Segmentation of 2D fetal ultrasound images by exploiting context information using conditional random fields

Abstract

This paper proposes a novel approach for segmenting fetal ultrasound images. This problem presents a variety of challenges including high noise, low contrast, and other US imaging properties such as similarity between texture and gray levels of two organs/ tissues. In this paper, we have proposed a Conditional Random Field (CRF) based framework to handle challenges in segmenting fetal ultrasound images. Clinically, it is known that fetus is surrounded by specific maternal tissues, amniotic fluid and placenta. We exploit this context information using CRFs for segmenting the fetal images accurately. The proposed CRF framework uses wavelet based texture features for representing the ultrasound image and Support Vector Machines (SVM) for initial label prediction. Initial results on a limited dataset of real world ultrasound images of fetus are promising. Results show that proposed method could handle the noise and similarity between fetus and its surroundings in ultrasound images.

HoliMAb: A holistic approach for Media–Adventitia border detection in intravascular ultrasound

“…Most of the proposed techniques are based on Conditional Random Fields (CRFs) or Markov Random Fields (MRFs). One example is in (Gupta et al, 2011), where CRFs is applied to the segmentation of fetal in ultrasound images; in (Schmidt et al, 2008) CRFs are applied to the detection of heart motion abnormality; in (Zhang et al, 2010) MRFs and Graph Cut are used in breast tumor detection. All these works can be compared to the approach presented in (Ciompi et al, 2011), where the tissue labeling relies on inference applied to a graphical model.…”

New Frontiers in Placenta Tissue Imaging

“…For example, Romeo et al 47 used machine learning methods with MRI-derived texture analysis features to assess the presence of placenta accreta spectrum in patients with placenta praevia with an accuracy up to 98%. Using an alternative segmentation approach, Gupta et al 48 applied wavelet decompositionbased conditional random fields to successfully develop segmentation methods for US images of the fetus. These tools could potentially be applied to placenta segmentation using proper constraints and choice of the training set features.…”

Segmentation atrioventricular septal defect by using convolutional neural networks based on U-NET architecture

“…Nguyen et al [7] discuss the surface extraction using support vector machine based texture classification for fetal ultrasound imaging. Gupta et al [8] using the conditional random field method for the segmentation process in 2D images of ultrasound fetal with exploiting context information. Rahmatullah et al [9] conducted a process of automated image analysis method based on a machine learning algorithm for detecting important anatomical landmarks employed in manual scoring of ultrasound images of the fetal abdomen.…”