Echocardiogram View Conversion using Clinically Constrained Conditional GAN

Gu, Ang Nan; Jafari, Mohammad H.; Luong, Christina; Tsang, Teresa S.M.; Abolmaesumi, Purang

doi:10.1109/isbi48211.2021.9434066

Cited by 2 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These echocardiographic views are acquired by scanning the patient while positioning the transducer at particular angles and positions with respect to the heart. These clinical procedures require specialized personnel to manually navigate the probe towards the correct imaging plane, which can be challenging for a novice operator ( 41 ). Moreover, the sonographers’ intense workload has put them at risk for health problems such work-related musculoskeletal illnesses ( 42 ).…”

Section: Artificial Intelligence Applications For Echocardiography Ac...mentioning

confidence: 99%

“…On the other hand, Gu et al ( 41 ) used view conversion, US image characteristics and anatomical knowledge to anticipate what an unseen view might resemble as the user moves the transducer. Based on a learned A4C-to-A2C mapping, the team suggested a novel constrained conditional GAN to produce geometrically accurate and aesthetically pleasing A2C images.…”

Section: Artificial Intelligence Applications For Echocardiography Ac...mentioning

confidence: 99%

See 1 more Smart Citation

Assisted probe guidance in cardiac ultrasound: A review

Ferraz

Coimbra²,

Pedrosa³

2023

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Echocardiography is the most frequently used imaging modality in cardiology. However, its acquisition is affected by inter-observer variability and largely dependent on the operator’s experience. In this context, artificial intelligence techniques could reduce these variabilities and provide a user independent system. In recent years, machine learning (ML) algorithms have been used in echocardiography to automate echocardiographic acquisition. This review focuses on the state-of-the-art studies that use ML to automate tasks regarding the acquisition of echocardiograms, including quality assessment (QA), recognition of cardiac views and assisted probe guidance during the scanning process. The results indicate that performance of automated acquisition was overall good, but most studies lack variability in their datasets. From our comprehensive review, we believe automated acquisition has the potential not only to improve accuracy of diagnosis, but also help novice operators build expertise and facilitate point of care healthcare in medically underserved areas.

show abstract

Section: Artificial Intelligence Applications For Echocardiography Ac...mentioning

confidence: 99%

Section: Artificial Intelligence Applications For Echocardiography Ac...mentioning

confidence: 99%