EUVIMEDOpdag EUVIMED
Crossref

Automation of ultrasonographic optic nerve sheath diameter measurement using convolutional neural networks

Mohammad I Hirzallah iD, Supratik Bose, Jingtong Hu, Jonathan S Maltz

Journal of Neuroimaging · 2023

DOI: 10.1111/jon.13163 ↗

At a glance

Journal article in Journal of Neuroimaging, 2023. Written by Mohammad I Hirzallah and 3 co-authors. Institution: Departments of Neurology and Neurosurgery, Baylor College of Medicine, Houston, Texas, USA. Major MEDLINE topics: Intracranial Hypertension, Brain Injuries. Cited 8 times so far (Crossref); 33 references.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background and purpose Ultrasonographic optic nerve sheath (ONS) diameter is a noninvasive intracranial pressure (ICP) surrogate. ICP is monitored invasively in specialized intensive care units. Noninvasive ICP monitoring is important in less specialized settings. However, noninvasive ICP monitoring using ONS diameter (ONSD) is limited by the need for experts to obtain and perform measurements. We aim to automate ONSD measurements using a deep convolutional neural network (CNN) with a novel masking technique.

Methods

We trained a CNN to reproduce masks that mark the ONS. The edges of the mask are defined by an expert. Eight models were trained with 1000 epochs per model. The Dice‐similarity‐coefficient‐weighted averaged outputs of the eight models yielded the final predicted mask. Eight hundred and seventy‐three images were obtained from 52 transorbital cine‐ultrasonography sessions, performed on 46 patients with brain injuries. Eight hundred and fourteen images from 48 scanning sessions were used for training and validation and 59 images from four sessions for testing. Bland‐Altman and Pearson linear correlation analyses were used to evaluate the agreement between CNN and expert measurements.

Results

Expert ONSD measurements and CNN‐derived ONSD estimates had strong agreement ( r = 0.7, p < .0001). The expert mean ONSD (standard deviation) is 5.27 mm (0.43) compared to CNN mean estimate of 5.46 mm (0.37). Mean difference (95% confidence interval, p value) is 0.19 mm (0.10‐0.27 mm, p = .0011), and root mean square error is 0.27 mm.

Conclusion

A CNN can learn ONSD measurement using masking without image segmentation or landmark detection.

Subjects

MeSH terms (MEDLINE)

Intracranial HypertensionBrain InjuriesHumansProspective StudiesOptic NerveIntracranial PressureUltrasonographyAutomation

Author keywords

ONSDautomationintracranial pressuremachine learningoptic nerve sheath diameterultrasound

Authors and institutions

  • Departments of Neurology and Neurosurgery, Baylor College of Medicine, Houston, Texas, USA.
  • Baylor College of Medicine, Center for Space Medicine, Houston, Texas, USA.
  • San Ramon, California, USA.
  • Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, Pennsylvania, USA.
  • Oakland, California, USA.

ORCID profiles: Mohammad I Hirzallah

Cite

APA

Hirzallah, M. I., Bose, S., Hu, J., & Maltz, J. S. (2023). Automation of ultrasonographic optic nerve sheath diameter measurement using convolutional neural networks. Journal of Neuroimaging. https://doi.org/10.1111/jon.13163

Vancouver

Hirzallah MI, Bose S, Hu J, Maltz JS. Automation of ultrasonographic optic nerve sheath diameter measurement using convolutional neural networks. Journal of Neuroimaging. 2023. doi:10.1111/jon.13163

BibTeX
@article{Hirzallah2023,
  author = {Hirzallah, Mohammad I and Bose, Supratik and Hu, Jingtong and Maltz, Jonathan S},
  title = {Automation of ultrasonographic optic nerve sheath diameter measurement using convolutional neural networks},
  journal = {Journal of Neuroimaging},
  year = {2023},
  doi = {10.1111/jon.13163}
}
Start for free →