Fetal MRI vs. fetal ultrasound in the diagnosis of pathologies of the central nervous system

Background Malformations of the central nervous system (CNS) constitute the 2nd most common group of fetal pathologies, which can be reflected throughout the patient's life. Fetal ultrasound (US), together with fetal magnetic resonance imaging (MRI) are extremely important techniques for the diagnosis of CNS malformations. The objective of this work was to address fetal US and fetal MRI, as well as the benefits of its use in different CNS pathologies and to ascertain which of the techniques presents better results. Methods For this systematic literature review, a search was conducted using databases such as PubMed® and ScienceDirect®, Google Scholar, b-on digital library, in a 10-year period, 2010 to 2020. 60 references were used, which met the inclusion criteria, namely compliance with the defined timeframe and the theme of the work to be addressed. Results As for the results, fetal US is the first-line technique for fetal evaluation, and its objective is to detect possible fetal malformations early, while fetal MRI complements the information collected through fetal US. When there are cases of isolated ventriculomegaly and complete agenesis of the corpus callosum, fetal US can correctly assess the pathology. When it comes to pathologies such as dysgenesis of the corpus callosum and malformations of the posterior fossa, fetal MRI evaluates more effectively in comparison to fetal US. Conclusions In conclusions, to reduce the number of false positives, the techniques should be used together, thus providing a better diagnosis.

Scale-aware Auto-context-guided Fetal US Segmentation with Structured Random Forests

Accurate measurement of fetal biometrics in ultrasound at different trimesters is essential in assisting clinicians to conduct pregnancy diagnosis. However, the accuracy of manual segmentation for measurement is highly user-dependent. Here, we design a general framework for automatically segmenting fetal anatomical structures in two-dimensional (2D) ultrasound (US) images and thus make objective biometric measurements available. We first introduce structured random forests (SRFs) as the core discriminative predictor to recognize the region of fetal anatomical structures with a primary classification map. The patch-wise joint labeling presented by SRFs has inherent advantages in identifying an ambiguous/fuzzy boundary and reconstructing incomplete anatomical boundary in US. Then, to get a more accurate and smooth classification map, a scale-aware auto-context model is injected to enhance the contour details of the classification map from various visual levels. Final segmentation can be obtained from the converged classification map with thresholding. Our framework is validated on two important biometric measurements, which are fetal head circumference (HC) and abdominal circumference (AC). The final results illustrate that our proposed method outperforms state-of-the-art methods in terms of segmentation accuracy.