{"schema":"pith.reference-change-event.v1","doi":"10.1016/j.echo.2021.07.006","canonical_url":"https://pith.science/event/10.1016/j.echo.2021.07.006","json_url":"https://pith.science/event/10.1016/j.echo.2021.07.006.json","not_a_judgment":"This page records that a citing paper's bibliography includes a work with a published notice. It is not a judgment on the citing paper.","primary":{"event_id":480831,"doi":"10.1016/j.echo.2021.07.006","event_type":"correction","event_type_label":"Correction","source":"crossref","source_label":"Crossref","event_date":"2022-04-01","title":"Correction","work_title":"Journal of the American Society of Echocardiography 35, 1–76 (2022)","work_doi":"10.1016/j.echo.2021.07.006","work_arxiv_id":null,"notice_doi":"10.1016/j.echo.2022.01.011","flag_count":0,"flags_open":0,"flags_disputed":0,"latest_flag_at":null,"human_href":"/event/10.1016/j.echo.2021.07.006","json_href":"/event/10.1016/j.echo.2021.07.006.json"},"events":[{"event_id":480831,"doi":"10.1016/j.echo.2021.07.006","event_type":"correction","event_type_label":"Correction","source":"crossref","source_label":"Crossref","event_date":"2022-04-01","title":"Correction","work_title":"Journal of the American Society of Echocardiography 35, 1–76 (2022)","work_doi":"10.1016/j.echo.2021.07.006","work_arxiv_id":null,"notice_doi":"10.1016/j.echo.2022.01.011","flag_count":0,"flags_open":0,"flags_disputed":0,"latest_flag_at":null,"human_href":"/event/10.1016/j.echo.2021.07.006","json_href":"/event/10.1016/j.echo.2021.07.006.json"}],"flags":[{"id":10537,"status":"open","status_label":"Open","citing_arxiv_id":"2508.13077","citing_title":"From Transthoracic to Transesophageal: Cross-Modality Generation using LoRA Diffusion","ref_index":2,"evidence_raw":"manner to generate synthetic TEE data. After training, we perform inference using real masks and masks sampled from SSMs to generate synthetic TEE datasets. Finally, we augment existing real TEE datasets and use them for a downstream task. publicly available pipeline introduced in [11]. This pipeline extracts planes from 3D heart statistical shape models (SSMs) [17] that correspond to standard TEE and TTE views defined by the American Society of Echocardiography [2]. Image GenerationFigure 1 illustrates our proposed pipeline. The base model is an EDM trained at a resolution of 224× 224, using a UNet with a depth of 3 [14]. We augment the UNet with both self-attention and cross-attention layers. The channel dimensionality follows64× [1, 2, 4] across the three stages.","evidence_cleaned":"manner to generate synthetic TEE data. After training, we perform inference using real masks and masks sampled from SSMs to generate synthetic TEE datasets. Finally, we augment existing real TEE datasets and use them for a downstream task. publicly available pipeline introduced in [11]. This pipeline extracts planes from 3D heart statistical shape models (SSMs) [17] that correspond to standard TEE and TTE views defined by the American Society of Echocardiography [2]. Image GenerationFigure 1 illustrates our proposed pipeline. The base model is an EDM trained at a resolution of 224× 224, using a UNet with a depth of 3 [14]. We augment the UNet with both self-attention and cross-attention layers. The channel dimensionality follows64× [1, 2, 4] across the three stages","evidence_source_label":"citation context","event_type":"correction","event_type_label":"Correction","source_label":"Crossref","event_date":"2022-04-01","work_title":"Journal of the American Society of Echocardiography 35, 1–76 (2022)","work_doi":"10.1016/j.echo.2021.07.006","event_doi":"10.1016/j.echo.2021.07.006","flag_href":"/flags/10537","event_href":"/event/10.1016/j.echo.2021.07.006","paper_href":"/paper/2508.13077","created_at":"2026-08-16T06:31:06.645986Z","dispute_note":null,"disputed_at":null,"disputed_by":null}],"flag_count":1,"flags_open":1,"flags_disputed":0,"desk_url":"https://pith.science/flags"}