Application of a semiautomatic boundary detection algorithm for the assessment of amniotic fluid quantity from ultrasound images

Sagiv, Chen; Akselrod, Solange; Tepper, R.

doi:10.1016/s0301-5629(98)00188-4

Cited by 2 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the enhanced image, the feature values namely, contrast, energy, correlation and homogeneity are extracted and these values are trained in ANFIS. The image sets are tested and gives the output value of Amniotic Fluid Index [10,12].…”

Section: Resultsmentioning

confidence: 99%

The Detection of Prenatal Growth using Artificial Neural Network

Radhika¹,

Ramya²,

Srinivasan³

2023

INT J COMPUT COMMUN, Int. J. Comput. Commun. Control

View full text Add to dashboard Cite

Amniotic fluid abnormalities are caused by perinatal death and morbidity. Foetal growth and development are examples of parameters that must be accessible. Ultrasound technology is used to make an image of the uterus. Main aim of this work is to reduce the mortality and morbidity. Because, every year, 30 million new-borns have growth limitation, and there is a link between oligohydramnios (lack of amniotic fluid) and perinatal death. AFI can be measured with the assistance of ultrasound images. It is divided into four equal quadrants, with the Amniotic Fluid Index being the average of these quadrants (AFI). The performance of an Adaptive Neuro-Fuzzy Inference classifier is used for classification techniques. For the implementation of this research uses convolution neural network. During the second and third trimesters of pregnancy, this method is used to detect malformations using deep learning techniques. This strategy aims to reduce diagnostic time and risk factors in earlier stages of pregnancy.

show abstract

Section: Resultsmentioning

confidence: 99%