Automatic segmentation approach to extracting neonatal cerebral ventricles from 3D ultrasound images

Neurosonography: Shaping the future of neuroprotection strategies in extremely preterm infants

This review aims to explore the current application of Cranial Ultrasound Screening (CUS) in the diagnosis and treatment of brain diseases in extremely preterm infants. It also discusses the potential role of emerging ultrasound-derived technologies such as Super Microvascular Structure Imaging (SMI), Shear Wave Elastography (SWE), Ultrafast Doppler Ultrasound (UfD), and 3D ventricular volume assessment and automated segmentation techniques in clinical practice. A systematic search of medical databases was conducted using the keywords "(preterm OR extremely preterm OR extremely low birth weight) AND (ultrasound OR ultrasound imaging) AND (neurodevelopment OR brain development OR brain diseases OR brain injury OR neuro*)" to identify relevant literature. The titles, abstracts, and full texts of the identified articles were carefully reviewed to determine their relevance to the research topic. CUS offers unique advantages in early screening and monitoring of brain diseases in extremely preterm infants, as it can be performed at the bedside without the need for anesthesia or special monitoring. This technique facilitates early detection and intervention of conditions such as intraventricular hemorrhage, white matter injury, hydrocephalus, and hypoxic-ischemic injury in critically ill preterm infants. Continuous refinement of the screening and follow-up processes provides reliable clinical decision-making support for healthcare professionals and parents. Emerging ultrasound technologies, such as SWE, SMI, and UfD, are being explored to provide more accurate and in-depth understanding of brain diseases in extremely preterm infants. SWE has demonstrated its effectiveness in assessing the elasticity of neonatal brain tissue, aiding in the localization and quantification of potential brain injuries. SMI can successfully identify microvascular structures in the brain, offering a new perspective on neurologic diseases. UfD provides a high-sensitivity and quantitative imaging method for the prevention and treatment of neonatal brain diseases by detecting subtle changes in red blood cell movement and accurately assessing the status and progression of brain diseases. CUS and its emerging technologies have significant applications in the diagnosis and treatment of brain diseases in extremely preterm infants. Future research aims to address current technical challenges, optimize and enhance the clinical decision-making capabilities related to brain development, and improve the prevention and treatment outcomes of brain diseases in extremely preterm infants.

Semi-supervised learning framework with shape encoding for neonatal ventricular segmentation from 3D ultrasound

BACKGROUND

Three-dimensional (3D) ultrasound (US) imaging has shown promise in non-invasive monitoring of changes in the lateral brain ventricles of neonates suffering from intraventricular hemorrhaging. Due to the poorly defined anatomical boundaries and low signal-to-noise ratio, fully supervised methods for segmentation of the lateral ventricles in 3D US images require a large dataset of annotated images by trained physicians, which is tedious, time-consuming, and expensive. Training fully supervised segmentation methods on a small dataset may lead to overfitting and hence reduce its generalizability. Semi-supervised learning (SSL) methods for 3D US segmentation may be able to address these challenges but most existing SSL methods have been developed for magnetic resonance or computed tomography (CT) images.

PURPOSE

To develop a fast, lightweight, and accurate SSL method, specifically for 3D US images, that will use unlabeled data towards improving segmentation performance.

METHODS

We propose an SSL framework that leverages the shape-encoding ability of an autoencoder network to enforce complex shape and size constraints on a 3D U-Net segmentation model. The autoencoder created pseudo-labels, based on the 3D U-Net predicted segmentations, that enforces shape constraints. An adversarial discriminator network then determined whether images came from the labeled or unlabeled data distributions. We used 887 3D US images, of which 87 had manually annotated labels and 800 images were unlabeled. Training/validation/testing sets of 25/12/50, 25/12/25 and 50/12/25 images were used for model experimentation. The Dice similarity coefficient (DSC), mean absolute surface distance (MAD), and absolute volumetric difference (VD) were used as metrics for comparing to other benchmarks. The baseline benchmark was the fully supervised vanilla 3D U-Net while dual task consistency, shape-aware semi-supervised network, correlation-aware mutual learning, and 3D U-Net Ensemble models were used as state-of-the-art benchmarks with DSC, MAD, and VD as comparison metrics. The Wilcoxon signed-rank test was used to test statistical significance between algorithms for DSC and VD with the threshold being p < 0.05 and corrected to p < 0.01 using the Bonferroni correction. The random-access memory (RAM) trace and number of trainable parameters were used to compare the computing efficiency between models.

RESULTS

Relative to the baseline 3D U-Net model, our shape-encoding SSL method reported a mean DSC improvement of 6.5%, 7.7%, and 4.1% with a 95% confidence interval of 4.2%, 5.7%, and 2.1% using image data splits of 25/12/50, 25/12/25, and 50/12/25, respectively. Our method only used a 1GB increase in RAM compared to the baseline 3D U-Net and required less than half the RAM and trainable parameters compared to the 3D U-Net ensemble method.

CONCLUSIONS

Based on our extensive literature survey, this is one of the first reported works to propose an SSL method designed for segmenting organs in 3D US images and specifically one that incorporates unlabeled data for segmenting neonatal cerebral lateral ventricles. When compared to the state-of-the-art SSL and fully supervised learning methods, our method yielded the highest DSC and lowest VD while being computationally efficient.

Fetal face shape analysis from prenatal 3D ultrasound images

3D ultrasound imaging of fetal faces has been predominantly confined to qualitative assessment. Many genetic conditions evade diagnosis and identification could assist with parental counselling, pregnancy management and neonatal care planning. We describe a methodology to build a shape model of the third trimester fetal face from 3D ultrasound and show how it can objectively describe morphological features and gestational-age related changes of normal fetal faces. 135 fetal face 3D ultrasound volumes (117 appropriately grown, 18 growth-restricted) of 24-34 weeks gestation were included. A 3D surface model of each face was obtained using a semi-automatic segmentation workflow. Size normalisation and rescaling was performed using a growth model giving the average size at every gestation. The model demonstrated a similar growth rate to standard head circumference reference charts. A landmark-free morphometry model was estimated to characterize shape differences using non-linear deformations of an idealized template face. Advancing gestation is associated with widening/fullness of the cheeks, contraction of the chin and deepening of the eyes. Fetal growth restriction is associated with a smaller average facial size but no morphological differences. This model may eventually be used as a reference to assist in the prenatal diagnosis of congenital anomalies with characteristic facial dysmorphisms.

Structural Alterations of the Corpus Callosum in Children With Infantile Hydrocephalus

This study investigates structural alterations of the corpus callosum in children diagnosed with infantile hydrocephalus. We aim to assess both macrostructural (volume) and microstructural (diffusion tensor imaging metrics) facets of the corpus callosum, providing insights into the nature and extent of alterations associated with this condition. Eighteen patients with infantile hydrocephalus (mean age = 9 years) and 18 age- and sex-matched typically developing healthy children participated in the study. Structural magnetic resonance imaging and diffusion tensor imaging were used to assess corpus callosum volume and microstructure, respectively. Our findings reveal significant alterations in corpus callosum volume, particularly in the posterior area, as well as distinct microstructural disparities, notably pronounced in these same segments. These results highlight the intricate interplay between macrostructural and microstructural aspects in understanding the impact of infantile hydrocephalus. Examining these structural alterations provides an understanding into the mechanisms underlying the effects of infantile hydrocephalus on corpus callosum integrity, given its pivotal role in interhemispheric communication. This knowledge offers a more nuanced perspective on neurologic disorders and underscores the significance of investigating the corpus callosum's health in such contexts.

Brain Network Connectivity and Executive Function in Children with Previous Infantile Hydrocephalus

INTRODUCTION

Infantile hydrocephalus is a condition in which there is an abnormal build-up of cerebrospinal fluid in the ventricles within the first few months of life, which puts pressure on surrounding brain tissues. Compression of the developing brain increases the risk of secondary brain injury and cognitive disabilities.

METHODS

In this study, we used diffusion-weighted imaging and resting-state functional MRI to investigate the effects of ventricle dilatation on structural and functional brain networks in children with shunted infantile hydrocephalus and examined how these brain changes may impact executive function.

RESULTS

We found that children with hydrocephalus have altered structural and functional connectivity between and within large-scale networks. Moreover, hyperconnectivity between the ventral attention and default mode network in children with hydrocephalus correlated with reduced executive function scores. Compared to typically developing age-matched control participants, our patient population also had lower fractional anisotropy in posterior white matter.

DISCUSSION

Overall, these findings suggest that infantile hydrocephalus has long-term effects on brain network connectivity, white matter development, and executive function in children at school-age. Future work will examine the relationship between ventricular volumes prior to shunt placement in infancy and brain network development throughout childhood.

Automatic brain segmentation in preterm infants with post-hemorrhagic hydrocephalus using 3D Bayesian U-Net

Post‐hemorrhagic hydrocephalus (PHH) is a severe complication of intraventricular hemorrhage (IVH) in very preterm infants. PHH monitoring and treatment decisions rely heavily on manual and subjective two‐dimensional measurements of the ventricles. Automatic and reliable three‐dimensional (3D) measurements of the ventricles may provide a more accurate assessment of PHH, and lead to improved monitoring and treatment decisions. To accurately and efficiently obtain these 3D measurements, automatic segmentation of the ventricles can be explored. However, this segmentation is challenging due to the large ventricular anatomical shape variability in preterm infants diagnosed with PHH. This study aims to (a) propose a Bayesian U‐Net method using 3D spatial concrete dropout for automatic brain segmentation (with uncertainty assessment) of preterm infants with PHH; and (b) compare the Bayesian method to three reference methods: DenseNet, U‐Net, and ensemble learning using DenseNets and U‐Nets. A total of 41 T₂‐weighted MRIs from 27 preterm infants were manually segmented into lateral ventricles, external CSF, white and cortical gray matter, brainstem, and cerebellum. These segmentations were used as ground truth for model evaluation. All methods were trained and evaluated using 4‐fold cross‐validation and segmentation endpoints, with additional uncertainty endpoints for the Bayesian method. In the lateral ventricles, segmentation endpoint values for the DenseNet, U‐Net, ensemble learning, and Bayesian U‐Net methods were mean Dice score = 0.814 ± 0.213, 0.944 ± 0.041, 0.942 ± 0.042, and 0.948 ± 0.034 respectively. Uncertainty endpoint values for the Bayesian U‐Net were mean recall = 0.953 ± 0.037, mean  negative predictive value = 0.998 ± 0.005, mean accuracy = 0.906 ± 0.032, and mean AUC = 0.949 ± 0.031. To conclude, the Bayesian U‐Net showed the best segmentation results across all methods and provided accurate uncertainty maps. This method may be used in clinical practice for automatic brain segmentation of preterm infants with PHH, and lead to better PHH monitoring and more informed treatment decisions.

Automated 3D U-net based segmentation of neonatal cerebral ventricles from 3D ultrasound images

BACKGROUND

Intraventricular hemorrhaging (IVH) within cerebral lateral ventricles affects 20-30% of very low birth weight infants (<1500g). As the ventricles increase in size, the intracranial pressure increases leading to post-hemorrhagic ventricle dilatation (PHVD), an abnormal enlargement of the head. The most widely used imaging tool for measuring IVH and PHVD is cranial two-dimensional (2D) ultrasound (US). Estimating volumetric changes over time with 2D US is unreliable due to high user variability when locating the same anatomical location at different scanning sessions. Compared to 2D US, three-dimensional (3D) US is more sensitive to volumetric changes in the ventricles and does not suffer from variability in slice acquisition. However, 3D US images require segmentation of the ventricular surface, which is tedious and time-consuming when done manually.

PURPOSE

A fast, automated ventricle segmentation method for 3D US would provide quantitative information in a timely manner when monitoring IVH and PHVD in pre-term neonates. To this end, we developed a fast and fully automated segmentation method to segment neonatal cerebral lateral ventricles from 3D ultrasound images using deep learning.

METHODS

Our method consists of a 3D U-Net ensemble model comprised of three U-Net variants, each highlighting various aspects of the segmentation task such as the shape and boundary of the ventricles. The ensemble is made of a U-Net++, Attention U-Net, and U-Net with a deep learning-based shape prior combined using a mean voting strategy. We used a dataset consisting of 190 3D US images, which was separated into two subsets, one set of 87 images contained both ventricles and one set of 103 images contained only one ventricle (caused by limited field-of-view during acquisition). We conducted 5-fold cross-validation to evaluate the performance of the models on a larger amount of test data; 165 test images of which 75 have two ventricles (two-ventricle images) and 90 have one ventricle (one-ventricle images). We compared these results to each stand-alone model and to previous works including 2D multiplane U-Net and 2D SegNet models.

RESULTS

Using 5-fold cross-validation, the ensemble method reported a Dice similarity coefficient (DSC) of 0.720±0.074, absolute volumetric difference (VD) of 3.7±4.1cm³ , and a mean absolute surface distance (MAD) of 1.14±0.41mm on 75 two-ventricle test images. Using 90 test images with a single ventricle, the model after cross-validation reported DSC, VD, and MAD values of 0.806±0.111, 3.5±2.9cm³ , and 1.37±1.70mm, respectively. Compared to alternatives, the proposed ensemble yielded a higher accuracy in segmentation on both test data sets. Our method required approximately five seconds to segment one image and was substantially faster than the state-of-the-art conventional methods.

CONCLUSIONS

Compared to the state-of-the-art non-deep learning methods, our method based on deep learning was more efficient in segmenting neonatal cerebral lateral ventricles from 3D US images with comparable or better DSC, VD, and MAD performance. Our dataset was the largest to date (190 images) for this segmentation problem and the first to segment images that show only one lateral cerebral ventricle. This article is protected by copyright. All rights reserved.

Precision Medicine in Neonates: A Tailored Approach to Neonatal Brain Injury

Despite advances in neonatal care to prevent neonatal brain injury and neurodevelopmental impairment, predicting long-term outcome in neonates at risk for brain injury remains difficult. Early prognosis is currently based on cranial ultrasound (CUS), MRI, EEG, NIRS, and/or general movements assessed at specific ages, and predicting outcome in an individual (precision medicine) is not yet possible. New algorithms based on large databases and machine learning applied to clinical, neuromonitoring, and neuroimaging data and genetic analysis and assays measuring multiple biomarkers (omics) can fulfill the needs of modern neonatology. A synergy of all these techniques and the use of automatic quantitative analysis might give clinicians the possibility to provide patient-targeted decision-making for individualized diagnosis, therapy, and outcome prediction. This review will first focus on common neonatal neurological diseases, associated risk factors, and most common treatments. After that, we will discuss how precision medicine and machine learning (ML) approaches could change the future of prediction and prognosis in this field.

Kidney Segmentation in 3-D Ultrasound Images Using a Fast Phase-Based Approach

Renal ultrasound (US) imaging is the primary imaging modality for the assessment of the kidney's condition and is essential for diagnosis, treatment and surgical intervention planning, and follow-up. In this regard, kidney delineation in 3-D US images represents a relevant and challenging task in clinical practice. In this article, a novel framework is proposed to accurately segment the kidney in 3-D US images. The proposed framework can be divided into two stages: 1) initialization of the segmentation method and 2) kidney segmentation. Within the initialization stage, a phase-based feature detection method is used to detect edge points at kidney boundaries, from which the segmentation is automatically initialized. In the segmentation stage, the B-spline explicit active surface framework is adapted to obtain the final kidney contour. Here, a novel hybrid energy functional that combines localized region- and edge-based terms is used during segmentation. For the edge term, a fast-signed phase-based detection approach is applied. The proposed framework was validated in two distinct data sets: 1) 15 3-D challenging poor-quality US images used for experimental development, parameters assessment, and evaluation and 2) 42 3-D US images (both healthy and pathologic kidneys) used to unbiasedly assess its accuracy. Overall, the proposed method achieved a Dice overlap around 81% and an average point-to-surface error of ~2.8 mm. These results demonstrate the potential of the proposed method for clinical usage.

Automatic segmentation and location learning of neonatal cerebral ventricles in 3D ultrasound data combining CNN and CPPN

Preterm neonates are highly likely to suffer from ventriculomegaly, a dilation of the Cerebral Ventricular System (CVS). This condition can develop into life-threatening hydrocephalus and is correlated with future neuro-developmental impairments. Consequently, it must be detected and monitored by physicians. In clinical routing, manual 2D measurements are performed on 2D ultrasound (US) images to estimate the CVS volume but this practice is imprecise due to the unavailability of 3D information. A way to tackle this problem would be to develop automatic CVS segmentation algorithms for 3D US data. In this paper, we investigate the potential of 2D and 3D Convolutional Neural Networks (CNN) to solve this complex task and propose to use Compositional Pattern Producing Network (CPPN) to enable Fully Convolutional Networks (FCN) to learn CVS location. Our database was composed of 25 3D US volumes collected on 21 preterm nenonates at the age of 35.8±1.6 gestational weeks. We found that the CPPN enables to encode CVS location, which increases the accuracy of the CNNs when they have few layers. Accuracy of the 2D and 3D FCNs reached intraobserver variability (IOV) in the case of dilated ventricles with Dice of 0.893±0.008 and 0.886±0.004 respectively (IOV = 0.898±0.008) and with volume errors of 0.45±0.42 cm³ and 0.36±0.24 cm³ respectively (IOV = 0.41±0.05 cm³). 3D FCNs were more accurate than 2D FCNs in the case of normal ventricles with Dice of 0.797±0.041 against 0.776±0.038 (IOV = 0.816±0.009) and volume errors of 0.35±0.29 cm³ against 0.35±0.24 cm³ (IOV = 0.2±0.11 cm³). The best segmentation time of volumes of size 320×320×320 was obtained by a 2D FCN in 3.5±0.2 s.

Automatic segmentation of ventricular volume by 3D ultrasonography in post haemorrhagic ventricular dilatation among preterm infants

To train, evaluate, and validate the application of a deep learning framework in three-dimensional ultrasound (3D US) for the automatic segmentation of ventricular volume in preterm infants with post haemorrhagic ventricular dilatation (PHVD). We trained a 2D convolutional neural network (CNN) for automatic segmentation ventricular volume from 3D US of preterm infants with PHVD. The method was validated with the Dice similarity coefficient (DSC) and the intra-class coefficient (ICC) compared to manual segmentation. The mean birth weight of the included patients was 1233.1 g (SD 309.4) and mean gestational age was 28.1 weeks (SD 1.6). A total of 152 serial 3D US from 10 preterm infants with PHVD were analysed. 230 ventricles were manually segmented. Of these, 108 were used for training a 2D CNN and 122 for validating the methodology for automatic segmentation. The global agreement for manual versus automated measures in the validation data (n = 122) was excellent with an ICC of 0.944 (0.874–0.971). The Dice similarity coefficient was 0.8 (± 0.01). 3D US based ventricular volume estimation through an automatic segmentation software developed through deep learning improves the accuracy and reduces the processing time needed for manual segmentation using VOCAL. 3D US should be considered a promising tool to help deepen our current understanding of the complex evolution of PHVD.

No-Reference Image Quality Assessment Based on the Fusion of Statistical and Perceptual Features

The goal of no-reference image quality assessment (NR-IQA) is to predict the quality of an image as perceived by human observers without using any pristine, reference images. In this study, an NR-IQA algorithm is proposed which is driven by a novel feature vector containing statistical and perceptual features. Different from other methods, normalized local fractal dimension distribution and normalized first digit distributions in the wavelet and spatial domains are incorporated into the statistical features. Moreover, powerful perceptual features, such as colorfulness, dark channel feature, entropy, and mean of phase congruency image, are also incorporated to the proposed model. Experimental results on five large publicly available databases (KADID-10k, ESPL-LIVE HDR, CSIQ, TID2013, and TID2008) show that the proposed method is able to outperform other state-of-the-art methods.

Ultrasound-Based Phenotyping of Lateral Ventricles to Predict Hydrocephalus Outcome in Premature Neonates

OBJECTIVE

Prediction of post-hemorrhagic hydrocephalus (PHH) outcome-i.e., whether it requires intervention or not-in premature neonates using cranial ultrasound (CUS) images is challenging. In this paper, we present a novel fully-automatic method to perform phenotyping of the brain lateral ventricles and predict PHH outcome from CUS.

METHODS

Our method consists of two parts: ventricle quantification followed by prediction of PHH outcome. First, cranial bounding box and brain interhemispheric fissure are detected to determine the anatomical position of ventricles and correct the cranium rotation. Then, lateral ventricles are extracted using a new deep learning-based method by incorporating the convolutional neural network into a probabilistic atlas-based weighted loss function and an image-specific adaption. PHH outcome is predicted using a support vector machine classifier trained using ventricular morphological phenotypes and clinical information.

RESULTS

Experiments demonstrated that our method achieves accurate ventricle segmentation results with an average Dice similarity coefficient of 0.86, as well as very good PHH outcome prediction with accuracy of 0.91.

CONCLUSION

Automatic CUS-based ventricular phenotyping in premature newborns could objectively and accurately predict the progression to severe PHH.

SIGNIFICANCE

Early prediction of severe PHH development in premature newborns could potentially advance criteria for diagnosis and offer an opportunity for early interventions to improve outcome.

Automatic Segmentation of Neonatal Ventricles from Cranial Ultrasound for Prediction of Intraventricular Hemorrhage Outcome

Intraventricular hemorrhage (IVH) followed by post hemorrhagic hydrocephalus (PHH) in premature neonates is one of the recognized reasons of brain injury in newborns. Cranial ultrasound (CUS) is a noninvasive imaging tool that has been used widely to diagnose and monitor neonates with IVH. In our previous work, we showed the potential of quantitative morphological analysis of lateral ventricles from early CUS to predict the PHH outcome in neonates with IVH. In this paper, we first present a new automatic method for ventricle segmentation in 2D CUS images. We detect the brain bounding box and brain mid-line to estimate the anatomical positions of ventricles and correct the brain rotation. The ventricles are segmented using a combination of fuzzy c-means, phase congruency, and active contour algorithms. Finally, we compare this fully automated approach with our previous work for the prediction of the outcome of PHH on a set of 2D CUS images taken from 60 premature neonates with different IVH grades. Experimental results showed that our method could segment ventricles with an average Dice similarity coefficient of 0.8 ± 0.12. In addition, our fully automated method could predict the outcome of PHH based on the extracted ventricle regions with similar accuracy to our previous semi-automated approach (83% vs. 84%, respectively, p-value = 0.8). This method has the potential to standardize the evaluation of CUS images and can be a helpful clinical tool for early monitoring and treatment of IVH and PHH.

Comparison of MRI and neurosonogram 1- and 2-dimensional morphological measurements of the newborn corpus callosum

BACKGROUND

Developmental abnormalities of the corpus callosum (CC) are linked to multiple neuro-developmental disorders, for which neonatal neuroimaging may allow earlier diagnosis and intervention. MRI is often considered the most sensitive imaging modality to white matter changes, while neurosonogram (NS) remains the clinical staple. This study assesses the correlation between MRI and US measurements of the neonatal CC using a protocol derived from established methodologies.

METHODS

MR and NS images from an existing cohort of term infants (≥37 weeks gestational age) were studied. Length and area measurements of the CC made with linear (LUS) and phased array US (PUS) data were compared to those from MRI. Intra-observer reliabilities were estimated.

RESULTS

Moderate-to-strong correlation strengths were observed for length measurements and the total area of the CC. Sectional area measurements showed poorer correlations. Bland-Altman plots support improved correspondence of length and total area measurements. LUS data appeared to correspond closer to MRI. All three modalities showed comparable repeatability.

CONCLUSION

NS correlates well with some MRI measurements of the CC and shows similar levels of repeatability, making them possibly interchangeable. Use of LUS, a technique rarely used for NS, may be preferable to the standard approach for morphological studies.

Automated brain extraction from head CT and CTA images using convex optimization with shape propagation

BACKGROUND AND OBJECTIVE

Non-Contrast Computer Tomography (NCCT) and CT angiography (CTA) are the most used and widely acceptable imaging modalities in clinical practice for the diagnosis and treatment of acute ischemic stroke (AIS) patients. Brain extraction of CT/CTA images plays an essential role in stroke imaging research. There is no robust automated brain extraction method in the literature that is well established for both NCCT and CTA images. Thus, a validated and automated brain extraction tool for CT imaging would be of great value for both research and clinical practice.

METHODS

The proposed brain extraction method is based on the contour evolution technique, which extracts brain tissues from acquired NCCT and CTA images in a slice-by-slice fashion. Specifically, the proposed approach makes use of a novel propagation framework, which is initialized by a localized slice with the largest brain section in axial views, followed by a geodesic level-set evolution for automatically extracting the brain section in each slice. In particular, the segmented contour propagated from the previous slice is reused to penalize the defined object function for contour evolution to enforce the shape continuity between any two adjacent contours. We show that the defined contour evolution function can be solved iteratively by globally optimal convex optimization.

RESULTS

The proposed brain extraction approach is quantitatively evaluated using 40 NCCT and CTA images acquired from 20 AIS patients and drawn from 4 different vendors, compared to manual segmentations using Dice and Jaccard coefficient metrics. The quantitative results show that the proposed segmentation algorithm is consistently accurate for both NCCT and CTA images using Dice metric. The proposed method is further validated on 1736 NCCT and CTA images of 1331 AIS patients acquired from three multi-national multi-centric clinical trials. A visual check performed on these data demonstrates a low failure rate of 0.4% for 1331 NCCT images and a zero-failure rate for 405 CTA images.

CONCLUSIONS

Both quantitative and qualitative evaluation suggest that the proposed brain extraction approach for NCCT and CTA images can be used for different clinical imaging settings, thus serving to improve current image analysis in the field of neuroimaging.

AUTOMATIC BODY LOCALIZATION AND BRAIN VENTRICLE SEGMENTATION IN 3D HIGH FREQUENCY ULTRASOUND IMAGES OF MOUSE EMBRYOS

This paper presents a fully automatic segmentation system for whole-body high-frequency ultrasound (HFU) images of mouse embryos that can simultaneously segment the body contour and the brain ventricles (BVs). Our system first locates a region of interest (ROI), which covers the interior of the uterus, by sub-surface analysis. Then, it segments the ROI into BVs, the body, the amniotic fluid, and the uterine wall, using nested graph cut. Simultaneously multilevel thresholding is applied to the whole-body image to propose candidate BV components. These candidates are further truncated by the embryo mask (body+BVs) to refine the BV candidates. Finally, subsets of all candidate BVs are compared with pre-trained spring models describing valid BV structures, to identify true BV components. The system can segment the body accurately in most cases based on visual inspection, and achieves average Dice similarity coefficient of 0.8924 ± 0.043 for the BVs on 36 HFU image volumes.

Ventricular shape evaluation on early ultrasound predicts post-hemorrhagic hydrocephalus

BACKGROUND

To compare the ability of ventricular morphology on cranial ultrasound (CUS) versus standard clinical variables to predict the need for temporizing cerebrospinal fluid drainage in newborns with intraventricular hemorrhage (IVH).

METHOD

This is a retrospective study of newborns (gestational age <29 weeks) diagnosed with IVH. Clinical variables known to increase the risk for post-hemorrhagic hydrocephalus were collected. The first CUS with IVH was identified and a slice in the coronal plane was selected. The frontal horns of the lateral ventricles were manually segmented. Automated quantitative morphological features were extracted from both lateral ventricles. Predictive models of the need of temporizing intervention were compared.

RESULTS

Sixty-two newborns met inclusion criteria. Fifteen out of the 62 had a temporizing intervention. The morphological features had a better accuracy predicting temporizing interventions when compared to clinical variables: 0.94 versus 0.85, respectively; p < 0.01 for both. By considering both morphological and clinical variables, our method predicts the need of temporizing intervention with positive and negative predictive values of 0.83 and 1, respectively, and accuracy of 0.97.

CONCLUSION

Early cranial ultrasound-based quantitative ventricular evaluation in premature newborns can predict the eventual use of a temporizing intervention to treat post-hemorrhagic hydrocephalus. This may be helpful for early monitoring and treatment.

Quantitative 3-D head ultrasound measurements of ventricle volume to determine thresholds for preterm neonates requiring interventional therapies following posthemorrhagic ventricle dilatation

Dilatation of the cerebral ventricles is a common condition in preterm neonates with intraventricular hemorrhage. This posthemorrhagic ventricle dilatation (PHVD) can lead to lifelong neurological impairment through ischemic injury due to increased intracranial pressure, and without treatment can lead to death. Two-dimensional ultrasound (US) through the fontanelles of the patients is serially acquired to monitor the progression of PHVD. These images are used in conjunction with clinical experience and physical exams to determine when interventional therapies such as needle aspiration of the built up cerebrospinal fluid (ventricle tap, VT) might be indicated for a patient; however, quantitative measurements of the ventricles size are often not performed. We describe the potential utility of the quantitative three-dimensional (3-D) US measurements of ventricle volumes (VVs) in 38 preterm neonates to monitor and manage PHVD. Specifically, we determined 3-D US VV thresholds for patients who received VT in comparison to patients with PHVD who resolve without intervention. In addition, since many patients who have an initial VT will receive subsequent interventions, we determined which PHVD patients will receive additional VT after the initial one has been performed.

Automatically measuring brain ventricular volume within PACS using artificial intelligence

The picture archiving and communications system (PACS) is currently the standard platform to manage medical images but lacks analytical capabilities. Staying within PACS, the authors have developed an automatic method to retrieve the medical data and access it at a voxel level, decrypted and uncompressed that allows analytical capabilities while not perturbing the system’s daily operation. Additionally, the strategy is secure and vendor independent. Cerebral ventricular volume is important for the diagnosis and treatment of many neurological disorders. A significant change in ventricular volume is readily recognized, but subtle changes, especially over longer periods of time, may be difficult to discern. Clinical imaging protocols and parameters are often varied making it difficult to use a general solution with standard segmentation techniques. Presented is a segmentation strategy based on an algorithm that uses four features extracted from the medical images to create a statistical estimator capable of determining ventricular volume. When compared with manual segmentations, the correlation was 94% and holds promise for even better accuracy by incorporating the unlimited data available. The volume of any segmentable structure can be accurately determined utilizing the machine learning strategy presented and runs fully automatically within the PACS.

Patient-specific model-based segmentation of brain tumors in 3D intraoperative ultrasound images

PURPOSE

Intraoperative ultrasound (iUS) imaging is commonly used to support brain tumor operation. The tumor segmentation in the iUS images is a difficult task and still under improvement because of the low signal-to-noise ratio. The success of automatic methods is also limited due to the high noise sensibility. Therefore, an alternative brain tumor segmentation method in 3D-iUS data using a tumor model obtained from magnetic resonance (MR) data for local MR-iUS registration is presented in this paper. The aim is to enhance the visualization of the brain tumor contours in iUS.

METHODS

A multistep approach is proposed. First, a region of interest (ROI) based on the specific patient tumor model is defined. Second, hyperechogenic structures, mainly tumor tissues, are extracted from the ROI of both modalities by using automatic thresholding techniques. Third, the registration is performed over the extracted binary sub-volumes using a similarity measure based on gradient values, and rigid and affine transformations. Finally, the tumor model is aligned with the 3D-iUS data, and its contours are represented.

RESULTS

Experiments were successfully conducted on a dataset of 33 patients. The method was evaluated by comparing the tumor segmentation with expert manual delineations using two binary metrics: contour mean distance and Dice index. The proposed segmentation method using local and binary registration was compared with two grayscale-based approaches. The outcomes showed that our approach reached better results in terms of computational time and accuracy than the comparative methods.

CONCLUSION

The proposed approach requires limited interaction and reduced computation time, making it relevant for intraoperative use. Experimental results and evaluations were performed offline. The developed tool could be useful for brain tumor resection supporting neurosurgeons to improve tumor border visualization in the iUS volumes.

Automatic renal lesion segmentation in ultrasound images based on saliency features, improved LBP, and an edge indicator under level set framework

PURPOSE

Segmentation of lesions in ultrasound images is widely used for preliminary diagnosis. In this paper, we develop an automatic segmentation algorithm for multiple types of lesions in ultrasound images. The proposed method is able to detect and segment lesions automatically as well as generate accurate segmentation results for lesion regions.

METHODS

In the detection step, two saliency detection frameworks which adopt global image information are designed to capture the differences between normal and abnormal organs as well as these between lesions and the normal tissues around them. In the segmentation step, three types of local information, i.e., image intensity, improved local binary patterns (LBP) features, and an edge indicator, are embedded into a modified level set framework to carry out the segmentation task.

RESULTS

The cyst and carcinoma regions in the ultrasound images of the human kidneys can be automatically detected and segmented by using the proposed method. The efficiency and accuracy of the method are validated by quantitative evaluations and comparative measurements with three well-recognized segmentation methods. Specifically, the average precision and dice coefficient of the proposed method in segmenting renal cysts are 95.33% and 90.16%, respectively, while those in segmenting renal carcinomas are 94.22% and 91.13%, respectively. The average precision and dice coefficient of the proposed method are higher than those of three compared segmentation methods.

CONCLUSIONS

The proposed method can efficiently detect and segment the renal lesions in ultrasound images. In addition, since the proposed method utilizes the differences between normal and abnormal organs as well as these between lesions and the normal tissues around them, it can be possibly extended to deal with lesions in other organs of ultrasound images as well as lesions in medical images of other modalities.

Preterm neonatal lateral ventricle volume from three-dimensional ultrasound is not strongly correlated to two-dimensional ultrasound measurements

The aim of this study is to compare longitudinal two-dimensional (2-D) and three-dimensional (3-D) ultrasound (US) estimates of ventricle size in preterm neonates with posthemorrhagic ventricular dilatation (PHVD) using quantitative measurements of the lateral ventricles. Cranial 2-D US and 3-D US images were acquired from neonatal patients with diagnosed PHVD within 10 min of each other one to two times per week and analyzed offline. Ventricle index, anterior horn width, third ventricle width, and thalamo-occipital distance were measured on the 2-D images and ventricle volume (VV) was measured from 3-D US images. Changes in the measurements between successive image sets were also recorded. No strong correlations were found between VV and 2-D US measurements ([Formula: see text] between 0.69 and 0.36). Additionally, weak correlations were found between changes in 2-D US measurements and 3-D US VV ([Formula: see text] between 0.13 and 0.02). A trend was found between increasing 2-D US measurements and 3-D US-based VV, but this was not the case when comparing changes between 3-D US VV and 2-D US measurements. If 3-D US-based VV provides a more accurate estimate of ventricle size than 2-D US measurements, moderate-weak correlations with 3-D US suggest that monitoring preterm patients with PHVD using 2-D US measurements alone might not accurately represent whether the ventricles are progressively dilating. A volumetric measure (3-D US or MRI) could be used instead to more accurately represent changes.