Ejection Fraction Classification in Transthoracic Echocardiography Using a Deep Learning Approach

Silva, João Figueira; Silva, Jorge Miguel; Guerra, Antonio; Matos, Sérgio; Costa, Carlos

doi:10.1109/cbms.2018.00029

Cited by 23 publications

(22 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An end-to-end neural network approach for automatic estimation of EF directly from ultrasound images is feasible, as demonstrated [20]. The downside of an end-to-end approach is that it results in a black-box method in which clinicians cannot visually inspect, verify, and correct the EF measurements.…”

Section: Discussionmentioning

confidence: 96%

“…Jafari et al [19] presented a similar approach in 2019, optimized for mobile devices, although without view classification, requiring users to specify which view is being scanned, and therefore not fully automatic. Silva et al [20] proposed to do automatic EF estimation as a direct classification problem instead, dividing EF into four categories.…”

Section: A Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning

Smistad

Østvik

Salte

et al. 2020

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

View full text Add to dashboard Cite

Volume and ejection fraction (EF) measurements of the left ventricle (LV) in 2-D echocardiography are associated with a high uncertainty not only due to interobserver variability of the manual measurement, but also due to ultrasound acquisition errors such as apical foreshortening. In this work, a real-time and fully automated EF measurement and foreshortening detection method is proposed. The method uses several deep learning components, such as view classification, cardiac cycle timing, segmentation and landmark extraction, to measure the amount of foreshortening, LV volume, and EF. A data set of 500 patients from an outpatient clinic was used to train the deep neural networks, while a separate data set of 100 patients from another clinic was used for evaluation, where LV volume and EF were measured by an expert using clinical protocols and software. A quantitative analysis using 3-D ultrasound showed that EF is considerably affected by apical foreshortening, and that the proposed method can detect and quantify the amount of apical foreshortening. The bias

show abstract

Section: Discussionmentioning

confidence: 96%

Section: A Related Workmentioning

confidence: 99%

Real-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning

Smistad

Østvik

Salte

et al. 2020

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

View full text Add to dashboard Cite

show abstract

“…with filters of shape N × N × N, a cascade of three asymmetric filters of shapes N × 1 × 1, 1 × N × 1, and 1 × 1 × N is used. Such a factorization of convolution operations reduces the computational cost by reducing the number of parameters (Szegedy et al, 2016) and has been used effectively in 3D medical image processing (Silva et al, 2018). Filter size is N = 5 (with a stride of 1) for the first set of convolution operations and N = 3 afterward.…”

Section: Neural Network Architecturementioning

confidence: 99%

Predicting Body Mass Index From Structural MRI Brain Images Using a Deep Convolutional Neural Network

Vakli

Deák-Meszlényi

Auer

et al. 2020

Front. Neuroinform.

View full text Add to dashboard Cite

“…Madani et al [213] trained a six layer CNN to classify between 15 views (12 video and 3 still) of transthoracic echocardiogram images, achieving better results than certified echocardographers. In [214] the authors created a residual 3D CNN for ejetion fraction classification from transthoracic echocardiogram images. They used 8715 exams each one with 30 sequential frames of the apical 4 chamber to train and test their method achieving preliminary results.…”

Section: Echocardiographymentioning

confidence: 99%

Deep Learning in Cardiology

Bizopoulos

Koutsouris

2019

IEEE Rev. Biomed. Eng.

140

View full text Add to dashboard Cite

The medical field is creating large amount of data that physicians are unable to decipher and use efficiently. Moreover, rule-based expert systems are inefficient in solving complicated medical tasks or for creating insights using big data. Deep learning has emerged as a more accurate and effective technology in a wide range of medical problems such as diagnosis, prediction and intervention. Deep learning is a representation learning method that consists of layers that transform the data non-linearly, thus, revealing hierarchical relationships and structures. In this review we survey deep learning application papers that use structured data, signal and imaging modalities from cardiology. We discuss the advantages and limitations of applying deep learning in cardiology that also apply in medicine in general, while proposing certain directions as the most viable for clinical use.

show abstract

Ejection Fraction Classification in Transthoracic Echocardiography Using a Deep Learning Approach

Cited by 23 publications

References 19 publications

Real-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning

Real-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning

Predicting Body Mass Index From Structural MRI Brain Images Using a Deep Convolutional Neural Network

Deep Learning in Cardiology

Contact Info

Product

Resources

About