Infections and tumor are common brain diseases that, sometimes, may have similar pattern on brain MRI. Neuroinfections can be caused by diverse etiological agents and affect millions of people worldwide [1, 2]. Altogether, benign and malignant tumors of the Central Nervous System (CNS) are accounted for 3.5/100.000 new cases and 2.5 deaths worldwide [3], exhibiting life-style and tumor type-dependent prognostic (5% to 92% with 5 years survival rate) [4].

Neuroinfections and CNS tumors may produce severe complications, disability, and economic burden [2]. The diagnosis of these neurological disorders usually considers patient history, symptoms, and physical and neurological examinations. Blood analysis, cerebrospinal fluid (CSF), biopsy, and neuroimaging are fundamental for diagnosis [2, 5]. Neuroimaging modalities such as Magnetic Resonance Imaging (MRI), Computed Tomography (CT) and Positron Emission Tomography (PET) are essential for localization, determination of etiology, and the follow up of these diseases.

Among these, MRI presents the best soft tissue contrast detection and diagnosis sensibility. Despite these qualities, MRI cannot always distinguish between tumors and neuroinfections due to similar imaging characteristic [6]. For this reason, a reliable diagnosis also depends on histopathological examination of biopsy samples obtained through invasive procedures, such as surgery.

Due to this limitations, and aiming non-invasive diagnostic aid, image processing and textures analysis [7] has been progressively used to assist radiologists in the diagnosis of diverse pathologies, including tumors [8–13] and infections [14–16]. Texture analysis is described as techniques that enable the quantification of the gray-level patterns, pixel interrelationships, and the spectral properties of an image[7]. The obtained features can be used in Machine Learning (ML) database to assist the correct classification of groups. 

In this study, we extracted textures that, combined with methods of ML, could assist in the differentiation of brain tumors and neuroinfections in MRI sequences.