Systematic and Comprehensive Automated Ventricle Segmentation on Ventricle Images of the Elderly Patients: A Retrospective Study

Abstract

Background and Objective: Ventricle volume is closely related to hydrocephalus, brain atrophy, Alzheimer's, Parkinson's syndrome, and other diseases. To accurately measure the volume of the ventricles for elderly patients, we use deep learning to establish a systematic and comprehensive automated ventricle segmentation framework. Methods: The study participation included 20 normal elderly people, 20 patients with cerebral atrophy, 64 patients with normal pressure hydrocephalus, and 51 patients with acquired hydrocephalus. Second, get their imaging data through the picture archiving and communication systems (PACS) system. Then use ITK software to manually label participants' ventricular structures. Finally, extract imaging features through machine learning. Results: This automated ventricle segmentation method can be applied not only to CT and MRI images but also to images with different scan slice thicknesses. More importantly, it produces excellent segmentation results (Dice > 0.9). Conclusion: This automated ventricle segmentation method has wide applicability and clinical practicability. It can help clinicians find early disease, diagnose disease, understand the patient's disease progression, and evaluate the patient's treatment effect.

Keywords: computer tomography (CT); convolutional neural network (CNN); deep learning; image segmentation; magnetic resonance imaging; neuroimage; ventricular segmentation.

Figure 1

Study flow chart for the inclusion of participants.

Figure 2

The workflow of proposed methods.

Figure 3

The visualization of segmentation results for thin-slice with MRI images and CT images. (A) The completeness of segmentation indicates the performance of each model on MRI images in which our method achieves the best. (B) Our method is superior to other competing approaches on CT images, specifically for low contrast images (The last row).