AbstractMeningioma brain tumor discrimination is challenging as many histological patterns are mixed between different subtypes. In clinical practice, dominant patterns are investigated for signs of specific meningioma pathology. However, the simple observation could result in inter- and intra-observer variation due to the complexity of histopathological patterns. Also, employing a computerized feature extraction approach applied at a single resolution scale might not suffice to accurately delineate the mixture of histopathological patterns. In this work we propose a novel multiresolution feature extraction approach for characterizing the textural properties of the different pathological patterns (i.e. mainly cell nuclei shape, orientation and spatial arrangement within the cytoplasm). The patterns’ textural properties are characterized at various scales and orientations for an improved separability between the different extracted features. The Gabor filter energy output of each magnitude response was combined with four other fixed-resolution texture signatures (2 model-based and 2 statistical-based) with and without cell nuclei segmentation. The highest classification accuracy of 95% was reported when combining the Gabor filters’ energy and the meningioma subimage fractal signature as a feature vector without performing any prior cell nuclei segmentation. This indicates that characterizing the cell-nuclei self-similarity properties via Gabor filters can assist in achieving an improved meningioma subtype classification, which can assist in overcoming variations in reported diagnosis.
Keywords: Brain Tumors, Fractal Dimension, Gabor Filter, Meningioma Histopathology, Texture Analysis.