Texture Analysis of Imaging: What Radiologists Need to Know

Texture Analysis in Cerebral Gliomas: A Review of the Literature

“…The superiority of one over the other remains speculative at best. 76 Future studies should assess the comparability and accuracy of results across multiple types of software, especially in terms of clinical outcomes, survival, and radiomic parameters, to help with standardization. Finally, adequate training of radiologists is also required for consistent evaluation and implementation in routine workflow.…”

“…Finally, the role of MRTA should also be evaluated in the context of deep learning and neural networks. Even though unsupervised deep learning can self-identify features for itself and does not need manual input (thereby reducing interobserver bias in ROI selection) and feature selection, 76 deep learning methods require higher processing powers and considerable high-quality ground truth data. The insatiable appetite of deep learning for large quantities of labeled training data (which are both expensive and difficult to produce) is another limitation of the deep learning approach.…”

Hiding beyond plain sight: Textural analysis of positron emission tomography to identify high-risk plaques in carotid atherosclerosis

“…2 Texture analysis is one form of radiomic assessment that specifically assesses the variation in grayscale image intensities within an image, i.e., radiologic texture. 3 The underlying assumption in texture analysis is that grayscale values and their spatial and temporal interrelationships within an image reflect phenotypic variations in the imaged tissue and may indicate molecular variations. 3,4 Recently, there has been a substantial interest in texture analysis in the oncology setting.…”

Editorial for “Texture Analysis of High b‐value Diffusion‐Weighted Imaging for Evaluating Consistency of Pituitary Macroadenomas”

“…A typical radiomics workflow involves image acquisition, image segmentation, feature extraction, and statistical analysis. Each component of the workflow is important, and a lack of standardization limits reproducibility . For example, it has been shown that variations in image acquisition and reconstruction parameters lead to inconsistent findings between different datasets .…”

“…Each method involves various benefits and drawbacks, including problems with accuracy, reproducibility, and generalizability, as the manual segmentation process can be tedious and time‐consuming. Feature extraction and statistical analysis are also limited due to a lack of consensus regarding software for feature extraction, methods for optimal feature selection, and variation in feature validation metrics . Other considerations for the implementation of radiomics include the integration of big data and data sharing …”