Objective: To use artificial intelligence (AI) to automatically extract video clips of the fetal heart from a stream of ultrasound video, and to assess the performance of these when used for remote second review.
Methods: Using a dataset from a previous clinical trial of AI to assist in fetal ultrasound scanning, AI was used to automatically extract video clips of the fetal heart from ultrasound scans of 48 fetuses in which the diagnosis was known: 24 normal and 24 with congenital heart disease (CHD). These, and manually still saved images, were shown in a random order to expert clinicians, who were asked to detect cardiac abnormalities.
Results: The initial manual scan had a sensitivity of 0.792 and specificity of 0.917 for detecting CHD in this cohort. The addition of second review improved the sensitivity to 0.975 using video clips, which was significantly higher than using still images (0.892, p = 0.002). There was a significant drop in specificity to 0.767 and 0.833 (p < 0.001) for the video and still method, respectively, which were statistically similar to each other (p = 0.117). The median review time was 1.0 min (IQR 0.71) for the still images, and 3.75 min (IQR 3.12) for the AI-generated video clips.
Conclusion: AI can be used to automatically extract fetal cardiac video clips, and these can be used for remote second review to improve detection rates. Video clips are superior to still images, but both methods result in a significant drop in specificity.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1002/pd.6757 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Exoscopic Clipping of a Superior Cerebellar Artery Aneurysm via a One-Piece Orbitozygomatic Approach: Educational Operative Video.
World Neurosurg
March 2025
Department of Neurosurgery, Lenox Hill Hospital, Zucker School of Medicine at Hofstra/Northwell, Northwell Health, New York, USA.
Querying the capability of the post-HoLEP endoscopic aspect of the membranous urethral mucosa in predicting urinary incontinence: a prospective AI-based analysis.
World J Urol
March 2025
Department of Urology, Tel Aviv Sourasky Medical Center, 6 Weizmann St., Tel-Aviv, 6423906, Israel.
Introduction: Transient stress urinary incontinence (SUI) after holmium laser enucleation of prostate (HoLEP) is commonly linked to intraoperative injury of the external urethral sphincter (EUS). We assessed the reliability of the post-HoLEP endoscopic appearance of the membranous urethra mucosa (MUM) in predicting post-HoLEP continence.
Methods: Forty HoLEPs were prospectively recorded by an artificial intelligence video platform capable of segmenting clips by surgical steps.
Laser biospeckle as a method to investigate the short-term effects of far-red light on an arugula ( Mill) plant.
Front Plant Sci
February 2025
Department of Mechanical Engineering, Shibaura Institute of Technology, Tokyo, Japan.
With rapid climate change, it has been increasingly difficult to grow different crops, and as an alternative method, artificial cultivation in controlled environments has evolved into a new sustainable agriculture practice. However, the cost of having a controlled environment has become a major issue, and investigations have been conducted to develop cost-saving and efficient cultivation techniques. One research focus is on the utilization of stimulating appropriate photoreceptors for a certain time by far-red (FR) light to influence plant development.
View Article and Find Full Text PDFAttentional biases for dynamic stimuli in emerging adults with anxiety: A preliminary eye-tracking study.
J Psychiatr Res
February 2025
Department of Psychiatry, Dalhousie University, Halifax, NS, Canada. Electronic address:
While attentional biases towards negative stimuli have previously been linked to the development and maintenance of anxiety disorders, a current limitation of this research involves the use of static images for stimuli, as they cannot adequately depict the dynamic nature of real-life interactions. Since attentional biases in those with elevated anxiety remain understudied using more naturalistic stimuli, such as dynamic social videos, the purpose of this explorative study was to use novel dynamic stimuli and modern eye-tracking equipment to further investigate negative attentional biases in anxious emerging, female adults. Non-clinical participants (N = 62; mean age = 20.
View Article and Find Full Text PDFAutomatic diagnosis of abdominal pathologies in untrimmed ultrasound videos.
Int J Comput Assist Radiol Surg
March 2025
Ircad Africa, Kigali, Rwanda.
Purpose: Despite major advances in Computer Assisted Diagnosis (CAD), the need for carefully labeled training data remains an important clinical translation barrier. This work aims to overcome this barrier for ultrasound video-based CAD, using video-level classification labels combined with a novel training strategy to improve the generalization performance of state-of-the-art (SOTA) video classifiers.
Methods: SOTA video classifiers were trained and evaluated on a novel ultrasound video dataset of liver and kidney pathologies, and they all struggled to generalize, especially for kidney pathologies.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!