A study investigating variability of left ventricular ejection fraction using manual and automatic processing modes in a single setting

Bresser, P.; Beer, Justin de; Wet, Y. de

doi:10.1016/j.radi.2014.10.002

Cited by 8 publications

(3 citation statements)

References 13 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such strategy has a significant potential for medical imaging analysis, as most of the time, there is a shortage of labeled data. It is not only difficult to get a large dataset labeled because of the manual effort involved, but also the labels may suffer from significant intra/inter-observer variability, specifically amongst less experienced operators [22], [23].…”

Section: Ap2 View Ap4 Viewmentioning

confidence: 99%

Echo-SyncNet: Self-Supervised Cardiac View Synchronization in Echocardiography

Dezaki

Luong

Ginsberg

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

In echocardiography (echo), an electrocardiogram (ECG) is conventionally used to temporally align different cardiac views for assessing critical measurements. However, in emergencies or point-of-care situations, acquiring an ECG is often not an option, hence motivating the need for alternative temporal synchronization methods. Here, we propose Echo-SyncNet, a self-supervised learning framework to synchronize various cross-sectional 2D echo series without any human supervision or external inputs. The proposed framework takes advantage of two types of supervisory signals derived from the input data: spatiotemporal patterns found between the frames of a single cine (intra-view self-supervision) and interdependencies between multiple cines (inter-view self-supervision). The combined supervisory signals are used to learn a featurerich and low dimensional embedding space where multiple echo cines can be temporally synchronized. Two intra-view self-supervisions are used, the first is based on the information encoded by the temporal ordering of a cine (temporal intra-view) and the second on the spatial similarities between nearby frames (spatial intra-view). The inter-view self-supervision is used to promote the learning of similar embeddings for frames captured from the same cardiac phase in different echo views. We evaluate the framework with multiple experiments: 1) Using data from 998 patients, Echo-SyncNet shows promising results for synchronizing Manuscript received ***; accepted ***. Date of publication ***; date of current version ***.

show abstract

Section: Ap2 View Ap4 Viewmentioning

confidence: 99%

Echo-SyncNet: Self-Supervised Cardiac View Synchronization in Echocardiography

Dezaki

Luong

Ginsberg

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

Section: Ap2 View Ap4 Viewmentioning

confidence: 99%

Echo-SyncNet: Self-supervised Cardiac View Synchronization in Echocardiography

Dezaki¹,

Luong²,

Ginsberg³

et al. 2021

Preprint

View full text Add to dashboard Cite

In echocardiography (echo), an electrocardiogram (ECG) is conventionally used to temporally align different cardiac views for assessing critical measurements. However, in emergencies or point-of-care situations, acquiring an ECG is often not an option, hence motivating the need for alternative temporal synchronization methods. Here, we propose Echo-SyncNet, a self-supervised learning framework to synchronize various cross-sectional 2D echo series without any human supervision or external inputs. The proposed framework takes advantage of two types of supervisory signals derived from the input data: spatiotemporal patterns found between the frames of a single cine (intra-view self-supervision) and interdependencies between multiple cines (inter-view self-supervision). The combined supervisory signals are used to learn a featurerich and low dimensional embedding space where multiple echo cines can be temporally synchronized. Two intra-view self-supervisions are used, the first is based on the information encoded by the temporal ordering of a cine (temporal intra-view) and the second on the spatial similarities between nearby frames (spatial intra-view). The inter-view self-supervision is used to promote the learning of similar embeddings for frames captured from the same cardiac phase in different echo views. We evaluate the framework with multiple experiments: 1) Using data from 998 patients, Echo-SyncNet shows promising results for synchronizing Apical 2 chamber and Apical 4 chamber cardiac views, which are acquired spatially perpendicular to each other; 2) Using data from 3070 patients, our experiments reveal that the learned representations of Echo-SyncNet outperform

show abstract

“…However, these advancements raised the possibility of variance in estimating the LVEF [14][15][16] . Once the gated image is acquired, algorithms and software are used to determine the LVEF from the left ventricle at end-systole and end-diastole regions of interest 12- 13 . In patients with coronary artery disease and decreased left ventricular function, LVEF and LV volume values predict survival [21][22][23][24] .…”

Section: Introductionmentioning

confidence: 99%

Comparison of totally automated and manual processing for calculation of left ventricular volumes and ejection fraction using gated myocardial perfusion SPECT

Alshammari¹,

Afzal²

2022

View full text Add to dashboard Cite

ated single-photon emission computed tomography (SPECT) allows for the assessment of myocardial left ventricular ejection fraction and left ventricular volumes. There is conflicting data regarding the difference between automated and manual processing of gated myocardial SPECT images. The purpose of this retrospective “cross-sectional study is to compare the degree of variability between automated and manual processing of Quantitative Gated SPECT algorithms for assessing left ventricular volumes and ejection percent”. Study was carried out in the Nuclear Medicine department “at the Security Forces Hospital, Riyadh, Saudi Arabia, and comprised of 96 participants who “underwent” both stress and “rest gated” myocardial perfusion “imaging” (MPI) from February to May 2021. Data were analyzed “using SPSS for Windows (version 22; IBM Corp., Armonk, NY, USA). The mean of EF, ESV, and EDV on stress test using the automatic technique were 62.46 ± 14.62%, 45.00 ± 37.10 ml, and 107.01 ± 43.70 ml, respectively while using the manual technique were 57.21±14.80%, 44.35±35.93 ml, and 93.26±39.14 ml, respectively. The mean of EF, ESV, and EDV on rest test using the automatic technique were 62.85± 15.47%, 43.44± 36.35 ml, and 104.27±42.51 ml, respectively while using the manual technique were 57.74±15.33%, 43.30±36.42 ml, and 91.72±41.50 ml, respectively. For LVEF and EDV, the difference between automated and manual techniques is statistically significant (p<0.05). However, no “statistically significant difference” exists between automated and manual ESV techniques (p>0.05). Discrepancies were observed that exist by using the fully automated and manual technique for determining LVEF and Left ventricular volumes by gated MPI.

show abstract

A study investigating variability of left ventricular ejection fraction using manual and automatic processing modes in a single setting

Cited by 8 publications

References 13 publications

Echo-SyncNet: Self-Supervised Cardiac View Synchronization in Echocardiography

Echo-SyncNet: Self-Supervised Cardiac View Synchronization in Echocardiography

Echo-SyncNet: Self-supervised Cardiac View Synchronization in Echocardiography

Comparison of totally automated and manual processing for calculation of left ventricular volumes and ejection fraction using gated myocardial perfusion SPECT

Contact Info

Product

Resources

About