Introduction to Radiomics

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.

Value of Shape and Texture Features from 18F-FDG PET/CT to Discriminate between Benign and Malignant Solitary Pulmonary Nodules: An Experimental Evaluation

“…The rationale behind radiomics is to leverage on that fraction of image information which may have clinical relevance but go unnoticed to the human eye [17]. Radiomics also enables full-field analysis of the region of interest, while biopsies only capture a small portion of the lesion [18]. Several studies have proposed predictive models based on a range of combinations of radiomics features from CT, with overall reported accuracy between 70% and 95% [19][20][21][22][23][24][25][26].…”

“…Several studies have proposed predictive models based on a range of combinations of radiomics features from CT, with overall reported accuracy between 70% and 95% [19][20][21][22][23][24][25][26]. Uptake parameters from 18 F fluodeoxyglucose (FDG) Positron Emission Tomography (PET henceforth) have also shown good diagnostic performance (accuracy between 65% and 91% in [3,8,[27][28][29][30]) with potential improvements coming from the characterisation of uptake heterogeneity [31,32]. In a recent meta-analysis, Jia et al [33] concluded that CT and PET/CT have both moderate-to-high diagnostic value in patients with SPN, with no significant differences between the two modalities.…”

Radiomics for intracerebral hemorrhage: are all small hematomas benign?

“…In the 3-10 mL subgroup, patients with poor outcomes had a higher frequency of the black hole sign (9.8% versus 2,8%, p= 0.029) and island sign (6.3% versus 0.9%, p = 0.047), lower admission GCS scores (median, 14 [IQR, [11][12][13][14][15] , and a higher rate of deep ICH(90.0% versus 75.9%, p = 0.001) ( Table S1). The multivariate logistic regression analysis indicated that deep location (OR, 5.167; 95% CI, 2.104-12.689; p < 0.001), the GCS score (OR, 0.737; 95% CI, 0.643-0.844; p < 0.001), and the R-score (OR, 1.297; 95% CI, 1.004-1.674; p = 0.046) were independent predictors of poor outcomes (Table 3).…”

“…Radiomics is an emerging approach that extracts high-throughput quantitative features from medical images and enables us to utilize the full potential of images [14,15]. It has been widely used for the prediction of cancer and differentiation of benign and malignant tumors [16,17].…”

The Challenge of Evaluating Response to Peptide Receptor Radionuclide Therapy in Gastroenteropancreatic Neuroendocrine Tumors: The Present and the Future.

“…These findings might partially explain the limited value delta SUV to monitor PRRT response. Moreover, the possibility to evaluate PRRT response with the use of Ki might reinforce the future use of dynamic PET/CT acquisition in this field.Other innovative methods for quantification and image analysis derived from radiomics are expected to gradually translate into clinical medicine[113][114][115][116]. Using mathematical models for data characterization, radiomics allow to extract a large number of features out of images, which might serve as prognostic parameters.…”