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

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.

Application value of cranial ultrasonography in quantitative evaluation of neonatal intracranial hemorrhage

BACKGROUND

Intracranial hemorrhage is a severe cranial disease in the perinatal period. We aimed to explore the feasibility and accuracy of three-dimensional (3D) ultrasonography for the quantitative evaluation of neonatal intracranial hemorrhage.

METHODS

A total of 374 neonates with suspected intracranial hemorrhage from January 2017 to December 2019 were selected to be primarily screened by cranial ultrasonography and then diagnosed by cranial CT scan. The examination results were compared to analyze the feasibility and accuracy of 3D ultrasonography in quantifying blood loss.

RESULTS

CT scan showed that there were 102 cases of Papile grade I, 106 cases of grade II, 124 cases of grade III and 42 cases of grade IV. 3D ultrasonography showed that there were 108 cases of Papile grade I, 98 cases of grade II, 130 cases of grade III and 38 cases of grade IV. The diagnostic results of these two methods were not significantly different (P>0.05). The accuracies of CT scan for subventricular, intraventricular, subdural, subarachnoid and intraparenchymal hemorrhages were 47.33%, 31.24%, 94.62%, 91.73% and 91.35% respectively, and those of 3D ultrasonography were 98.74%, 96.37%, 91.51%, 90.41% and 97.64% respectively. The accuracies of 3D ultrasonography were significantly superior to those of CT scan for subependymal, intraventricular and intraparenchymal hemorrhages (P<0.05).

CONCLUSIONS

Neonatal intracranial hemorrhage can be well diagnosed by cranial ultrasonography which timely provides evidence for clinicians, thereby elevating the cure rate and reducing the mortality rate and incidence rate of sequelae. 3D ultrasonography is feasible and accurate for the quantitative evaluation of neonatal intracranial hemorrhage, thus being of great significance to prognostic determination in clinical practice.

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.

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.

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.