Are AI Foundation Models Efficient for Segmentation of Echocardiograms?

J Am Soc Echocardiogr

Division of Cardiology, Department of Medicine, University of California, San Francisco, San Francisco, California; Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, California; UCSF-UC Berkeley Joint Program in Computational Precision Health, Uni

Published: June 2025


Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12140858PMC
http://dx.doi.org/10.1016/j.echo.2025.02.001DOI Listing

Publication Analysis

Top Keywords

foundation models
4
models efficient
4
efficient segmentation
4
segmentation echocardiograms?
4
foundation
1
efficient
1
segmentation
1
echocardiograms?
1

Similar Publications

Within this special issue we would like to celebrate 200 years of the Karlsruhe Institute of Technology (KIT) and the former Technical University Karlsruhe/Germany. The Technical University Karlsruhe served, according to the first president of MIT, William Barton Rogers, as the role model for the planned MIT in Boston/USA after he visited Karlsruhe. All authors of this special issue of Macromolecular Rapid Communications have been or are still active in Karlsruhe.

View Article and Find Full Text PDF

Importance: There is an unmet need for long-term, safe, effective, and hormone-free treatments for menopausal symptoms, including vasomotor symptoms (VMS) and sleep disturbances.

Objective: To evaluate the 52-week efficacy and safety of elinzanetant, a dual neurokinin-targeted therapy, for treating moderate to severe VMS associated with menopause.

Design, Setting, And Participants: OASIS-3 was a double-blind, placebo-controlled, randomized phase 3 clinical trial that was conducted at 83 sites in North America and Europe from August 27, 2021, to February 12, 2024, and included postmenopausal women aged 40 to 65 years who were seeking treatment for moderate to severe VMS (no requirement for a minimum number of VMS events per week).

View Article and Find Full Text PDF

An Antibacterial and Electroactive Chitosan-Based Dressing with Dual Stimulus-Responsive Drug Delivery for Wound Healing.

Macromol Rapid Commun

September 2025

Key Laboratory of Textile Science & Technology, College of Textiles, Ministry of Education, Donghua University, Shanghai, China.

Persistent bacterial infections remain a major challenge in wound management. Although drug-loaded wound dressings have gained increasing attention, their therapeutic efficacy is often hindered by uncontrolled drug release and a lack of electrical signal responsiveness. Herein, an antibacterial dressing (CCS-PC) with electroactivity and stimulus-responsive drug release properties was fabricated via electro-assembly, wherein chitosan and ciprofloxacin hydrochloride (CIP) were co-deposited onto polypyrrole (PPy)-coated gauze.

View Article and Find Full Text PDF

Segmentectomies Made Easy series: robotic-assisted right S1 and S2 segmentectomy.

Multimed Man Cardiothorac Surg

September 2025

Department of Thoracic Surgery, New Cross Hospital, Royal Wolverhampton NHS Trust, Wolverhampton, UK

Three-dimensional (3D) guided robotic-assisted thoracic surgery is increasingly recognized as the pioneering approach for the most complex of pulmonary resections, offering high-definition 3D visualization, enhanced instrument augmentation and tremor-free tissue articulation. Compared with open thoracotomy, the robotic platform is associated with reduced peri-operative morbidity, shorter hospital admissions and faster patient recovery. However, sublobar resections such as segmentectomies remain anatomically and technically demanding, particularly in the context of resecting multiple segments, as showcased in this right S1 and S2 segmentectomy.

View Article and Find Full Text PDF

Segmentectomies Made Easy series: robotic-assisted left S1 and S2 segmentectomy.

Multimed Man Cardiothorac Surg

September 2025

Department of Cardiothoracic Surgery, St George’s Hospital, St George's University Hospitals NHS Foundation Trust, London, UK

Three-dimensional (3D) guided robotic-assisted thoracic surgery is increasingly recognized as a leading technique for undertaking the most complex pulmonary resections, providing high-definition 3D visualization, advanced instrument control and tremor-free tissue handling. Compared with open thoracotomy, the robotic platform offers reduced peri-operative complications, shorter hospital stays and faster patient recovery. Nevertheless, sublobar resections, such as segmentectomies, remain both anatomically intricate and technically challenging, particularly when resecting multiple segments, as in this left S1 and S2 segmentectomy.

View Article and Find Full Text PDF