Radiomics in Oncological PET/CT: Clinical Applications

Lee, Jeong Won; Lee, Sang Mi

doi:10.1007/s13139-017-0500-y

Cited by 89 publications

(69 citation statements)

References 154 publications

(196 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additional studies will evaluate the putative assets (not only cross‐sectional/diagnostic but also longitudinal/predictive) of this 18 F‐FDG‐based iconomarker, possibly combined with blood and/or urine biomarkers. The technique of 18 F‐FDG renal uptake quantification will most probably improve, including automated segmentation, texture analysis, and radiomics . Note also that 18 F‐FDG PET/CT provides images of the entire kidney allograft, which may help distinguish AR from pyelonephritis or kidney infarction and evaluate the global intensity of AR‐associated inflammation.…”

Section: Discussionmentioning

confidence: 99%

Diagnostic yield of 18F-FDG PET/CT imaging and urinary CXCL9/creatinine levels in kidney allograft subclinical rejection

Hanssen

Weekers

Lovinfosse

et al. 2020

American Journal of Transplantation

View full text Add to dashboard Cite

Subclinical kidney allograft acute rejection (SCR) corresponds to “the unexpected histological evidence of acute rejection in a stable patient.” SCR detection relies on surveillance biopsy. Noninvasive approaches may help avoid biopsy‐associated complications. From November 2015 to January 2018, we prospectively performed positron emission tomography/computed tomography (PET/CT) after injection of F18‐fluorodeoxyglucose (18F‐FDG) in adult kidney transplant recipients with surveillance biopsy at ~3 months posttransplantation. The Banff‐2017 classification was used. The ratio of the mean standard uptake value (mSUVR) between kidney cortex and psoas muscle was measured. Urinary levels of CXCL‐9 were concomitantly quantified. Our 92‐patient cohort was categorized upon histology: normal (n = 70), borderline (n = 16), and SCR (n = 6). No clinical or biological difference was observed between groups. The mSUVR reached 1.87 ± 0.55, 1.94 ± 0.35, and 2.41 ± 0.54 in normal, borderline, and SCR groups, respectively. A significant difference in mSUVR was found among groups. Furthermore, mSUVR was significantly higher in the SCR vs normal group. The area under the receiver operating characteristic curve (AUC) was 0.79, with 83% sensitivity using an mSUVR threshold of 2.4. The AUC of urinary CXCL‐9/creatinine ratios comparatively reached 0.79. The mSUVR positively correlated with ti and acute composite Banff scores. 18F‐FDG‐PET/CT helps noninvasively exclude SCR, with a negative predictive value of 98%. External validations are required.

show abstract

Section: Discussionmentioning

confidence: 99%

Diagnostic yield of 18F-FDG PET/CT imaging and urinary CXCL9/creatinine levels in kidney allograft subclinical rejection

Hanssen

Weekers

Lovinfosse

et al. 2020

American Journal of Transplantation

View full text Add to dashboard Cite

show abstract

“…Several studies perform conventional correlation analysis [156,160,165,168,169], as well as robust machine learning evaluation [10,170,171] of textural features to characterize tumors in vivo. An oncological review of PET-based radiomic approaches concluded that it is a promising method for personalized medicine as it can enhance cancer management [172].…”

Section: Radiomicsmentioning

confidence: 99%

Personalizing Medicine Through Hybrid Imaging and Medical Big Data Analysis

et al. 2018

View full text Add to dashboard Cite

Medical imaging has evolved from a pure visualization tool to representing a primary source of analytic approaches toward in vivo disease characterization. Hybrid imaging is an integral part of this approach, as it provides complementary visual and quantitative information in the form of morphological and functional insights into the living body. As such, non-invasive imaging modalities no longer provide images only, but data, as stated recently by pioneers in the field. Today, such information, together with other, non-imaging medical data creates highly heterogeneous data sets that underpin the concept of medical big data. While the exponential growth of medical big data challenges their processing, they inherently contain information that benefits a patient-centric personalized healthcare. Novel machine learning approaches combined with high-performance distributed cloud computing technologies help explore medical big data. Such exploration and subsequent generation of knowledge require a profound understanding of the technical challenges. These challenges increase in complexity when employing hybrid, aka dual-or even multi-modality image data as input to big data repositories. This paper provides a general insight into medical big data analysis in light of the use of hybrid imaging information. First, hybrid imaging is introduced (see further contributions to this special Research Topic), also in the context of medical big data, then the technological background of machine learning as well as state-of-the-art distributed cloud computing technologies are presented, followed by the discussion of data preservation and data sharing trends. Joint data exploration endeavors in the context of in vivo radiomics and hybrid imaging will be presented. Standardization challenges of imaging protocol, delineation, feature engineering, and machine learning evaluation will be detailed. Last, the paper will provide an outlook into the future role of hybrid imaging in view of personalized medicine, whereby a focus will be given to the derivation of prediction models as part of clinical decision support systems, to which machine learning approaches and hybrid imaging can be anchored.

show abstract

“…Radi omics refers to the process of extracting and analyzing in vivo features from medical images for disease characterization (1). The radiomics approach was originally conceived for morphologic images only (2,3) but recently was adopted also for the analysis of 18 F-FDG PET/CT images, with promising results in various patient cohorts (4)(5)(6)(7)(8)(9). It has been shown that several features, particularly textural indices, used in the radiomics approach are affected by, for example, variations in biologic factors (10), imaging and reconstruction protocols (11,12), delineation approaches (13)(14)(15), or feature extraction methods (12,(16)(17)(18).…”

mentioning

confidence: 99%

Optimized Feature Extraction for Radiomics Analysis of ¹⁸F-FDG PET Imaging

et al. 2018

View full text Add to dashboard Cite

Radiomics analysis of 18 F-FDG PET/CT images promises well for an improved in vivo disease characterization. To date, several studies have reported significant variations in textural features due to differences in patient preparation, imaging protocols, lesion delineation, and feature extraction. Our objective was to study variations in features before a radiomics analysis of 18 F-FDG PET data and to identify those feature extraction and imaging protocol parameters that minimize radiomic feature variations across PET imaging systems. Methods: A whole-body National Electrical Manufacturers Association image-quality phantom was imaged with 13 PET/CT systems at 12 different sites following local protocols. We selected 37 radiomic features related to the 4 largest spheres (17-37 mm) in the phantom. On the basis of a combined analysis of voxel size, bin size, and lesion volume changes, feature and imaging system ranks were established. A 1-way ANOVA was performed over voxel size, bin size, and lesion volume subgroups to identify the dependency and the trend change in feature variations across these parameters. Results: Feature ranking revealed that the gray-level cooccurrence matrix and shape features are the least sensitive to PET imaging system variations. Imaging system ranking illustrated that the use of point-spread function, small voxel sizes, and narrow gaussian postfiltering helped minimize feature variations. ANOVA subgroup analysis indicated that variations in each of the 37 features and for a given voxel size and bin size can be minimized. Conclusion: Our results provide guidance to selecting optimized features from 18 F-FDG PET/CT studies. We were able to demonstrate that feature variations can be minimized for selected image parameters and imaging systems. These results can help imaging specialists and feature engineers in increasing the quality of future radiomics studies involving PET/CT.

show abstract

Radiomics in Oncological PET/CT: Clinical Applications

Cited by 89 publications

References 154 publications

Diagnostic yield of 18F-FDG PET/CT imaging and urinary CXCL9/creatinine levels in kidney allograft subclinical rejection

Diagnostic yield of 18F-FDG PET/CT imaging and urinary CXCL9/creatinine levels in kidney allograft subclinical rejection

Personalizing Medicine Through Hybrid Imaging and Medical Big Data Analysis

Optimized Feature Extraction for Radiomics Analysis of ¹⁸F-FDG PET Imaging

Contact Info

Product

Resources

About

Radiomics in Oncological PET/CT: Clinical Applications

Cited by 89 publications

References 154 publications

Diagnostic yield of 18F-FDG PET/CT imaging and urinary CXCL9/creatinine levels in kidney allograft subclinical rejection

Diagnostic yield of 18F-FDG PET/CT imaging and urinary CXCL9/creatinine levels in kidney allograft subclinical rejection

Personalizing Medicine Through Hybrid Imaging and Medical Big Data Analysis

Optimized Feature Extraction for Radiomics Analysis of 18F-FDG PET Imaging

Contact Info

Product

Resources

About

Optimized Feature Extraction for Radiomics Analysis of ¹⁸F-FDG PET Imaging