Dataset Information

Radiomics Features Differentiate Between Normal and Tumoral High-Fdg Uptake.

ABSTRACT: Identification of FDGavid- neoplasms may be obscured by high-uptake normal tissues, thus limiting inferences about the natural history of disease. We introduce a FDG-PET radiomics tissue classifier for differentiating FDGavid- normal tissues from tumor. Thirty-three scans from 15 patients with Hodgkin lymphoma and 68 scans from 23 patients with Ewing sarcoma treated on two prospective clinical trials were retrospectively analyzed. Disease volumes were manually segmented on FDG-PET and CT scans. Brain, heart, kidneys and bladder and tumor volumes were automatically segmented on PET images. Standard-uptake-value (SUV) derived shape and first order radiomics features were computed to build a random forest classifier. Manually segmented volumes were compared to automatically segmented tumor volumes. Classifier accuracy for normal tissues was 90%. Classifier performance was varied across normal tissue types (brain, left kidney and bladder, hear and right kidney were 100%, 96%, 97%, 83% and 87% respectively). Automatically segmented tumor volumes showed high concordance with the manually segmented tumor volumes (R2?=?0.97). Inclusion of texture-based radiomics features minimally contributed to classifier performance. Accurate normal tissue segmentation and classification facilitates accurate identification of FDGavid tissues and classification of those tissues as either tumor or normal tissue.

SUBMITTER: Hsu CY

PROVIDER: S-EPMC5834444 | biostudies-literature | 2018 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Radiomics Features Differentiate Between Normal and Tumoral High-Fdg Uptake.

Hsu Chih-Yang CY Doubrovin Mike M Hua Chia-Ho CH Mohammed Omar O Shulkin Barry L BL Kaste Sue S Federico Sara S Metzger Monica M Krasin Matthew M Tinkle Christopher C Merchant Thomas E TE Lucas John T JT

Scientific reports 20180302 1

Identification of FDGavid- neoplasms may be obscured by high-uptake normal tissues, thus limiting inferences about the natural history of disease. We introduce a FDG-PET radiomics tissue classifier for differentiating FDGavid- normal tissues from tumor. Thirty-three scans from 15 patients with Hodgkin lymphoma and 68 scans from 23 patients with Ewing sarcoma treated on two prospective clinical trials were retrospectively analyzed. Disease volumes were manually segmented on FDG-PET and CT scans. ...[more]

PMID: 29500442

Similar Datasets

Project description:Besides basic measurements as maximum standardized uptake value (SUV)max or SUVmean derived from 18F-FDG positron emission tomography (PET) scans, more advanced quantitative imaging features (i.e. "Radiomics" features) are increasingly investigated for treatment monitoring, outcome prediction, or as potential biomarkers. With these prospected applications of Radiomics features, it is a requisite that they provide robust and reliable measurements. The aim of our study was therefore to perform an integrated stability analysis of a large number of PET-derived features in non-small cell lung carcinoma (NSCLC), based on both a test-retest and an inter-observer setup.Eleven NSCLC patients were included in the test-retest cohort. Patients underwent repeated PET imaging within a one day interval, before any treatment was delivered. Lesions were delineated by applying a threshold of 50% of the maximum uptake value within the tumor. Twenty-three NSCLC patients were included in the inter-observer cohort. Patients underwent a diagnostic whole body PET-computed tomography (CT). Lesions were manually delineated based on fused PET-CT, using a standardized clinical delineation protocol. Delineation was performed independently by five observers, blinded to each other. Fifteen first order statistics, 39 descriptors of intensity volume histograms, eight geometric features and 44 textural features were extracted. For every feature, test-retest and inter-observer stability was assessed with the intra-class correlation coefficient (ICC) and the coefficient of variability, normalized to mean and range. Similarity between test-retest and inter-observer stability rankings of features was assessed with Spearman's rank correlation coefficient.Results showed that the majority of assessed features had both a high test-retest (71%) and inter-observer (91%) stability in terms of their ICC. Overall, features more stable in repeated PET imaging were also found to be more robust against inter-observer variability.Results suggest that further research of quantitative imaging features is warranted with respect to more advanced applications of PET imaging as being used for treatment monitoring, outcome prediction or imaging biomarkers.

Project description:Purpose: Building a universal genomic signature predicting the intensity of FDG uptake in diverse metastatic tumors may allow us to understand better the biological processes underlying this phenomenon and their requirements of glucose uptake. Methods: A balanced training set (n=71) of metastatic tumors including some of the most frequent histologies, with matched PET/CT quantification measurements and whole human genome gene expression microarrays, was used to build the signature. Selection of microarray features was carried out exclusively on the basis of their strong association with FDG uptake (as measured by SUVmean35) by means of univariate linear regression. A thorough bioinformatics study of these genes was performed and multivariable models were built by fitting several state of the art regression techniques to the training set for comparison. Results: The 909 probes with the strongest association with the SUVmean35 (comprising 742 identifiable genes and 62 probes not matched to a symbol) were used to build the signature. Partial Least Squares using 3 components (PLS-3) was the best performing model in the training dataset cross-validation (Root Mean Square Error, RMSE=0.443) and was validated further in an independent validation dataset (n=13) obtaining a performance within the 95% CI of that obtained in the training dataset (RMSE=0.645). Significantly overrepresented biological processes correlating with the SUVmean35 were identified beyond glycolysis, such as ribosome biogenesis and DNA replication (correlating with a higher SUVmean35), and cytoskeleton reorganization and autophagy (correlating with a lower SUVmean35), among others. Conclusions: PLS-3 is a signature predicting accurately the intensity of FDG uptake in diverse metastatic tumors. FDG-PET might help in the design of specific targeted therapies directed to counteract the identified malignant biological processes more likely activated in a tumor as inferred from the SUVmean35 and also from its variations in response to antineoplastic treatments.

Dataset Information

Radiomics Features Differentiate Between Normal and Tumoral High-Fdg Uptake.

Publications

Radiomics Features Differentiate Between Normal and Tumoral High-Fdg Uptake.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets