Computer-aided lateral ventricular and brain volume measurements in 3D ultrasound for assessing growth trajectories in newborns and neonates

FetSAM: Advanced Segmentation Techniques for Fetal Head Biometrics in Ultrasound Imagery

Goal: FetSAM represents a cutting-edge deep learning model aimed at revolutionizing fetal head ultrasound segmentation, thereby elevating prenatal diagnostic precision. Methods: Utilizing a comprehensive dataset-the largest to date for fetal head metrics-FetSAM incorporates prompt-based learning. It distinguishes itself with a dual loss mechanism, combining Weighted DiceLoss and Weighted Lovasz Loss, optimized through AdamW and underscored by class weight adjustments for better segmentation balance. Performance benchmarks against prominent models such as U-Net, DeepLabV3, and Segformer highlight its efficacy. Results: FetSAM delivers unparalleled segmentation accuracy, demonstrated by a DSC of 0.90117, HD of 1.86484, and ASD of 0.46645. Conclusion: FetSAM sets a new benchmark in AI-enhanced prenatal ultrasound analysis, providing a robust, precise tool for clinical applications and pushing the envelope of prenatal care with its groundbreaking dataset and segmentation capabilities.

A deep sift convolutional neural networks for total brain volume estimation from 3D ultrasound images

Preterm infants are a highly vulnerable population. The total brain volume (TBV) of these infants can be accurately estimated by brain ultrasound (US) imaging which enables a longitudinal study of early brain growth during Neonatal Intensive Care (NICU) admission. Automatic estimation of TBV from 3D images increases the diagnosis speed and evades the necessity for an expert to manually segment 3D images, which is a sophisticated and time consuming task. We develop a deep-learning approach to estimate TBV from 3D ultrasound images. It benefits from deep convolutional neural networks (CNN) with dilated residual connections and an additional layer, inspired by the fuzzy c-Means (FCM), to further separate the features into different regions, i.e. sift layer. Therefore, we call this method deep-sift convolutional neural networks (DSCNN). The proposed method is validated against three state-of-the-art methods including AlexNet-3D, ResNet-3D, and VGG-3D, for TBV estimation using two datasets acquired from two different ultrasound devices. The results highlight a strong correlation between the predictions and the observed TBV values. The regression activation maps are used to interpret DSCNN, allowing TBV estimation by exploring those pixels that are more consistent and plausible from an anatomical standpoint. Therefore, it can be used for direct estimation of TBV from 3D images without needing further image segmentation.

Ultrasonographic Estimation of Ventricular Volume in Infants Born Preterm with Posthemorrhagic Ventricular Dilatation: A Nested Substudy of the Randomized Controlled Early Versus Late Ventricular Intervention Study (ELVIS) Trial

OBJECTIVE

To study the potential role of ventricular volume (VV) estimation in the management of posthemorrhagic ventricular dilatation related to the need for ventriculoperitoneal (VP)-shunt insertion and 2-year neurodevelopmental outcome in infants born preterm.

STUDY DESIGN

We included 59 patients from the Early vs Late Ventricular Intervention Study from 4 participating centers. VV was manually segmented in 209 3-dimensional ultrasound scans and estimated from 2-dimensional ultrasound linear measurements in a total of 1226 ultrasounds. We studied the association of both linear measurements and VV to the need for VP shunt and 2-year neurodevelopmental outcome in the overall cohort and in the 29 infants who needed insertion of a reservoir. We used general estimating equations to account for repeated measures per individual.

RESULTS

Maximum pre-reservoir VV (β coefficient = 0.185, P = .0001) and gestational age at birth (β = -0.338; P = .0001) were related to the need for VP shunt. The estimated optimal single VV measurement cut point of 17 cm3 correctly classified 79.31% with an area under the curve of 0.76 (CI 95% 0.74-0.79). Maximum VV (β = 0.027; P = .012) together with VP shunt insertion (β = 3.773; P = .007) and gestational age (β = -0.273; P = .0001) were related to cognitive outcome at 2 years. Maximum ventricular index and anterior horn width before reservoir insertion were independently associated with the need of VP shunt and the proposed threshold groups in the Early vs Late Ventricular Intervention Study trial were associated with long-term outcome.

CONCLUSIONS

Pre-reservoir VV measurements were associated with the need for VP-shunt insertion and 2-year cognitive outcome among infants born preterm with posthemorrhagic ventricular dilatation.

TRIAL REGISTRATION

ISRCTN43171322.

Impact of brain overgrowth on sensorial learning processing during the first year of life

Macrocephaly is present in about 2–5% of the general population. It can be found as an isolated benign trait or as part of a syndromic condition. Brain overgrowth has been associated with neurodevelopmental disorders such as autism during the first year of life, however, evidence remains inconclusive. Furthermore, most of the studies have involved pathological or high-risk populations, but little is known about the effects of brain overgrowth on neurodevelopment in otherwise neurotypical infants. We investigated the impact of brain overgrowth on basic perceptual learning processes (repetition effects and change detection response) during the first year of life. We recorded high density electroencephalograms (EEG) in 116 full-term healthy infants aged between 3 and 11 months, 35 macrocephalic (14 girls) and 81 normocephalic (39 girls) classified according to the WHO head circumference norms. We used an adapted oddball paradigm, time-frequency analyses, and auditory event-related brain potentials (ERPs) to investigate differences between groups. We show that brain overgrowth has a significant impact on repetition effects and change detection response in the 10–20 Hz frequency band, and in N450 latency, suggesting that these correlates of sensorial learning processes are sensitive to brain overgrowth during the first year of life.

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.

Reference Charts for Neonatal Cranial Volume Based on 3D Laser Scanning to Monitor Head Growth

Background: Postnatal brain growth is an important predictor of neurodevelopmental outcome in preterm infants. A new reliable proxy for brain volume is cranial volume, which can be measured routinely by 3-D laser scanning. The aim of this study was to develop reference charts for normal cranial volume in newborn infants at different gestational ages starting from late preterm for both sexes. Methods: Cross-sectional cohort study in a German university hospital, including singleton, clinically stable, neonates born after 34 weeks of gestation. Cranial volume was measured in the first week of life by a validated 3-D laser scanner. Cranial volume data was modeled to calculate percentile values by gestational age and birth weight and to develop cranial volume reference charts for girls and boys separately. Results: Of the 1,703 included infants, 846 (50%) were female. Birth weights ranged from 1,370 to 4,830 grams (median 3,370). Median cranial volume ranged from 320 [interquartile range (IQR) 294-347] ml at 34 weeks to 469 [IQR 442-496] ml at 42 weeks and was higher in boys than in girls. Conclusions: This study presents the first reference charts of cranial volume which can be used in clinical practice to monitor brain growth between 34 and 42 weeks gestation in infants.