Texture Analysis in Quantitative MR Imaging

Abstract

The diagnostic potential of texture analysis in quantitative tissue characterisation by MR imaging at 1.5 T was evaluated in the brain of 6 healthy volunteers and in 88 patients with intracranial tumours. Texture images were computed from calculated Tl and T2 parameter images by applying groups of common first-order and second-order grey level statistics. Tissue differentiation in the images was estimated by the presence or absence of significant differences between tissue types. A fine discrimination was obtained between white matter, cortical grey matter, and cerebrospinal fluid in the normal brain, and white matter was readily separated from the tumour lesions. Moreover, separation of solid tumour tissue and peritumoural oedema was suggested for some tumour types. Mutual comparison of all tumour types revealed extensive differences, and even specific tumour differentiation turned out to be successful in some cases of clinical importance. However, no discrimination between benign and malignant tumour growth was possible. Much texture information seems to be contained in MR images, which may prove useful for classification and image segmentation.

Applications and limitations of radiomics

“…In the 1990s, GLCM textures derived from a 2D slice of T1- and T2-weighted MR images were first reported to be potentially useful for tissue differentiation, with the ability to differentiate brain tumour tissue, edema, cerebrospinal fluid (CSF), white matter, and gray matter, in patients with brain cancer (Lerski et al 1993, Kjær et al 1995). Mahmoud-Ghoneim et al (2003) demonstrated that GLCM textures computed within a 3D volume of the MR images outperformed 2D textures in separating necrosis and edema from solid tumours (Mahmoud-Ghoneim et al 2003).…”

Machine learning predicts histologic type and grade of canine gliomas based on MRI texture analysis

“…29,38,47 Important limitations in our study, due to its retrospective nature, are the use of different slice thicknesses and coils according to patients size, and the TR variability particularly in T2w sequences. These differences may have influenced the TA, but pre-processing methods were implemented before texture feature extraction according to other publications, [28][29][30] aiming to homogenize images across all segments, sequences, and subjects. These pre-processing techniques may facilitate multicenter studies, allowing to increase the sample size and improve the generalizability of the results.…”

“…Image interpolation was performed setting the common in-plane resolution to 1×1 mm while maintaining the original slice thickness. For image discretization, a fixed bin number of 32 was applied, [28][29][30] and the MRI gray levels within the segmentations were normalized to the mean ± 3 standard deviations. 9 Sixty-one texture features were then extracted per segment in each sequence, leading to a maximum of 732 texture values per tumor.…”

Correlation of Bone Textural Parameters with Age in the Context of Orthopedic X-ray Studies

“…The idea of using textural analysis for the evaluation of human tissue visualized in diagnostic imaging techniques is not new. It has been implemented for brain tissue [40][41][42], breast [43], and even muscle [44]. In the context of bone-based analysis, textural parameters are used, e.g., for the prediction of incident radiographic hip osteoarthritis [45], age-texture correlation analysis [46,47], and association with bone mineral density [48] and bone quality [49].…”