3 results match your criteria: "The Second Hospital of Quanzhou Affiliated to Fujian Medical University[Affiliation]"
Application of artificial intelligence in VSD prenatal diagnosis from fetal heart ultrasound images.
BMC Pregnancy Childbirth
November 2024
Department of Ultrasound, The Second Hospital of Quanzhou Affiliated to Fujian Medical University, Quanzhou, China.
Background: Developing a combined artificial intelligence (AI) and ultrasound imaging to provide an accurate, objective, and efficient adjunctive diagnostic approach for fetal heart ventricular septal defects (VSD).
Methods: 1,451 fetal heart ultrasound images from 500 pregnant women were comprehensively analyzed between January 2016 and June 2022. The fetal heart region was manually labeled and the presence of VSD was discriminated by experts.
SEG-LUS: A novel ultrasound segmentation method for liver and its accessory structures based on muti-head self-attention.
Comput Med Imaging Graph
April 2024
Collaborative Innovation Center for Maternal and Infant Health Service Application Technology, Quanzhou Medical College, Quanzhou 362011, China; Department of Ultrasound, The Second Hospital of Quanzhou Affiliated to Fujian Medical University, Quanzhou, China. Electronic address:
Although liver ultrasound (US) is quick and convenient, it presents challenges due to patient variations. Previous research has predominantly focused on computer-aided diagnosis (CAD), particularly for disease analysis. However, characterizing liver US images is complex due to structural diversity and a limited number of samples.
View Article and Find Full Text PDFFHUSP-NET: A Multi-task model for fetal heart ultrasound standard plane recognition and key anatomical structures detection.
Comput Biol Med
January 2024
Department of Ultrasound, The First Hospital of Quanzhou Affiliated to Fujian Medical University, Quanzhou, China. Electronic address:
Article Synopsis
- The study focuses on enhancing the prenatal ultrasound screening process by developing a deep learning-based network, called FHUSP-NET, to automatically recognize fetal heart ultrasound standard planes (FHUSPs) and detect anatomical structures simultaneously.
- The FHUSP-NET utilizes 3,360 ultrasound images and incorporates advanced techniques like spatial pyramid pooling and squeeze-and-excitation networks to improve image perception and feature sensitivity.
- The results show the model's high effectiveness, achieving impressive precision (0.958), recall (0.931), and recognition accuracy (0.964), while also significantly speeding up detection time to just 13.6 ms per image, enhancing the quality control for ultrasonographers.