Automated detection and localization of pericardial effusion from point-of-care cardiac ultrasound examination

Yıldız, İlkay; Leo, Megan; Vaziri, Ashkan; Feldman, James A.

doi:10.1007/s11517-023-02855-6

Cited by 3 publications

(7 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Depending on the type of software, it helps detect key structures for performing a specific medical procedure, such as cannulation, finding the optimal ultrasound plane for imaging of the heart, lungs, or abdominal organs [ 4 , 10 ] as well as setting the appropriate image quality, and performing measurements, including complex Doppler measurements [ 11 ]. At the same time, it significantly reduces the time needed to learn how to perform imaging and the time to acquire clinically significant images, and it improves the accuracy of the obtained results [ 2 , 10 , 12 , 13 ].…”

Section: Introductionmentioning

confidence: 99%

Ultrasonographic Applications of Novel Technologies and Artificial Intelligence in Critically Ill Patients

Mika,

Gola,

Gil-Mika

et al. 2024

JPM

View full text Add to dashboard Cite

The diagnostic process in Intensive Care Units has been revolutionized by ultrasonography and accelerated by artificial intelligence. Patients in critical condition are often sonoanatomically challenging, with time constraints being an additional stress factor. In this paper, we describe the technology behind the development of AI systems to support diagnostic ultrasound in intensive care units. Among the AI-based solutions, the focus was placed on systems supporting cardiac ultrasound, such as Smart-VTI, Auto-VTI, SmartEcho Vue, AutoEF, Us2.ai, and Real Time EF. Solutions to assist hemodynamic assessment based on the evaluation of the inferior vena cava, such as Smart-IVC or Auto-IVC, as well as to facilitate ultrasound assessment of the lungs, such as Smart B-line or Auto B-line, and to help in the estimation of gastric contents, such as Auto Gastric Antrum, were also discussed. All these solutions provide doctors with support by making it easier to obtain appropriate diagnostically correct ultrasound images by automatically performing time-consuming measurements and enabling real-time analysis of the obtained data. Artificial intelligence will most likely be used in the future to create advanced systems facilitating the diagnostic and therapeutic process in intensive care units.

show abstract

Section: Introductionmentioning

confidence: 99%

Ultrasonographic Applications of Novel Technologies and Artificial Intelligence in Critically Ill Patients

Mika,

Gola,

Gil-Mika

et al. 2024

JPM

View full text Add to dashboard Cite

show abstract

“… 6 E‐FAST is a rapid ultrasound examination used to screen for pericardial, abdominal free fluid, and thoracic injuries. 2 , 7 , 8 , 9 It allows clinicians to diagnose significant trauma at the bedside quickly and without ionizing radiation. 7 A positive E‐FAST exam has been demonstrated as a strong independent predictor for the need of surgical intervention and critical decision‐making in trauma cases.…”

Section: Introductionmentioning

confidence: 99%

“… 7 A positive E‐FAST exam has been demonstrated as a strong independent predictor for the need of surgical intervention and critical decision‐making in trauma cases. 8 Therefore, the timely detection of free fluid with the E‐FAST exam has been shown to reduce the time to surgical intervention and improve resource utilization. 8 One of the key components of the E‐FAST protocol is the detection and evaluation of pleural effusion.…”

Section: Introductionmentioning

confidence: 99%

“… 8 Therefore, the timely detection of free fluid with the E‐FAST exam has been shown to reduce the time to surgical intervention and improve resource utilization. 8 One of the key components of the E‐FAST protocol is the detection and evaluation of pleural effusion. However, the diagnostic ultrasound examination in E‐FAST relies on the operator's proficiency, and correct technical execution and image interpretation are essential for achieving high diagnostic accuracy, 5 particularly in trauma situations.…”

Section: Introductionmentioning

confidence: 99%

“… 11 In recent years, deep learning models have been employed to address diagnostic tasks in E‐FAST in various studies. 8 , 12 , 13 , 14 , 15 Lin et al. 14 employed the U‐net to detect and segment ultrasonic images of ascites.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated detection and segmentation of pleural effusion on ultrasound images using an Attention U‐net

Huang,

Lin,

Cao

et al. 2023

J Applied Clin Med Phys

View full text Add to dashboard Cite

BackgroundUltrasonic for detecting and evaluating pleural effusion is an essential part of the Extended Focused Assessment with Sonography in Trauma (E‐FAST) in emergencies. Our study aimed to develop an Artificial Intelligence (AI) diagnostic model that automatically identifies and segments pleural effusion areas on ultrasonography.MethodsAn Attention U‐net and a U‐net model were used to detect and segment pleural effusion on ultrasound images of 848 subjects through fully supervised learning. Sensitivity, specificity, precision, accuracy, F1 score, the receiver operating characteristic (ROC) curve, and the area under the curve (AUC) were used to assess the model's effectiveness in classifying the data. The dice coefficient was used to evaluate the segmentation performance of the model.ResultsIn 10 random tests, the Attention U‐net and U‐net ’s average sensitivity of 97% demonstrated that the pleural effusion was well detectable. The Attention U‐net performed better at identifying negative images than the U‐net, which had an average specificity of 91% compared to 86% for the U‐net. Additionally, the Attention U‐net was more accurate in predicting the pleural effusion region because its average dice coefficient was 0.86 as opposed to the U‐net's average dice coefficient of 0.82.ConclusionsThe Attention U‐net showed excellent performance in detecting and segmenting pleural effusion on ultrasonic images, which is expected to enhance the operation and application of E‐FAST in clinical work.

show abstract

Applications of Deep Learning in Trauma Radiology: A Narrative Review

Cheng,

Ooyang,

Kang

et al. 2024

Biomedical Journal

View full text Add to dashboard Cite

Automated detection and localization of pericardial effusion from point-of-care cardiac ultrasound examination

Cited by 3 publications

References 64 publications

Ultrasonographic Applications of Novel Technologies and Artificial Intelligence in Critically Ill Patients

Ultrasonographic Applications of Novel Technologies and Artificial Intelligence in Critically Ill Patients

Automated detection and segmentation of pleural effusion on ultrasound images using an Attention U‐net

Applications of Deep Learning in Trauma Radiology: A Narrative Review

Contact Info

Product

Resources

About