PMID- 35152371 OWN - NLM STAT- Publisher LR - 20240220 IS - 1875-8312 (Electronic) IS - 1569-5794 (Linking) DP - 2022 Feb 13 TI - Fully automated quantification of cardiac chamber and function assessment in 2-D echocardiography: clinical feasibility of deep learning-based algorithms. LID - 10.1007/s10554-021-02482-y [doi] AB - We aimed to compare the segmentation performance of the current prominent deep learning (DL) algorithms with ground-truth segmentations and to validate the reproducibility of the manually created 2D echocardiographic four cardiac chamber ground-truth annotation. Recently emerged DL based fully-automated chamber segmentation and function assessment methods have shown great potential for future application in aiding image acquisition, quantification, and suggestion for diagnosis. However, the performance of current DL algorithms have not previously been compared with each other. In addition, the reproducibility of ground-truth annotations which are the basis of these algorithms have not yet been fully validated. We retrospectively enrolled 500 consecutive patients who underwent transthoracic echocardiogram (TTE) from December 2019 to December 2020. Simple U-net, Res-U-net, and Dense-U-net algorithms were compared for the segmentation performances and clinical indices such as left atrial volume (LAV), left ventricular end diastolic volume (LVEDV), left ventricular end systolic volume (LVESV), LV mass, and ejection fraction (EF) were evaluated. The inter- and intra-observer variability analysis was performed by two expert sonographers for a randomly selected echocardiographic view in 100 patients (apical 2-chamber, apical 4-chamber, and parasternal short axis views). The overall performance of all DL methods was excellent [average dice similarity coefficient (DSC) 0.91 to 0.95 and average Intersection over union (IOU) 0.83 to 0.90], with the exception of LV wall area on PSAX view (average DSC of 0.83, IOU 0.72). In addition, there were no significant difference in clinical indices between ground truth and automated DL measurements. For inter- and intra-observer variability analysis, the overall intra observer reproducibility was excellent: LAV (ICC = 0.995), LVEDV (ICC = 0.996), LVESV (ICC = 0.997), LV mass (ICC = 0.991) and EF (ICC = 0.984). The inter-observer reproducibility was slightly lower as compared to intraobserver agreement: LAV (ICC = 0.976), LVEDV (ICC = 0.982), LVESV (ICC = 0.970), LV mass (ICC = 0.971), and EF (ICC = 0.899). The three current prominent DL-based fully automated methods are able to reliably perform four-chamber segmentation and quantification of clinical indices. Furthermore, we were able to validate the four cardiac chamber ground-truth annotation and demonstrate an overall excellent reproducibility, but still with some degree of inter-observer variability. CI - (c) 2022. The Author(s). FAU - Kim, Sekeun AU - Kim S AD - CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, South Korea. AD - Graduate Program of Biomedical Engineering, Yonsei University College of Medicine, Seoul, South Korea. FAU - Park, Hyung-Bok AU - Park HB AD - CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, South Korea. AD - Department of Cardiology, Catholic Kwandong University International St. Mary's Hospital, Incheon, South Korea. FAU - Jeon, Jaeik AU - Jeon J AD - CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, South Korea. FAU - Arsanjani, Reza AU - Arsanjani R AD - Department of Cardiovascular Diseases, Mayo Clinic Arizona, Phoenix, AZ, USA. FAU - Heo, Ran AU - Heo R AD - CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, South Korea. AD - Department of Cardiology, Hanyang University Seoul Hospital, Hanyang University College of Medicine, Seoul, South Korea. FAU - Lee, Sang-Eun AU - Lee SE AD - CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, South Korea. AD - Department of Cardiology, Ewha Womans University Seoul Hospital, Seoul, South Korea. FAU - Moon, Inki AU - Moon I AD - CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, South Korea. AD - Division of Cardiology, Department of Internal Medicine, Soonchunghyang University Bucheon Hospital, Bucheon, South Korea. FAU - Yoo, Sun Kook AU - Yoo SK AD - Department of Medical Engineering, Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, South Korea. sunkyoo@yuhs.ac. FAU - Chang, Hyuk-Jae AU - Chang HJ AUID- ORCID: 0000-0002-6139-7545 AD - CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, South Korea. hjchang@yuhs.ac. AD - Division of Cardiology, Department of Cardiology, Severance Cardiovascular Hospital, Yonsei University College of Medicine, Yonsei University Health System, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, South Korea. hjchang@yuhs.ac. AD - Ontact Health Co., Ltd., Seoul, South Korea. hjchang@yuhs.ac. LA - eng PT - Journal Article DEP - 20220213 PL - United States TA - Int J Cardiovasc Imaging JT - The international journal of cardiovascular imaging JID - 100969716 SB - IM OTO - NOTNLM OT - Deep learning OT - Echocardiography OT - Fully automated EDAT- 2022/02/14 06:00 MHDA- 2022/02/14 06:00 CRDT- 2022/02/13 20:37 PHST- 2021/09/27 00:00 [received] PHST- 2021/11/24 00:00 [accepted] PHST- 2022/02/13 20:37 [entrez] PHST- 2022/02/14 06:00 [pubmed] PHST- 2022/02/14 06:00 [medline] AID - 10.1007/s10554-021-02482-y [pii] AID - 10.1007/s10554-021-02482-y [doi] PST - aheadofprint SO - Int J Cardiovasc Imaging. 2022 Feb 13. doi: 10.1007/s10554-021-02482-y.