active contours

Left ventricular segmentation based on a parallel watershed transformation towards an accurate heart function evaluation

Contact Info

Product

Resources

About