Challenges and Promises of PET Radiomics

Abstract

PurposeRadiomics describes the extraction of multiple, otherwise invisible, features from medical images that, with bioinformatic approaches, can be used to provide additional information that can predict underlying tumor biology and behavior.Methods and MaterialsRadiomic signatures can be used alone or with other patient-specific data to improve tumor phenotyping, treatment response prediction, and prognosis, noninvasively. The data describing 18F-fluorodeoxyglucose positron emission tomography radiomics, often using texture or heterogeneity parameters, are increasing rapidly.ResultsIn relation to radiation therapy practice, early data have reported the use of radiomic approaches to better define tumor volumes and predict radiation toxicity and treatment response.ConclusionsAlthough at an early stage of development, with many technical challenges remaining and a need for standardization, promise nevertheless exists that PET radiomics will contribute to personalized medicine, especially with the availability of increased computing power and the development of machine-learning approaches for imaging.

Die Wichtigkeit des „Machine Learning“ und der Texturanalyse in der Onkologie anhand der Fusionsbildgebung

“…Es wird dabei davon ausgegangen, dass ein Zusammenhang von molekularer und genotypischer Tumorbiologie mit den extrahierten Bildparametern besteht, was bereits in vielen Studien bez. unterschiedlichster Tumorentitäten untersucht worden ist [7,8].…”

“…Da sich diese Bildparameter der anatomischen Bildgebung mittels CT oder MRT und der funktionellen Bildgebung mittels PET bez. der Aussage über ein eher aggressiveres Tumorverhalten oder ein potenziell schlechtes Therapieansprechen ergänzen, nimmt gerade für das "Radiomics" der Stellenwert der Fusionsbildgebung durch PET/CT oder PET/MRT deutlich zu um daraus letztlich prognostische und prädiktive Faktoren für den individuellen Patienten und dessen weitere Behandlung ableiten zu können [7,8].…”

Utility of radiomics for predicting patient survival in hepatocellular carcinoma with portal vein tumor thrombosis treated with stereotactic body radiotherapy

“…Studies have also investigated the possibility of using radiomics as a potential prognostic indicator in oncology, speci cally to classify patients and assess their risk categories, to develop personalized oncological treatments [16][17][18]. The aim of this study was to develop a combination of radiomic features and clinical characteristics to estimate the overall survival (OS) in patients with HCC with PVTT treated using SBRT.…”

The Statistical Influence of Imaging Time and Segmentation Volume on PET Radiomic Features: A Preclinical Study

“…Radiomics is defined as the field involved in extracting high dimensional quantitative features from medical images. However, radiomic features however may vary with different factors and conditions [8]. Previous research has highlighted numerous confounding factors that affect texture features such as image reconstruction type [7], respiratory motion [8] and variability in the delineation of the segmented volume [11], [12].…”

“…However, radiomic features however may vary with different factors and conditions [8]. Previous research has highlighted numerous confounding factors that affect texture features such as image reconstruction type [7], respiratory motion [8] and variability in the delineation of the segmented volume [11], [12]. For increased confidence in the utilization of texture features as imaging biomarkers it is necessary to understand the extent these confounding factors have on Radiomic analysis which will inform attempts to standardize texture analysis.…”