Automated Left Ventricular Dimension Assessment Using Artificial Intelligence Developed and Validated by a UK-Wide Collaborative.

Autor:	Howard JP; Imperial College London (J.P.H., C.C.S., G.D.C., K.A., K.V., D.P.F., M.J.S.-S.).; Hammersmith Hospital, London (J.P.H., C.C.S., D.P.F.)., Stowell CC; Imperial College London (J.P.H., C.C.S., G.D.C., K.A., K.V., D.P.F., M.J.S.-S.).; Hammersmith Hospital, London (J.P.H., C.C.S., D.P.F.)., Cole GD; Imperial College London (J.P.H., C.C.S., G.D.C., K.A., K.V., D.P.F., M.J.S.-S.).; Charing Cross Hospital, London (G.D.C., B.R.)., Ananthan K; Imperial College London (J.P.H., C.C.S., G.D.C., K.A., K.V., D.P.F., M.J.S.-S.)., Demetrescu CD; Guy's and St Thomas' NHS Foundation Trust (C.D.D., R.R., J.B.C.)., Pearce K; Manchester University Foundation Trust, Wythenshawe Hospital Manchester (K.P.)., Rajani R; Guy's and St Thomas' NHS Foundation Trust (C.D.D., R.R., J.B.C.).; School of Biomedical Engineering and Imaging Sciences, King's College London (R.R.)., Sehmi J; West Hertfordshire Hospitals NHS Trust (J.S.)., Vimalesvaran K; Imperial College London (J.P.H., C.C.S., G.D.C., K.A., K.V., D.P.F., M.J.S.-S.)., Kanaganayagam GS; Chelsea and Westminster and Imperial NHS Trust (G.S.K.)., McPhail E; King's College Hospital, London (E.M.)., Ghosh AK; Barts Heart Centre, St Bartholomew's Hospital, London (A.K.G.)., Chambers JB; Guy's and St Thomas' NHS Foundation Trust (C.D.D., R.R., J.B.C.)., Singh AP; London North West University Healthcare NHS Trust (A.P.S.)., Zolgharni M; University of West London (M.Z.)., Rana B; Charing Cross Hospital, London (G.D.C., B.R.)., Francis DP; Imperial College London (J.P.H., C.C.S., G.D.C., K.A., K.V., D.P.F., M.J.S.-S.).; Hammersmith Hospital, London (J.P.H., C.C.S., D.P.F.)., Shun-Shin MJ; Imperial College London (J.P.H., C.C.S., G.D.C., K.A., K.V., D.P.F., M.J.S.-S.).; St Mary's Hospital, London (M.J.S.-S.).
Jazyk:	angličtina
Zdroj:	Circulation. Cardiovascular imaging [Circ Cardiovasc Imaging] 2021 May; Vol. 14 (5), pp. e011951. Date of Electronic Publication: 2021 May 17.
DOI:	10.1161/CIRCIMAGING.120.011951
Abstrakt:	Background: requires training and validation to standards expected of humans. We developed an online platform and established the Unity Collaborative to build a dataset of expertise from 17 hospitals for training, validation, and standardization of such techniques. Methods: The training dataset consisted of 2056 individual frames drawn at random from 1265 parasternal long-axis video-loops of patients undergoing clinical echocardiography in 2015 to 2016. Nine experts labeled these images using our online platform. From this, we trained a convolutional neural network to identify keypoints. Subsequently, 13 experts labeled a validation dataset of the end-systolic and end-diastolic frame from 100 new video-loops, twice each. The 26-opinion consensus was used as the reference standard. The primary outcome was precision SD, the SD of the differences between AI measurement and expert consensus. Results: In the validation dataset, the AI's precision SD for left ventricular internal dimension was 3.5 mm. For context, precision SD of individual expert measurements against the expert consensus was 4.4 mm. Intraclass correlation coefficient between AI and expert consensus was 0.926 (95% CI, 0.904-0.944), compared with 0.817 (0.778-0.954) between individual experts and expert consensus. For interventricular septum thickness, precision SD was 1.8 mm for AI (intraclass correlation coefficient, 0.809; 0.729-0.967), versus 2.0 mm for individuals (intraclass correlation coefficient, 0.641; 0.568-0.716). For posterior wall thickness, precision SD was 1.4 mm for AI (intraclass correlation coefficient, 0.535 [95% CI, 0.379-0.661]), versus 2.2 mm for individuals (0.366 [0.288-0.462]). We present all images and annotations. This highlights challenging cases, including poor image quality and tapered ventricles. Conclusions: Experts at multiple institutions successfully cooperated to build a collaborative AI. This performed as well as individual experts. Future echocardiographic AI research should use a consensus of experts as a reference. Our collaborative welcomes new partners who share our commitment to publish all methods, code, annotations, and results openly.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu