Automated Techniques for the Interpretation of Fetal Abnormalities: A Review

Abstract

Ultrasound (US) image segmentation methods, focusing on techniques developed for fetal biometric parameters and nuchal translucency, are briefly reviewed. Ultrasound medical images can easily identify the fetus using segmentation techniques and calculate fetal parameters. It can timely find the fetal abnormality so that necessary action can be taken by the pregnant woman. Firstly, a detailed literature has been offered on fetal biometric parameters and nuchal translucency to highlight the investigation approaches with a degree of validation in diverse clinical domains. Then, a categorization of the bibliographic assessment of recent research effort in the segmentation field of ultrasound 2D fetal images has been presented. The fetal images of high-risk pregnant women have been taken into the routine and continuous monitoring of fetal parameters. These parameters are used for detection of fetal weight, fetal growth, gestational age, and any possible abnormality detection.

Data-Driven Modeling of Pregnancy-Related Complications

“…However, machine-learning research has made tremendous progress on more complex data types such as text, images, videos, time series, and even complex networks, which this review refers to as complex data. In medical settings, such modalities (e.g., ultrasound images [146,151,152]) are often converted into handcrafted features to fit the paradigm of tabular data. Due to this inherent handcrafting process, these features are susceptible to human bias and information loss.…”

“…In particular, Doppler ultrasoundwhich can quantify fetal and umbilical blood flowhas been studied in the context of predicting adverse pregnancy outcomes in the first and second trimesters [149,150]. However, images and videos are often converted into (handcrafted) features for manual inspection or for input into machine-learning models using various feature-extraction methods [146,151,152]. While there are approaches to aid in the interpretation of pregnancy-related imaging data [146], only limited work has tried to tap into the full potential of image and video material to model and predict pregnancy-related outcomes [153].…”

Machine Learning in Fetal Cardiology: What to Expect

“…Similarly, Kim et al [27] used a CNN to estimate AC from 2-D US data. For further information on biometric measurements, we refer the reader to a recent review of automated techniques for the interpretation of fetal abnormalities [28].…”

Detection and Classification of Fetal Abnormalities by Anfis in First Trimester

“…Of these, the US (Ultra sound) techniques are found to be more suitable for fetal studies because of noninvasive nature, safety of radiation, cheaper cost. In this imaging, beam of waves operating above the sound-range are sent through transducer into the human body and the received echoes are used to create image formation which has to take care of problems of attenuation, missing boundaries, presence of artifacts or speckles [1]. Fetal abnormalities are detected by study of fetal biometric parameters and thickness of nuchal translucency.…”

“…Fetal abnormalities are detected by study of fetal biometric parameters and thickness of nuchal translucency. For detecting abnormalities biometric parameters include bi parietal diameter (BPD) , gestational sac(G.Sac) head circumference (HC), abdominal circumference (AC), femur length (FL).These parameters measure the gestational age of the features and detect growth patterns and abnormalities [1].Fetal abnormalities increases rate of mortality, still birth and morbidity during early life. Diagnosis of abnormalities during fetal growth gives wide option for doctors and patients.…”