Automatic Detection of the End-Diastolic and End-Systolic from 4D Echocardiographic Images

Abboud, Anas A.; Rahmat, Rahmita Wirza O. K.; Kadiman, Suhaini; Dimon, Mohd Zamrin; Nurliyana, Lili; Saripan, M. Iqbal; Khaleel, Hasan H.

doi:10.3844/jcssp.2015.230.240

Cited by 9 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, we propose a method for semi-automatic segmentation of the right ventricle to measure the stroke volume from four Dimensions (4D) echocardiography, based on a novel analysing for the complex geometrical structure and function of the right ventricle, (Rahmat et al, 2013;Anas et al, 2014).…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Cavity Segmentation and Stroke Volume Measurement Methods From Echocardiographic Images: Review

Abboud¹,

Rahmat²,

Kadiman³

et al. 2014

Journal of Computer Science

Self Cite

View full text Add to dashboard Cite

The complexity and criticality of heart disease diagnosis and treatment have frequently attracted the attention of researchers to develop approaches that can handle accurate clinical assessments. One of these complexities is measuring the Right Ventricle stroke volume. Therefore, different cardiac imaging techniques have been developed to help specialists in their regular clinical work and in the operating theatre to assist in the diagnosis, monitoring of the treatment and to ensure the success of a cardiac intervention as far as possible. Echocardiography is one of the cardiac imaging techniques and is considered as the most effective imaging technique as it is minimally invasive, quick and the cheapest method. Many studies have been conducted on Right Ventricle assessment from echocariographic images. This review is aimed at presenting the previous technical elements and algorithms used to measure the ventricle stroke volume from echocardiographic images. The review focuses on the five technical approaches that have been used, which are pre-processing, End-Distally (ED) and End-Systolic (ES) frame detection, cavity segmentation, the stoke volume measurement and 3D reconstruction. Finally, a summary will conclude this study.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

Cavity Segmentation and Stroke Volume Measurement Methods From Echocardiographic Images: Review

Abboud¹,

Rahmat²,

Kadiman³

et al. 2014

Journal of Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Other techniques take advantage of the fact that the left ventricle expands the most during ED and contracts the most during ES. [7], [3], and [8] utilized the speckle tracing or image segmentation to follow the left ventricle volume changes. However, the noise in cardiac ultrasound imaging or discontinuous edges makes these approaches prone to significant inaccuracies.…”

Section: Introductionmentioning

confidence: 99%

Preprocessing and Frame Level Classification Framework for Cardiac Phase Detection in 2D Echocardiography

Singh,

Darji,

Sarvaiya

et al. 2023

Preprint

View full text Add to dashboard Cite

The first and critical step of accurate heart function analysis (i.e., ventricles volume, Ejection Fraction, and stroke volume measurement) in echocardiography is the detection of end-diastole (ED) and end-systole (ES) frames. Detecting these frames is challenging due to variations in cardiac structure, heart rate associated with clinical conditions, and the low-resolution nature of echo sequences. Several deep learning techniques have recently emerged, primarily combining convolutional neural networks (CNN) and recurrent neural networks (RNN). These models were trained on a range of datasets, including open-access sources like CAMUS, PACS, and EchoNet-Dynamic, as well as private datasets. The largest open-access dataset, EchoNet Dynamic, has poor echo phase detection compared to other datasets. This suggests that the dataset has noise, which is removed in this study using three preprocessing steps: Noise reduction using heart rate formulation, Video frame synchronization, and Non-oscillating Mean absolute frame difference (MAFD). Additionally, this study formulates the echo phase detection problem as frame-level binary classification, distinguishing between diastole and systole phases. The proposed architecture takes the echo sequence as an input and a customized time-distributed CNN extracts spatial features from each frame. These frame features are fed into a bidirectional long short-term memory (BLSTM) network, capturing temporal information, followed by a classification layer. The model is trained on the pre-processed EchoNet-Dynamic dataset. Compared to true labels, an average absolute frame distance (aaFD) of 1.02 and 1.04 frames is achieved for ED and ES frames, respectively. Moreover, it operates with an inference time of less than 65 ms for an input sequence consisting of 32 frames on a graphics processing unit (GPU).

show abstract

“…Other methods for ED and ES frame detection use either segmentation or speckle tracking-based approaches for tracking the changes in LV volume [7]- [9]. Segmentation-based approaches characterize the ED and ES frames with the assumption that the largest and smallest LV segmented cross-sections in a cardiac cycle correspond to the ED and ES frames.…”

Section: Introductionmentioning

confidence: 99%

Cardiac Phase Detection in Echocardiograms With Densely Gated Recurrent Neural Networks and Global Extrema Loss

Dezaki

Liao

Luong

et al. 2019

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Accurate detection of end-systolic (ES) and end-diastolic (ED) frames in an echocardiographic cine series can be difficult but necessary pre-processing step for the development of automatic systems to measure cardiac parameters. The detection task is challenging due to variations in cardiac anatomy and heart rate often associated with pathological conditions. We formulate this problem as a regression problem and propose several deep learningbased architectures that minimize a novel global extrema structured loss function to localize the ED and ES frames. The proposed architectures integrate convolution neural networks (CNNs)-based image feature extraction model and recurrent neural networks (RNNs) to model temporal dependencies between each frame in a sequence. We explore two CNN architectures: DenseNet and ResNet, and four RNN architectures: long short-term memory, bi-directional LSTM, gated recurrent unit (GRU), and Bi-GRU, and compare the performance of these models. The optimal deep learning model consists of a DenseNet and GRU trained with the proposed loss function. On average, we achieved 0.20 and 1.43 frame mismatch for the ED and ES frames, respectively, which are within reported inter-observer variability for the manual detection of these frames.

show abstract

Automatic Detection of the End-Diastolic and End-Systolic from 4D Echocardiographic Images

Cited by 9 publications

References 17 publications

Cavity Segmentation and Stroke Volume Measurement Methods From Echocardiographic Images: Review

Cavity Segmentation and Stroke Volume Measurement Methods From Echocardiographic Images: Review

Preprocessing and Frame Level Classification Framework for Cardiac Phase Detection in 2D Echocardiography

Cardiac Phase Detection in Echocardiograms With Densely Gated Recurrent Neural Networks and Global Extrema Loss

Contact Info

Product

Resources

About