Deep Learning for Improved Precision and Reproducibility of Left Ventricular Strain in Echocardiography: A Test-Retest Study
Salte, Ivar Mjåland; Østvik, Andreas; Olaisen, Sindre Hellum; Karlsen, Sigve; Dahlslett, Thomas; Smistad, Erik; Eriksen-Volnes, Torfinn Kirknes; Brunvand, Harald; Haugaa, Kristina Ingrid Helena Hermann; Edvardsen, Thor; Dalen, Håvard; Løvstakken, Lasse; Grenne, Bjørnar Leangen
Peer reviewed, Journal article
Published version
![Thumbnail](/ntnu-xmlui/bitstream/handle/11250/3079725/Salte%2bet%2bal.pdf.jpg?sequence=6&isAllowed=y)
View/ Open
Date
2023Metadata
Show full item recordCollections
- Institutt for sirkulasjon og bildediagnostikk [1919]
- Publikasjoner fra CRIStin - NTNU [38294]
- St. Olavs hospital [2536]
Original version
Journal of the American Society of Echocardiography. 2023, . 10.1016/j.echo.2023.02.017Abstract
Aims
Assessment of left ventricular (LV) function by echocardiography is hampered by modest test-retest reproducibility. A novel artificial intelligence (AI) method based on deep learning provides fully automated measurements of LV global longitudinal strain (GLS) and may improve the clinical utility of echocardiography by reducing user-related variability. The aim of this study was to assess within-patient test-retest reproducibility of LV GLS measured by the novel AI method in repeated echocardiograms recorded by different echocardiographers and to compare the results to manual measurements.
Methods
Two test-retest data sets (n = 40 and n = 32) were obtained at separate centers. Repeated recordings were acquired in immediate succession by 2 different echocardiographers at each center. For each data set, 4 readers measured GLS in both recordings using a semiautomatic method to construct test-retest interreader and intrareader scenarios. Agreement, mean absolute difference, and minimal detectable change (MDC) were compared to analyses by AI. In a subset of 10 patients, beat-to-beat variability in 3 cardiac cycles was assessed by 2 readers and AI.
Results
Test-retest variability was lower with AI compared with interreader scenarios (data set I: MDC = 3.7 vs 5.5, mean absolute difference = 1.4 vs 2.1, respectively; data set II: MDC = 3.9 vs 5.2, mean absolute difference = 1.6 vs 1.9, respectively; all P < .05). There was bias in GLS measurements in 13 of 24 test-retest interreader scenarios (largest bias, 3.2 strain units). In contrast, there was no bias in measurements by AI. Beat-to-beat MDCs were 1,5, 2.1, and 2.3 for AI and the 2 readers, respectively. Processing time for analyses of GLS by the AI method was 7.9 ± 2.8 seconds.
Conclusion
A fast AI method for automated measurements of LV GLS reduced test-retest variability and removed bias between readers in both test-retest data sets. By improving the precision and reproducibility, AI may increase the clinical utility of echocardiography.