BRAIM: A computer-aided diagnosis system for neurodegenerative diseases and brain lesion monitoring from volumetric analyses

Abstract

Background and objective: This paper presents BRAIM, a computer-aided diagnosis (CAD) system to help clinicians in diagnosing and treatment monitoring of brain diseases from magnetic resonance image processing. BRAIM can be used for early diagnosis of neurodegenerative diseases such as Parkinson, Alzheimer or Multiple Sclerosis and also for brain lesion diagnosis and monitoring.

Methods: The developed CAD system includes different user-friendly tools for segmenting and determining whole brain and brain structure volumes in an easy and accurate way. Specifically, three types of measurements can be performed: (1) total volume of white, gray matter and cerebrospinal fluid; (2) brain structure volumes (volume of putamen, thalamus, hippocampus and caudate nucleus); and (3) brain lesion volumes.

Results: As a proof of concept, some study cases were analyzed with the presented system achieving promising results. In addition to be used to quantify treatment effectiveness in patients with brain lesions, it was demonstrated that BRAIM is able to classify a subject according to the brain volume measurements using as reference a healthy control database created for this purpose.

Conclusions: The CAD system presented in this paper simplifies the daily work of clinicians and provides them with objective and quantitative volume data for prospective and retrospective analyses.

Keywords: Brain lesions; Brain segmentation; CAD; Magnetic resonance imaging; Volumetric analysis.