Evaluation of the LVivo Image Quality Scoring (IQS)

Heart Diseases Clinical Trial

Official title:

Evaluation of the LVivo Image Quality Scoring (IQS)

Clinical Trial Details — Status: Completed

Administrative data

• NCT number: NCT05563701
• Other study ID #: CR2P0021
• Status: Completed
• Start date: September 5, 2022
• Est. completion date: September 13, 2022

Study information

• Verified date: September 2022
• Source: DiA Imaging Analysis Ltd
• Contact: n/a
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

The study includes two parts:

Part 1:

• 100 examinations of patient referred for echo evaluation, containing clips that were acquired from the 4CH apical view were collected retrospectively. Each study includes 10 clips that represent typical user scanning errors

• Offline evaluation of the system (by batch processing) shall be performed by comparing the system output to preliminary quality tagging by experienced sonographers

Part 2:

• Live scans of apical 4CH clips of patients with indication for POCUS examination will be performed by POC physicians

• LVivo IQS shall be used (on Lumify) during the scan for patients that meet inclusion criteria until 50 exams will be collected. 3 sec of each scan shall be saved, and Image quality score (IQS) shall be documented

• Saved scans shall be reviewed by an expert physician to determine whether they are clinically interpretable

Description:

Part 1 Total of 424 examination were collected from two medical centers. Participants that were referred to routine echo examinations and signed an informed consent were enrolled to the study. The image acquisition was done using ultrasound devices available in the medical centers. In addition Lumify ultrasound device was supplied by the sponsor.

Each examination contained 10 clips, each representing a different scanning scenario where the image acquisition contained transitions between common user "acquisition error" to correctly acquired images.

The examinations in DICOM format and echo reports were collected after anonymization, the patient details were documented in a study log that was stored in the medical center.

The collected clips were tagged for image quality by experienced sonographers. The distribution of the collected data according to ultrasound devices, age, gender and LV function was analyzed.

The data was randomly split into training and clinical validation sets, such that the proportion of data according to data distribution was maintained and the data set for the clinical evaluation will contain 100 patient examinations.

The LVivo IQS algorithm will be applied to the clinical validation set automatically by batch processing. The image quality score provided by the LVivo IQS will be compared to the image quality tagging by the sonographers

Part 2 The trial is designed as a prospective multicenter study, enrolling 50 patients at two medical centers. In each medical center Lumify ultrasound devices on which the LVivo IQS demo software will be installed will be provided for image acquisition. The image acquisition will be done by POC medical doctors, at different stages of their internship, that received POCUS training during their medical studies and are using ultrasound devices in accordance with their routine workflow. The scans will be done in different POC units including ER, ICU and internal departments.

Recruitment information / eligibility

• Status: Completed
• Enrollment: 164
• Est. completion date: September 13, 2022
• Est. primary completion date: September 13, 2022
• Accepts healthy volunteers: No
• Gender: All
• Age group: 18 Years and older

Eligibility

Inclusion Criteria:

Part 1 Study:

1. Age =18

2. Referred to routine Echo examination

Part 2 Study:

1. Age =18

2. Indication for POCUS

Exclusion Criteria:

Part 1 Study:

1. Subjects who fail to meet any inclusion criteria

Part 2 Study:

1. Subjects who fail to meet any inclusion criteria

2. Image quality 1-2 according to ACEP June 2018 [11]

Related Conditions & MeSH terms

• Angina Pectoris
• Angina, Unstable
• Arrhythmia, Cardiac
• Arrhythmias, Cardiac
• Congestive Heart Failure
• Heart Diseases
• Heart Failure
• Lung Diseases
• Shock
• Unstable Angina

Locations

Country	Name	City	State
Israel	Soroka university medical center	Beer-Sheva

Sponsors (1)

Lead Sponsor	Collaborator
DiA Imaging Analysis Ltd

Country where clinical trial is conducted

Israel, 

References & Publications (13)

Blanco P, Volpicelli G. Common pitfalls in point-of-care ultrasound: a practical guide for emergency and critical care physicians. Crit Ultrasound J. 2016 Dec;8(1):15. Epub 2016 Oct 26. Review. — View Citation

Dall T. et al. The Complexities of Physician Supply and Demand: Projections From 2019 to 2034. Association Of American Medical Collage, 2021.

Dixon, W.J., Massey, F.J. Introduction to Statistical Analysis. 4th Edition McGraw-Hill, 1983. pp. 105-107

Goldman, L. et al. Echocardiography. Elsevier, Inc, 2020. pp. 253-260

Hashim A, Tahir MJ, Ullah I, Asghar MS, Siddiqi H, Yousaf Z. The utility of point of care ultrasonography (POCUS). Ann Med Surg (Lond). 2021 Nov 2;71:102982. doi: 10.1016/j.amsu.2021.102982. eCollection 2021 Nov. — View Citation

Johri AM, Galen B, Kirkpatrick JN, Lanspa M, Mulvagh S, Thamman R. ASE Statement on Point-of-Care Ultrasound during the 2019 Novel Coronavirus Pandemic. J Am Soc Echocardiogr. 2020 Jun;33(6):670-673. doi: 10.1016/j.echo.2020.04.017. Epub 2020 Apr 15. Review. — View Citation

Kumar V. There is No Substitute for Human Intelligence. Indian J Crit Care Med. 2021 May;25(5):486-488. doi: 10.5005/jp-journals-10071-23832. — View Citation

Liu B.R et al. Emergency Ultrasound Standard Reporting Guidelines. ACEP, 2018. pp. 2-44.

Nagata Y, Kado Y, Onoue T, Otani K, Nakazono A, Otsuji Y, Takeuchi M. Impact of image quality on reliability of the measurements of left ventricular systolic function and global longitudinal strain in 2D echocardiography. Echo Res Pract. 2018 Mar;5(1):27-39. doi: 10.1530/ERP-17-0047. Epub 2018 Feb 5. — View Citation

Narang A, Bae R, Hong H, Thomas Y, Surette S, Cadieu C, Chaudhry A, Martin RP, McCarthy PM, Rubenson DS, Goldstein S, Little SH, Lang RM, Weissman NJ, Thomas JD. Utility of a Deep-Learning Algorithm to Guide Novices to Acquire Echocardiograms for Limited Diagnostic Use. JAMA Cardiol. 2021 Jun 1;6(6):624-632. doi: 10.1001/jamacardio.2021.0185. — View Citation

Russell FM, Herbert A, Ferre RM, Zakeri B, Echeverria V, Peterson D, Wallach P. Development and implementation of a point of care ultrasound curriculum at a multi-site institution. Ultrasound J. 2021 Feb 21;13(1):9. doi: 10.1186/s13089-021-00214-w. — View Citation

Smistad E, Ostvik A, Salte IM, Melichova D, Nguyen TM, Haugaa K, Brunvand H, Edvardsen T, Leclerc S, Bernard O, Grenne B, Lovstakken L. Real-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning. IEEE Trans Ultrason Ferroelectr Freq Control. 2020 Dec;67(12):2595-2604. doi: 10.1109/TUFFC.2020.2981037. Epub 2020 Nov 24. — View Citation

Ünlü S, Duchenne J, Mirea O, Pagourelias ED, Bézy S, Cvijic M, Beela AS, Thomas JD, Badano LP, Voigt JU; EACVI-ASE Industry Standardization Task Force. Impact of apical foreshortening on deformation measurements: a report from the EACVI-ASE Strain Standardization Task Force. Eur Heart J Cardiovasc Imaging. 2020 Mar 1;21(3):337-343. doi: 10.1093/ehjci/jez189. — View Citation

* Note: There are 13 references in all — Click here to view all references

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Part 1: Overall agreement of 75% between image quality classification by LVivo IQS and the data tagging by experienced sonographers		Up to 24 weeks
Primary	Part 2: 80% of the Exams with image quality 3-5 by visual estimation, received at least "Medium" image quality by LVivo IQS		Up to 24 weeks
Primary	Part 2: 90% of these cases (when at least "Medium" image quality is indicated by LVivo IQS) are clinically interpretable		Up to 24 weeks

External Links

•   EchoNous official cite
•   FDA official cite, "FDA Authorizes Marketing of First Cardiac Ultrasound Software That Uses Artificial Intelligence to Guide User", February 2020.
•   Ultrasight official site