Fetal Brain MRI: Segmentation and Biometric Analysis of the Posterior Fossa

Image Recovery Matters: A Recovery-Extraction Framework for Robust Fetal Brain Extraction From MR Images

The extraction of the fetal brain from magnetic resonance (MR) images is a challenging task. In particular, fetal MR images suffer from different kinds of artifacts introduced during the image acquisition. Among those artifacts, intensity inhomogeneity is a common one affecting brain extraction. In this work, we propose a deep learning-based recovery-extraction framework for fetal brain extraction, which is particularly effective in handling fetal MR images with intensity inhomogeneity. Our framework involves two stages. First, the artifact-corrupted images are recovered with the proposed generative adversarial learning-based image recovery network with a novel region-of-darkness discriminator that enforces the network focusing on artifacts of the images. Second, we propose a brain extraction network for more effective fetal brain segmentation by strengthening the association between lower- and higher-level features as well as suppressing task-irrelevant features. Thanks to the proposed recovery-extraction strategy, our framework is able to accurately segment fetal brains from artifact-corrupted MR images. The experiments show that our framework achieves promising performance in both quantitative and qualitative evaluations, and outperforms state-of-the-art methods in both image recovery and fetal brain extraction.

Prediction of Medical Conditions Using Machine Learning Approaches: Alzheimer’s Case Study

Alzheimer’s Disease (AD) is a highly prevalent condition and most of the people suffering from it receive the diagnosis late in the process. The diagnosis is currently established following an evaluation of the protein biomarkers in cerebrospinal fluid (CSF), brain imaging, cognitive tests, and the medical history of the individuals. While diagnostic tools based on CSF collections are invasive, the tools used for acquiring brain scans are expensive. Taking these into account, an early predictive system, based on Artificial Intelligence (AI) approaches, targeting the diagnosis of this condition, as well as the identification of lead biomarkers becomes an important research direction. In this survey, we review the state-of-the-art research on machine learning (ML) techniques used for the detection of AD and Mild Cognitive Impairment (MCI). We attempt to identify the most accurate and efficient diagnostic approaches, which employ ML techniques and therefore, the ones most suitable to be used in practice. Research is still ongoing to determine the best biomarkers for the task of AD classification. At the beginning of this survey, after an introductory part, we enumerate several available resources, which can be used to build ML models targeting the diagnosis and classification of AD, as well as their main characteristics. After that, we discuss the candidate markers which were used to build AI models with the best results in terms of diagnostic accuracy, as well as their limitations.

Reference biometry of foetal brain by prenatal MRI and the distribution of measurements in foetuses with ventricular septal defect

OBJECTIVE

To provide the reference biometric measurements of the normal foetal brain by prenatal MRI and describe the distribution of measurements in the foetuses with ventricular septal defect (VSD).

METHODS

This retrospective study analysed the biometric measurements of 218 foetuses between 18 - 37 gestational weeks with normal MRI findings from July 2014 to August 2019, as well as 18 foetuses with VSD. The measurements included fronto-occipital diameter (FOD), biparietal diameter (BPD), and transverse cerebellar diameter (TCD). All the prenatal MRI examinations have been taken on the same 1.5 T MR unit with a standard protocol of the foetal brain. All the linear measurements of the foetal brain were obtained on the T2-weighted imaging. The distribution of measurements in 18 foetuses with VSD was plotted on centile curves.

RESULTS

The reference data were presented in mean, standard deviation, 95% predicted confidence intervals, and the 3rd, 10th, 25th, 50th, 75th, 90th, 97th centiles at each gestational age. The value of TCD in 56% (10/18 cases) foetuses with VSD was lower than the 3rd centile, and the rate for FOD and BPD was 33% (6/18 cases) and 22% (4/18 cases) separately. On the curves, most VSD cases with measurements lower than the 3rd centile were in relatively early gestational stage (≤28 weeks).

CONCLUSIONS

We have presented reference linear biometry of the foetal brain by prenatal MRI from 18 to 37 gestational weeks, which could help us to interpret and monitor the brain development for foetuses with VSD and other congenital heart diseases.Key messages:We have presented reference linear biometry of the foetal brain by prenatal MRI from 18 to 37 gestational weeks in multiple statistical methods: mean and standard deviation; 95% predicted confidence intervals and the 3rd, 10th, 25th, 50th, 75th, 90th, 97th centiles.Our data showed that the involvement of the brain in VSD may be not globally, but regionally, and the cerebellum may be more possible to be involved.We speculated that the earlier the VSD diagnosed the worse the brain involved, which might suggest a poor outcome and necessary follow-up.

MRI Segmentation and Classification of Human Brain Using Deep Learning for Diagnosis of Alzheimer's Disease: A Survey

Many neurological diseases and delineating pathological regions have been analyzed, and the anatomical structure of the brain researched with the aid of magnetic resonance imaging (MRI). It is important to identify patients with Alzheimer's disease (AD) early so that preventative measures can be taken. A detailed analysis of the tissue structures from segmented MRI leads to a more accurate classification of specific brain disorders. Several segmentation methods to diagnose AD have been proposed with varying complexity. Segmentation of the brain structure and classification of AD using deep learning approaches has gained attention as it can provide effective results over a large set of data. Hence, deep learning methods are now preferred over state-of-the-art machine learning methods. We aim to provide an outline of current deep learning-based segmentation approaches for the quantitative analysis of brain MRI for the diagnosis of AD. Here, we report how convolutional neural network architectures are used to analyze the anatomical brain structure and diagnose AD, discuss how brain MRI segmentation improves AD classification, describe the state-of-the-art approaches, and summarize their results using publicly available datasets. Finally, we provide insight into current issues and discuss possible future research directions in building a computer-aided diagnostic system for AD.

A new approach to automatic fetal brain extraction from MRI using a variational level set method

BACKGROUND AND PURPOSE

Appropriate images extracted from the MRI of mothers' wombs can be of great help in the medical diagnosis of fetal abnormalities. As maternal tissue may appear in such images, affecting visualization of myelination of the fetal brain, it is not possible to use methods routinely used for extraction of adult brains for fetal brains. The aim of the present study was to use a variational level set approach to extract fetal brain from T2-weighted MR images of the womb.

METHODS

Coronal T2-weighted images were acquired using fast MRI protocols (to avoid artifacts). The database includes 105 MR images from eight subjects. After correcting the inhomogeneity of the images, the fetal eyes were located, and from that information, the location of the fetus brain was automatically determined. Then, the variational level set was used for fetus brain extraction. The results were analyzed by a clinical specialist (radiologist) and the similarity (Dice and Jaccard coefficients), sensitivity and specificity were calculated.

RESULTS AND CONCLUSIONS

The means of the statistical analysis for the Dice and Jaccard coefficients, sensitivity and specificity, were 99.56%, 96.89%, 95.71%, and 97.96%, respectively. Thus, extraction of fetal brain from MR images was confirmed, both statistically and visually through cross-validation.

Toward the automatic quantification of in utero brain development in 3D structural MRI: A review

Investigating the human brain in utero is important for researchers and clinicians seeking to understand early neurodevelopmental processes. With the advent of fast magnetic resonance imaging (MRI) techniques and the development of motion correction algorithms to obtain high-quality 3D images of the fetal brain, it is now possible to gain more insight into the ongoing maturational processes in the brain. In this article, we present a review of the major building blocks of the pipeline toward performing quantitative analysis of in vivo MRI of the developing brain and its potential applications in clinical settings. The review focuses on T1- and T2-weighted modalities, and covers state of the art methodologies involved in each step of the pipeline, in particular, 3D volume reconstruction, spatio-temporal modeling of the developing brain, segmentation, quantification techniques, and clinical applications. Hum Brain Mapp 38:2772-2787, 2017. © 2017 Wiley Periodicals, Inc.

Adaptive prior probability and spatial temporal intensity change estimation for segmentation of the one-year-old human brain

The degree of white matter (WM) myelination is rather inhomogeneous across the brain. White matter appears differently across the cortical lobes in MR images acquired during early postnatal development. Specifically at 1-year of age, the gray/white matter contrast of MR T1 and T2 weighted images in prefrontal and temporal lobes is reduced as compared to the rest of the brain, and thus, tissue segmentation results commonly show lower accuracy in these lobes. In this novel work, we propose the use of spatial intensity growth maps (IGM) for T1 and T2 weighted images to compensate for local appearance inhomogeneity. The IGM captures expected intensity changes from 1 to 2 years of age, as appearance homogeneity is greatly improved by the age of 24 months. The IGM was computed as the coefficient of a voxel-wise linear regression model between corresponding intensities at 1 and 2 years. The proposed IGM method revealed low regression values of 1-10% in GM and CSF regions, as well as in WM regions at maturation stage of myelination at 1 year. However, in the prefrontal and temporal lobes we observed regression values of 20-25%, indicating that the IGM appropriately captures the expected large intensity change in these lobes mainly due to myelination. The IGM is applied to cross-sectional MRI datasets of 1-year-old subjects via registration, correction and tissue segmentation of the IGM-corrected dataset. We validated our approach in a small leave-one-out study of images with known, manual 'ground truth' segmentations.

A review of atlas-based segmentation for magnetic resonance brain images

Normal and abnormal brains can be segmented by registering the target image with an atlas. Here, an atlas is defined as the combination of an intensity image (template) and its segmented image (the atlas labels). After registering the atlas template and the target image, the atlas labels are propagated to the target image. We define this process as atlas-based segmentation. In recent years, researchers have investigated registration algorithms to match atlases to query subjects and also strategies for atlas construction. In this paper we present a review of the automated approaches for atlas-based segmentation of magnetic resonance brain images. We aim to point out the strengths and weaknesses of atlas-based methods and suggest new research directions. We use two different criteria to present the methods. First, we refer to the algorithms according to their atlas-based strategy: label propagation, multi-atlas methods, and probabilistic techniques. Subsequently, we classify the methods according to their medical target: the brain and its internal structures, tissue segmentation in healthy subjects, tissue segmentation in fetus, neonates and elderly subjects, and segmentation of damaged brains. A quantitative comparison of the results reported in the literature is also presented.

Atlas-based segmentation of developing tissues in the human brain with quantitative validation in young fetuses

Imaging of the human fetus using magnetic resonance (MR) is an essential tool for quantitative studies of normal as well as abnormal brain development in utero. However, because of fundamental differences in tissue types, tissue properties and tissue distribution between the fetal and adult brain, automated tissue segmentation techniques developed for adult brain anatomy are unsuitable for this data. In this paper, we describe methodology for automatic atlas-based segmentation of individual tissue types in motion-corrected 3D volumes reconstructed from clinical MR scans of the fetal brain. To generate anatomically correct automatic segmentations, we create a set of accurate manual delineations and build an in utero 3D statistical atlas of tissue distribution incorporating developing gray and white matter as well as transient tissue types such as the germinal matrix. The probabilistic atlas is associated with an unbiased average shape and intensity template for registration of new subject images to the space of the atlas. Quantitative whole brain 3D validation of tissue labeling performed on a set of 14 fetal MR scans (20.57-22.86 weeks gestational age) demonstrates that this atlas-based EM segmentation approach achieves consistently high DSC performance for the main tissue types in the fetal brain. This work indicates that reliable measures of brain development can be automatically derived from clinical MR imaging and opens up possibility of further 3D volumetric and morphometric studies with multiple fetal subjects.

Automatic segmentation of the cerebellum of fetuses on 3D ultrasound images, using a 3D Point Distribution Model

Analysis of fetal biometric parameters on ultrasound images is widely performed and it is essential to estimate the gestational age, as well as the fetal growth pattern. The use of three dimensional ultrasound (3D US) is preferred over other tomographic modalities such as CT or MRI, due to its inherent safety and availability. However, the image quality of 3D US is not as good as MRI and therefore there is little work on the automatic segmentation of anatomic structures in 3D US of fetal brains. In this work we present preliminary results of the development of a 3D Point Distribution Model (PDM), for automatic segmentation, of the cerebellum in 3D US of the fetal brain. The model is adjusted to a fetal 3D ultrasound, using a genetic algorithm which optimizes a model fitting function. Preliminary results show that the approach reported is able to automatically segment the cerebellum in 3D ultrasounds of fetal brains.

Gaussian mixture model-based segmentation of MR images taken from premature infant brains

Segmentation of Magnetic Resonance multi-layer images of premature infant brain has additional challenges in comparison to normal adult brain segmentation. Images of premature infants contain lower signal to noise ratio due to shorter scanning times. Further, anatomic structure include still greater variations which can impair the accuracy of standard brain models. A fully automatic brain segmentation method for T1-weighted images is proposed in present paper. The method uses watershed segmentation with Gaussian mixture model clustering for segmenting cerebrospinal fluid from brain matter and other head tissues. The effect of the myelination process is considered by utilizing information from T2-weighted images. The performance of the new method is compared voxel-by-voxel to the corresponding expert segmentation. The proposed method is found to produce more uniform results in comparison to three accustomary segmentation methods originally developed for adults. This is the case in particular when anatomic forms are still under development and differ in their form from those of adults.

Cerebral biometry in fetal magnetic resonance imaging: new reference data

OBJECTIVES

To provide normal magnetic resonance imaging (MRI) reference biometric data of the fetal brain, to evaluate reproducibility and gender effect, to compare the two cerebral hemispheres and to compare MRI with ultrasonographic biometry, in a large cohort.

METHODS

Normal cerebral fetal MRI examinations were collected prospectively and several parameters were measured: the supratentorial space (bone and cerebral fronto-occipital and biparietal (BPD) diameters), the length of the corpus callosum (LCC), the surface area, height and anteroposterior diameter of the vermis, the transverse cerebellar diameter (TCD) and the anteroposterior diameter of the pons. We evaluated the interobserver reproducibility of measurements and the possible gender effect on measurements of bone BPD, TCD and LCC. We compared right and left hemispheres, right and left atria and ultrasound and MRI measurements.

RESULTS

The study included 589 fetuses, ranging from 26 to 40 weeks. Normal values (from 3(rd) to 97(th) percentile) are provided for each parameter. Interobserver agreement was excellent, with an intraclass correlation coefficient (ICC) > 0.75 for many parameters. The gender effect was evaluated in 372 cases and did not reveal any clinically meaningful difference. Comparison between the right and left cerebral hemispheres and between the right and left atria did not reveal any meaningful differences. Ultrasound and MRI measurements of BPD and TCD were compared in 94 cases and 48 cases, respectively, and the agreement was excellent (ICC = 0.85).

CONCLUSIONS

We present new reproducible reference charts for cerebral MRI biometry at 26-40 weeks' gestation, from a large cohort of fetuses.

MR volume of the fetal cerebellum in relation to growth

PURPOSE

To quantify fetal cerebellar growth by measuring cerebellar volumes of normal fetuses throughout gestation with MRI.

MATERIALS AND METHODS

A total of 93 fetuses with normal brains ranging in age from 16 to 40 gestational weeks were included in the study. Standard fetal biometric measurements were made on a three-dimensional postprocessing workstation and included the head circumference, transverse cerebellar diameter, biparietal diameter, occipital-frontal diameter, as well as cerebellar volume. The gestational ages were estimated from fetal head circumference measurements. Regression analysis was used to find the best-fit model.

RESULTS

There is a strong correlation describing cerebellar volume and gestational age in fetuses with normal central nervous systems. A second-order polynomial regression model was found to be the most appropriate descriptor of cerebellar volume in relation to normal fetal growth. In addition, the cerebellar volume was also found to correlate strongly with the common fetal biometric measurements of transverse cerebellar diameter, biparietal diameter, and occipital-frontal diameter.

CONCLUSION

Nomograms for fetal cerebellar volume with gestational age derived from head circumference measurements are presented for the first time with MRI. A normal fetal cerebellar volume growth chart is established. These results should prove helpful in defining situations of abnormal growth development and dysmorphology.

Knowledge-based localization of hippocampus in human brain MRI

We present a novel and efficient method for localization of human brain structures such as hippocampus. Landmark localization is important for segmentation and registration. This method follows a statistical roadmap, consisting of anatomical landmarks, to reach the desired structures. Using a set of desired and undesired landmarks, identified on a training set, we estimate Gaussian models and determine optimal search areas for desired landmarks. The statistical models form a set of rules to evaluate the extracted landmarks during the search procedure. When applied on 900 MR images of 10 epileptic patients, this method demonstrated an overall success rate of 83%.

Quantitative MRI measurements of human fetal brain development in utero

Magnetic resonance imaging (MRI) allows for high resolution imaging of the central nervous system. We have tested the feasibility of using MRI in conjunction with quantitative image analysis to perform volumetric measurements of the brain in the developing human fetus in utero. The database comprises MR images of a total of 56 fetuses (gestational age 25-41 weeks) referred because of suspected abnormalities due to ultrasound findings, family history or maternal illness and scanned on a 1.5 T MR system using a single-shot fast spin echo (SSFSE) T2 sequence, slice thickness 3 mm, no gap. Four out of the 56 scans could not be used in the analysis due to poor image quality. Automatic segmentation (using NIH Image routines) was found to be unreliable in these fetal brains, so cerebral, cerebellar and ventricular regions were traced manually. Ventricular volumes did not vary with gestational age in normal fetuses (N=27, R=0.05, p=0.8) while cerebral parenchyma and cerebellum volumes increased significantly during the same period (R=0.67, p=0.0002 and R=0.51, p=0.0066 respectively). Two calculated parameters: percent ventricular asymmetry and volume ratio of ventricles to hemispheric parenchyma were found to be very sensitive to ventricular pathology; such that the mean value of the latter in normal fetuses was 4.4%+/-0.56 (mean+/-SEM, N=27) compared to 34.3%+/-17.6 (N=6, p<0.0001) in fetuses with ventriculomegaly. These results support the use of image analysis and MRI to produce normal growth curves as well as quantitative severity assessments of brain pathologies in the developing human fetus.