Brain MRI

Brain in MRI

---
This page will be updated soon.
---

Accurate assessment of acute and chronic hydrocephalus and ventricular size is important in management and treatment planning. In this study, we propose a deep learning-driven measurement for ventricular cerebrospinal fluid (CSF) volume applying automatic segmentation performed using a UNet architecture, a fully convolutional neural network.

Conclusions: Brain ventricle segmentation from MRI datasets can be automated using a deep learning approach. The proposed method performs very well in terms of segmentation accuracy, robustness, and computational time. The high correlation between the automatic and manual references indicates the accuracy and potential clinical applicability of the proposed framework for automatic evaluation of the ventricular system.