Celine Firtion

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

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.

Automated risk assessment tool for pregnancy care

Clinical decision support systems augment the quality of medical care by aiding healthcare workers in the evaluation and management of complicated cases. Clinical decision support systems are especially instrumental in quickly assessing the criticality of pregnancy as it involves interpreting multiple maternal and fetal parameters. We propose a machine learning approach for early determination of the risk category of pregnancy based on patterns gleaned from profiles of known clinical parameters. In particular, we demonstrate the usefulness of classification and regression trees in solving multivariate problems in obstetric care since the decision making process and the importance of specific parameters are clearly illustrated in the tree. As proof of concept, an application use case has been presented.

Doppler based identification of uterine artery and umbilical artery for monitoring pregnancy

In this paper, we present an algorithm to identify umbilical and uterine arteries from a set of four different maternal and fetal arteries using their Doppler signatures. To distinguish these arteries, we use 132 Doppler signals collected from pregnant women with gestational ages between 24 to 40 weeks. Initially we filter them to remove noise; spectrograms are generated to extract good cycles, which are then analyzed to derive independent features that could uniquely represent an artery. A non-linear classification technique using k-NN (k-nearest neighbor) classifier is further applied to identify umbilical and uterine arteries. The proposed algorithm achieves sensitivity and specificity of above 95% and 97% for identification of uterine artery and above 63% and 80% for umbilical artery.

Automated fetal spine detection in ultrasound images

A novel method is proposed for the automatic detection of fetal spine in ultrasound images along with its orientation in this paper. This problem presents a variety of challenges, including robustness to speckle noise, variations in the visible shape of the spine due to orientation of the ultrasound probe with respect to the fetus and the lack of a proper edge enclosing the entire spine on account of its composition out of distinct vertebra. The proposed method improves robustness and accuracy by making use of two independent techniques to estimate the spine, and then detects the exact location using a cross-correlation approach. Experimental results show that the proposed method is promising for fetal spine detection.