Program Information
Validating Quantitative Radiomic Texture Features for Oncologic PET: A Digital Phantom Study
F Yang1*, Y Yang1 , L Young2 , (1) University of Miami Miller School of Medicine, Miami, FL, (2) University of Washington Medical Center, Seattle, WA
Presentations
SU-F-R-36 (Sunday, July 31, 2016) 3:00 PM - 6:00 PM Room: Exhibit Hall
Purpose: Radiomic texture features derived from the oncologic PET have recently been brought under intense investigation within the context of patient stratification and treatment outcome prediction in a variety of cancer types; however, their validity has not yet been examined. This work is aimed to validate radiomic PET texture metrics through the use of realistic simulations in the ground truth setting.
Methods: Simulation of FDG-PET was conducted by applying the Zubal phantom as an attenuation map to the SimSET software package that employs Monte Carlo techniques to model the physical process of emission imaging. A total of 15 irregularly-shaped lesions featuring heterogeneous activity distribution were simulated. For each simulated lesion, 28 texture features in relation to the intensity histograms (GLIH), grey-level co-occurrence matrices (GLCOM), neighborhood difference matrices (GLNDM), and zone size matrices (GLZSM) were evaluated and compared with their respective values extracted from the ground truth activity map.
Results: In reference to the values from the ground truth images, texture parameters appearing on the simulated data varied with a range of 0.73-3026.2% for GLIH-based, 0.02-100.1% for GLCOM-based, 1.11-173.8% for GLNDM-based, and 0.35-66.3% for GLZSM-based. For majority of the examined texture metrics (16/28), their values on the simulated data differed significantly from those from the ground truth images (P-value ranges from <0.0001 to 0.04). Features not exhibiting significant difference comprised of GLIH-based standard deviation, GLCO-based energy and entropy, GLND-based coarseness and contrast, and GLZS-based low gray-level zone emphasis, high gray-level zone emphasis, short zone low gray-level emphasis, long zone low gray-level emphasis, long zone high gray-level emphasis, and zone size nonuniformity.
Conclusion: The extent to which PET imaging disturbs texture appearance is feature-dependent and could be substantial. It is thus advised that use of PET texture parameters for predictive and prognostic measurements in oncologic setting awaits further systematic and critical evaluation.
Contact Email: