Dilatation of Lateral Ventricles with Brain Volumes in Infants with 3D Transfontanelle US

Boucher, Marc-Antoine; Lippé, Sarah; Damphousse, Amélie; El-Jalbout, Ramy; Kadoury, Samuel

doi:10.48550/arxiv.1806.02305

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 3D US data, its segmentation was achieved non automatically by [23] using a multi-atlas deformable registration method and by [24] employing an intensity-based surface-evolution method. It was achieved automatically by [25] utilizing a multiphase geodesic level-set method based on phase congruency maps and by [26] using a 2D CNN.…”

Section: Related Workmentioning

confidence: 99%

“…It has no clue whether it comes from inside the brain, the cortex prefrontal area or the cerebellum area. Nevertheless, the automation of the conventional methods used in 3D ultrasound to segment CVS [23,25] and in MRI to segment several brain structures [31,32] rely on the use of atlases. The latter allow to introduce an a priori on the position of the cerebral structures.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Segmentation and Location Learning of Neonatal Cerebral Ventricles in 3D Ultrasound Data Combining CNN and CPPN

Martin,

Sciolla,

Sdika

et al. 2020

Preprint

View full text Add to dashboard Cite

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 the CNNs 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 CNNs 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 cm 3 and 0.36 ± 0.24 cm 3 respectively (IOV = 0.41 ± 0.05 cm 3 ). 3D CNNs were more accurate than 2D CNNs 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 cm 3 against 0.35 ± 0.24 cm 3 (IOV = 0.2 ± 0.11 cm 3 ). The best segmentation time of volumes of size 320 × 320 × 320 was obtained by a 2D CNN in 3.5 ± 0.2 s.

show abstract