Research Spotlight

Research Spotlight

To recognise the great work of our members in the field of Neurosonology, ESNCH will spotlight relevant publications on our social media channels (Facebook, Twitter and LinkedIn) and collect them here for easy access. If you have recently published a paper or would like to nominate the work of another member, please send your suggestions for Research Spotlights to info@esnch.org with a brief summary of why the research is important.

This month, we highlight new research published by ESNCH members in Frontiers of Medicine regarding detection of vasculitis in vertebral artery in patients affected of giant cell arteritis measuring the vertebral canal.

Introduction: The diagnosis of giant cell arteritis (GCA) by ultrasonography including large vessels, apart from the temporal artery increases the sensibility of the study and informs about the risk of specific complications. However, there is less information about the study of these arteries, whose affection carries higher proportion of severe complications.

For more information, read the full article:

Full title: Increased vertebral canal diameter measured by ultrasonography as a sign of vasculitis in patients with giant cell arteritis

Link: Volume 10 – 2023 | https://doi.org/10.3389/fmed.2023.1283285

The study was led by the ESNCH working group member Mark Rubin, with participation of several ESNCH members. Congratulations to all involved on this important publication.

For more information, read the full article:

Full title: Robot-Assisted Transcranial Doppler Versus Transthoracic Echocardiography for Right to Left Shunt Detection

Link: https://www.ahajournals.org/doi/pdf/10.1161/STROKEAHA.123.043380

This paper describes a deep learning–based system for automatic characterization of the optic nerve from B-mode TOS images by automatic measurement of the OND and ONSD. The authors additionally determine how the signal-to-noise ratio in two different areas of the image influences system performance.
A UNet was trained as the segmentation model. The training was performed on a multidevice, multicenter data set of 464 TOS images from 110 subjects. Fivefold cross-validation was performed, and the training process was repeated eight times. The final prediction was made as an ensemble of the predictions of the eight single models. Automatic OND and ONSD measurements were compared with the manual measurements taken by an expert with a graphical user interface that mimics a clinical setting.
This recent publication focuses on the use of transcranial sonography to study white matter lesions. This project was awarded as “Best Young Investigator Study” in the 25th Conference of the European Society of Neurosonology and Cerebral Hemodynamics (Belgrade, 2021).