nach oben

10.05.2024 | Paediatric

Machine learning in prenatal MRI predicts postnatal ventricular abnormalities in fetuses with isolated ventriculomegaly

verfasst von: Xue Chen, Daqiang Xu, Xiaowen Gu, Zhisen Li, Yisha Zhang, Peng Wu, Zhou Huang, Jibin Zhang, Yonggang Li

Einloggen, um Zugang zu erhalten

Abstract

Objectives

To evaluate the intracranial structures and brain parenchyma radiomics surrounding the occipital horn of the lateral ventricle in normal fetuses (NFs) and fetuses with ventriculomegaly (FVs), as well as to predict postnatally enlarged lateral ventricle alterations in FVs.

Methods

Between January 2014 and August 2023, 141 NFs and 101 FVs underwent 1.5 T balanced steady-state free precession (BSSFP), including 68 FVs with resolved lateral ventricles (FVM-resolved) and 33 FVs with stable lateral ventricles (FVM-stable). Demographic data and intracranial structures were analyzed. To predict the enlarged ventricle alterations of FVs postnatally, logistic regression models with 5-fold cross-validation were developed based on lateral ventricle morphology, blended-cortical or/and subcortical radiomics characteristics. Validation of the models’ performance was conducted using the receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA).

Results

Significant alterations in cerebral structures were observed between NFs and FVs (p < 0.05), excluding the maximum frontal horn diameter (FD). However, there was no notable distinction between the FVM-resolved and FVM-stable groups (all p > 0.05). Based on subcortical-radiomics on the aberrant sides of FVs, this approach exhibited high efficacy in distinguishing NFs from FVs in the training/validation set, yielding an impressive AUC of 1/0.992. With an AUC value of 0.822/0.743 in the training/validation set, the Subcortical-radiomics model demonstrated its ability to predict lateral ventricle alterations in FVs, which had the greatest predictive advantages indicated by DCA.

Conclusions

Microstructural alterations in subcortical parenchyma associated with ventriculomegaly can serve as predictive indicators for postnatal lateral ventricle variations in FVs.

Clinical relevance statement

It is critical to gain pertinent information from a solitary fetal MRI to anticipate postnatal lateral ventricle alterations in fetuses with ventriculomegaly. This approach holds the potential to diminish the necessity for recurrent prenatal ultrasound or MRI examinations.

Key Points

Fetal ventriculomegaly is a dynamic condition that affects postnatal neurodevelopment.
Machine learning and subcortical-radiomics can predict postnatal alterations in the lateral ventricle.
Machine learning, applied to single-fetal MRI, might reduce required antenatal testing.

Nur mit Berechtigung zugänglich

Cardoza JD, Goldstein RB, Filly RA (1988) Exclusion of fetal ventriculomegaly with a single measurement: the width of the lateral ventricular atrium. Radiology 169:711–714. https://doi.org/10.1148/radiology.169.3.3055034CrossRefPubMed

Pilu G, Hobbins JC (2002) Sonography of fetal cerebrospinal anomalies. Prenat Diagn 22:321–330. https://doi.org/10.1002/pd.310CrossRefPubMed

Salomon LJ, Garel C (2007) Magnetic resonance imaging examination of the fetal brain. Ultrasound Obstet Gynecol 30:1019–1032. https://doi.org/10.1002/uog.5176CrossRefPubMed

Tarui T, Madan N, Graham G et al (2023) Comprehensive quantitative analyses of fetal magnetic resonance imaging in isolated cerebral ventriculomegaly. Neuroimage Clin 37:103357. https://doi.org/10.1016/j.nicl.2023.103357CrossRefPubMedPubMedCentral

Li QM, Liao HZ, Wang WB et al (2021) Prognostic analysis and risk factors associated with fetal ventriculomegaly. Pediatr Neurosurg 56:407–415. https://doi.org/10.1159/000516378CrossRefPubMed

Parilla BV, Endres LK, Dinsmoor MJ, Curran L (2006) In utero progression of mild fetal ventriculomegaly. Int J Gynecol Obstetr 93:106–109. https://doi.org/10.1016/j.ijgo.2006.01.026CrossRef

Kelly EN, Allen VM, Seaward G, Windrim R, Ryan G (2001) Mild ventriculomegaly in the fetus, natural history, associated findings and outcome of isolated mild ventriculomegaly: a literature review. Prenat Diagn 21:697–700. https://doi.org/10.1002/pd.138CrossRefPubMed

Melchiorre K, Bhide A, Gika AD, Pilu G, Papageorghiou AT (2009) Counseling in isolated mild fetal ventriculomegaly. Ultrasound Obstetr Gynecol 34:212–224. https://doi.org/10.1002/uog.7307CrossRef

Pisapia JM, Rozycki M, Akbari H et al (2017) Correlations of atrial diameter and frontooccipital horn ratio with ventricle size in fetal ventriculomegaly. J Neurosurg Pediatr 19:300–306. https://doi.org/10.3171/2016.9.Peds16210CrossRefPubMed

10.

McKechnie L, Vasudevan C, Levene M (2012) Neonatal outcome of congenital ventriculomegaly. Seminars Fetal Neonatal Med 17:301–307. https://doi.org/10.1016/j.siny.2012.06.001CrossRef

11.

Peña A, Harris NG, Bolton MD, Czosnyka M, Pickard JD (2002) Communicating hydrocephalus: the biomechanics of progressive ventricular enlargement revisited. Acta Neurochir Suppl 81:59–63. https://doi.org/10.1007/978-3-7091-6738-0_15CrossRefPubMed

12.

Duy PQ, Rakic P, Alper SL et al (2022) Brain ventricles as windows into brain development and disease. Neuron 110:12–15. https://doi.org/10.1016/j.neuron.2021.12.009CrossRefPubMedPubMedCentral

13.

Svancer P, Spaniel F (2021) Brain ventricular volume changes in schizophrenia. A narrative review. Neurosci Lett 759:136065. https://doi.org/10.1016/j.neulet.2021.136065CrossRefPubMed

14.

Pang D, Altschuler E (1994) Low-pressure hydrocephalic state and viscoelastic alterations in the brain. Neurosurgery 35:643–655. https://doi.org/10.1227/00006123-199410000-00010.CrossRefPubMed

15.

Hannon T, Tennant WG, Rankin J, Robson SC (2012) Epidemiology, natural history, progression, and postnatal outcome of severe fetal ventriculomegaly. Obstetr Gynecol 120:1345–1353. https://doi.org/10.1097/AOG.0b013e3182732b53CrossRef

16.

Chang Q, Peng Y, Huang Q et al (2019) Prognosis of fetuses with ventriculomegaly: an observational retrospective study. Prenat Diagn 39:901–909. https://doi.org/10.1002/pd.5503CrossRefPubMed

17.

Pisapia JM, Akbari H, Rozycki M et al (2018) Use of fetal magnetic resonance image analysis and machine learning to predict the need for postnatal cerebrospinal fluid diversion in fetal ventriculomegaly. JAMA Pediatr 172:128–135. https://doi.org/10.1001/jamapediatrics.2017.3993CrossRefPubMed

18.

Gu JL, Johnson A, Kerr M et al (2017) Correlating prenatal imaging findings of fetal ventriculomegaly with the need for surgical intervention in the first 3 months after birth. Pediatr Neurosurg 52:20–25. https://doi.org/10.1159/000449003CrossRefPubMed

19.

Carta S, Kaelin Agten A, Belcaro C, Bhide A (2018) Outcome of fetuses with prenatal diagnosis of isolated severe bilateral ventriculomegaly: systematic review and meta-analysis. Ultrasound Obstet Gynecol 52:165–173. https://doi.org/10.1002/uog.19038CrossRefPubMed

20.

Chiarelli PA, Hauptman JS, Browd SR (2018) Machine learning and the prediction of hydrocephalus: can quantitative image analysis assist the clinician? JAMA Pediatr 172:116–118. https://doi.org/10.1001/jamapediatrics.2017.4450CrossRefPubMed

21.

Hale AT, Riva-Cambrin J, Wellons JC et al (2021) Machine learning predicts risk of cerebrospinal fluid shunt failure in children: a study from the hydrocephalus clinical research network. Childs Nervous System 37:1485–1494. https://doi.org/10.1007/s00381-021-05061-7CrossRef

22.

Shi W, Yan GH, Li YM et al (2020) Fetal brain age estimation and anomaly detection using attention-based deep ensembles with uncertainty. Neuroimage 223. https://doi.org/10.1016/j.neuroimage.2020.117316

23.

Varela MF, Miyabe MM, Oria M (2020) Fetal brain damage in congenital hydrocephalus. Childs Nerv Syst 36:1661–1668. https://doi.org/10.1007/s00381-020-04657-9CrossRefPubMed

24.

Roales-Bujan R, Paez P, Guerra M et al (2012) Astrocytes acquire morphological and functional characteristics of ependymal cells following disruption of ependyma in hydrocephalus. Acta Neuropathologica 124:531–546. https://doi.org/10.1007/s00401-012-0992-6CrossRefPubMedPubMedCentral

25.

Del Bigio MR (2010) Ependymal cells: biology and pathology. Acta Neuropathol 119:55–73. https://doi.org/10.1007/s00401-009-0624-yCrossRefPubMed

26.

Del Bigio MR (2010) Neuropathology and structural changes in hydrocephalus. Dev Disabil Res Rev 16:16–22. https://doi.org/10.1002/ddrr.94CrossRefPubMed

27.

Guerra MM, Henzi R, Ortloff A et al (2015) Cell junction pathology of neural stem cells is associated with ventricular zone disruption, hydrocephalus, and abnormal neurogenesis. J Neuropathol Exp Neurol 74:653–671. https://doi.org/10.1097/nen.0000000000000203CrossRefPubMed

28.

Delbigio MR (1993) Neuropathological changescaused by hydrocephalus. Acta Neuropathol 85:573–585. https://doi.org/10.1007/bf00334666CrossRef

29.

Horgos BMM, Boer A, Buruiana A et al (2023) White matter changes in fetal brains with ventriculomegaly. Front Neuroanat 17:1160742. https://doi.org/10.3389/fnana.2023.1160742

30.

Vasung L, Rollins CK, Zhang J et al (2022) Abnormal development of transient fetal zones in mild isolated fetal ventriculomegaly. Cereb Cortex 33:1130–1139. https://doi.org/10.1093/cercor/bhac125

Titel: Machine learning in prenatal MRI predicts postnatal ventricular abnormalities in fetuses with isolated ventriculomegaly
verfasst von: Xue Chen
Daqiang Xu
Xiaowen Gu
Zhisen Li
Yisha Zhang
Peng Wu
Zhou Huang
Jibin Zhang
Yonggang Li
Publikationsdatum: 10.05.2024
Verlag: Springer Berlin Heidelberg
Erschienen in: European Radiology
Print ISSN: 0938-7994
Elektronische ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-024-10785-6

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Die Highlights vom Kongress des American College of Cardiology 2024

Springer Medizin

Machine learning in prenatal MRI predicts postnatal ventricular abnormalities in fetuses with isolated ventriculomegaly

Abstract

Objectives

Methods

Results

Conclusions

Clinical relevance statement

Key Points

Neu im Fachgebiet Radiologie

Darf man die Behandlung eines Neonazis ablehnen?

Ein Drittel der jungen Ärztinnen und Ärzte erwägt abzuwandern

Endlich: Zi zeigt, mit welchen PVS Praxen zufrieden sind

Akuter Schwindel: Wann lohnt sich eine MRT?

Update Radiologie

Die Highlights vom Kongress des American College of Cardiology 2024

Springer Medizin

Abstract

Objectives

Methods

Results

Conclusions

Clinical relevance statement

Key Points

Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten

Neu im Fachgebiet Radiologie

Darf man die Behandlung eines Neonazis ablehnen?

Ein Drittel der jungen Ärztinnen und Ärzte erwägt abzuwandern

Endlich: Zi zeigt, mit welchen PVS Praxen zufrieden sind

Akuter Schwindel: Wann lohnt sich eine MRT?

Update Radiologie