AI Article Synopsis

  • - Fetal head circumference (HC) is crucial for tracking fetal development, but existing measurement methods can be error-prone due to sonographer skill levels, highlighting the need for an automatic and accurate solution.
  • - The research introduces a new one-stage network for detecting fetal HC using an anchor-free, end-to-end approach that combines transformers and CNNs to enhance both global and local feature extraction without adding computational strain.
  • - The method addresses detection challenges, particularly with angle variations, by implementing a soft stage-wise regression strategy and a novel loss function, demonstrating strong results on the HC18 dataset and aiming to aid less experienced sonographers and improve prenatal care globally.

Article Abstract

Fetal head circumference (HC) is an important biological parameter to monitor the healthy development of the fetus. Since there are some HC measurement errors that affected by the skill and experience of the sonographers, a rapid, accurate and automatic measurement for fetal HC in prenatal ultrasound is of great significance. We proposed a new one-stage network for rotating elliptic object detection based on anchor-free method, which is also an end-to-end network for fetal HC auto-measurement that no need for any post-processing. The network structure used simple transformer structure combined with convolutional neural network (CNN) for a lightweight design, meanwhile, made full use of powerful global feature extraction ability of transformer and local feature extraction ability of CNN to extract continuous and complete skull edge information. The two complement each other for promoting detection precision of fetal HC without significantly increasing the amount of computation. In order to reduce the large variation of intersection over union (IOU) in rotating elliptic object detection caused by slight angle deviation, we used soft stage-wise regression (SSR) strategy for angle regression and added KLD that is approximate to IOU loss into total loss function. The proposed method achieved good results on the HC18 dataset to prove its effectiveness. This study is expected to help less experienced sonographers, provide help for precision medicine, and relieve the shortage of sonographers for prenatal ultrasound in worldwide.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9002127PMC
http://dx.doi.org/10.3389/fmed.2022.848904DOI Listing

Publication Analysis

Top Keywords

fetal head
8
head circumference
8
automatic measurement
8
prenatal ultrasound
8
rotating elliptic
8
elliptic object
8
object detection
8
feature extraction
8
extraction ability
8
fetal
5

Similar Publications

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!