Automatic brain matter segmentation of computed tomography images using a statistical model: A tool to gain working...

Area of Science:

• Medical Imaging
• Radiology
• Artificial Intelligence in Medicine

Background:

• Brain computed tomography (CT) is a vital diagnostic tool for neurological disorders.
• Accurate segmentation of brain matter in CT images is crucial for diagnosis.
• Current manual segmentation methods can be time-consuming and prone to variability.

Purpose of the Study:

• To develop and evaluate a novel automated method for brain matter segmentation in CT images.
• To assist radiologists in the evaluation of neurological disorders.
• To improve the efficiency and accuracy of neuroimaging analysis.

Main Methods:

• The study proposes an automated method utilizing the active appearance model (AAM).
• The AAM was applied to segment brain matter in 54 CT images from outpatients with cognitive impairment.
• The method focuses on automatic segmentation and recognition of regions of interest (ROIs).

Main Results:

• The developed automated method achieved good precision in segmenting brain matter.
• The generated model showed accurate overlapping with the original CT images.
• The technique demonstrated potential for assisting in the evaluation of cognitive impairment.

Conclusions:

• Automated brain matter segmentation using AAM is a promising approach in CT neuroimaging.
• This method can potentially reduce radiologist workload and improve diagnostic accuracy.
• Further development of automated tools is needed to support physicians in diagnosing neurological diseases.