Dynamic PET Imaging Using Dual Texture Features

Abstract

Purpose: This study aims to explore the impact of adding texture features in dynamic positron emission tomography (PET) reconstruction of imaging results.Methods: We have improved a reconstruction method that combines radiological dual texture features. In this method, multiple short time frames are added to obtain composite frames, and the image reconstructed by composite frames is used as the prior image. We extract texture features from prior images by using the gray level-gradient cooccurrence matrix (GGCM) and gray-level run length matrix (GLRLM). The prior information contains the intensity of the prior image, the inverse difference moment of the GGCM and the long-run low gray-level emphasis of the GLRLM.Results: The computer simulation results show that, compared with the traditional maximum likelihood, the proposed method obtains a higher signal-to-noise ratio (SNR) in the image obtained by dynamic PET reconstruction. Compared with similar methods, the proposed algorithm has a better normalized mean squared error (NMSE) and contrast recovery coefficient (CRC) at the tumor in the reconstructed image. Simulation studies on clinical patient images show that this method is also more accurate for reconstructing high-uptake lesions.Conclusion: By adding texture features to dynamic PET reconstruction, the reconstructed images are more accurate at the tumor.

Metabolic and textural changes in the brain of non‐small cell lung cancer patients: A total‐body positron emission tomography/computed tomography study

“…According to our radiomics analysis, textural features including the first‐order gray‐level run‐length matrix (GLRLM) and gray‐level co‐occurrence matrix, extracted from the left insula, anterior cingulate, and medial frontal gyrus, had high value for discriminating NSCLC patients and healthy controls. The GLRLM provides comprehensive information about changes of direction, adjacent intervals, and the gray level of images [51]. The combination of the GLRLM and maximum standardized uptake value better‐predicted the prognosis of cancer patients [52].…”

Artificial intelligence strategies based on run length matrix and wavelet analyses for detection of subtle alterations in hepatocyte chromatin organization following exposure to iron oxide nanoparticles

“…Alternatively, and yet relatively uninvestigated, approaches to textural analysis of cell structure include Run Length Matrix analysis (RLM), which can be particularly useful for providing information on intensity and spatial relationships of micrograph components. Run Length Matrix analysis, also known as Gray-Level Run Length Matrix (GLRLM) analysis, can extract measures of cell texture such as Short Run Emphasis (SRE), Long Run Emphasis (LRE), and Gray Level Non-Uniformity (GLN), quantifiers that are closely related to two-dimensional heterogeneity and the level of textural disorder 10,11 . A vector of these features can later be used as valuable input for supervised ML training in classification and regression tasks.…”