No abstract

by on July 31, 2020. For personal use only. jnm.snmjournals.org Downloaded from ABSTRACT Radiomics is a rapidly evolving field of research concerned with the extraction and quantification of patterns -the so-called radiomic features -within medical images. Radiomic features capture tissue and lesion characteristics such as heterogeneity and shape, and may, alone or in combination with demographic, histological, genomic or proteomic data, be used for clinical problem-solving. The goal of this CE article is to provide an introduction to the field, covering the basic radiomics workflow:feature calculation and selection, dimensionality reduction, and data processing . Potential clinical applications in nuclear medicine that include PET radiomics-based prediction of treatment response and survival will be discussed. Current limitations of radiomics, such as sensitivity to acquisition parameter variations, and common pitfalls will also be covered.

MRI texture features are generally considered to be sensitive to variations in signal-to-noise ratio and spatial resolution, which represents an obstacle for the widespread clinical application of texture-based pattern discrimination with MRI. This study investigates the sensitivity of texture features of different categories (co-occurrence matrix, run-length matrix, absolute gradient, autoregressive model, and wavelet transform) to variations in the number of acquisitions (NAs), repetition time (TR), echo time (TE), and sampling bandwidth (SBW) at different spatial resolutions. Special emphasis was placed on the influence of MRI protocol heterogeneity and implications for the results of pattern discrimination. Experiments were performed using two polystyrene spheres and agar gel phantoms with different nodular patterns. T2-weighted multislice multiecho images were obtained using a 3.0 T scanner equipped with a microimaging gradient insert coil. Linear discriminant analysis and k nearest neighbor classification were used for texture-based pattern discrimination. Results show that texture features of all categories are increasingly sensitive to acquisition parameter variations with increasing spatial resolution. Nevertheless, as long as the spatial resolution is sufficiently high, variations in NA, TR, TE, and SBW have little effect on the results of pattern discrimination. Texture features derived from the co-occurrence matrix are superior to features of other categories because they enable discrimination of different patterns close to the resolution limits for the smallest structures of physical texture even for datasets that are heterogeneous with regard to different acquisition parameters, including spatial resolution.

No abstract

Purpose: To investigate the reproducibility and transferability of texture features between MR centers, and to compare two feature selection methods and two classifiers. Materials and Methods:Coronal T1-weighted MR images of the knees of 63 patients, divided into three groups, were included in the study. MR images were obtained at three different MR centers. Regions of interest (ROIs) were drawn in the bone marrow and fat tissue. Then texture analysis (TA) of the ROIs was performed, and the most discriminant features were identified using Fisher coefficients and POEϩACC (probability of classification error and average correlation coefficients). Based on these features, artificial neural network (ANN) and k-nearest-neighbor (k-NN) classifiers were used for tissue discrimination. Results:Although the texture features differed among the MR centers, features from one center could be successfully used for tissue discrimination in texture data on MR images from other centers. The best results were achieved using the ANN classifier in combination with features selected by POEϩACC. Conclusion:The differences in texture features extracted from MR images from different centers seem to have only a small impact on the results of tissue discrimination.

No abstract

No abstract

MR image interpolation has the potential to improve the results of pattern classification, based on COC, RUN, and GRA features. Unless spatial resolution is very poor, zero-filling is the interpolation technique of choice, with a recommended maximum interpolation factor of 4.