Experimental phantom evaluation to identify robust positron emission tomography (PET) radiomic features

Abstract

Background Radiomics analysis usually involves, especially in multicenter and large hospital studies, different imaging protocols for acquisition, reconstruction, and processing of data. Differences in protocols can lead to differences in the quantification of the biomarker distribution, leading to radiomic feature variability. The aim of our study was to identify those radiomic features robust to the different degrading factors in positron emission tomography (PET) studies. We proposed the use of the standardized measurements of the European Association Research Ltd. (EARL) accreditation to retrospectively identify the radiomic features having low variability to the different systems and reconstruction protocols. In addition, we presented a reproducible procedure to identify PET radiomic features robust to PET/CT imaging metal artifacts. In 27 heterogeneous homemade phantoms for which ground truth was accurately defined by CT segmentation, we evaluated the segmentation accuracy and radiomic feature reliability given by the contrast-oriented algorithm (COA) and the 40% threshold PET segmentation. In the comparison of two data sets, robustness was defined by Wilcoxon rank tests, bias was quantified by Bland–Altman (BA) plot analysis, and strong correlations were identified by Spearman correlation test (r > 0.8 and p satisfied multiple test Bonferroni correction). Results Forty-eight radiomic features were robust to system, 22 to resolution, 102 to metal artifacts, and 42 to different PET segmentation tools. Overall, only 4 radiomic features were simultaneously robust to all degrading factors. Although both segmentation approaches significantly underestimated the volume with respect to the ground truth, with relative deviations of −62 ± 36% for COA and −50 ± 44% for 40%, radiomic features derived from the ground truth were strongly correlated and/or robust to 98 radiomic features derived from COA and to 102 from 40%. Conclusion In multicenter studies, we recommend the analysis of EARL accreditation measurements in order to retrospectively identify the robust PET radiomic features. Furthermore, 4 radiomic features (area under the curve of the cumulative SUV volume histogram, skewness, kurtosis, and gray-level variance derived from GLRLM after application of an equal probability quantization algorithm on the voxels within lesion) were robust to all degrading factors. In addition, the feasibility of 40% and COA segmentations for their use in radiomics analysis has been demonstrated.

Radiomics of Tumor Heterogeneity in 18F-FDG-PET-CT for Predicting Response to Immune Checkpoint Inhibition in Therapy-Naïve Patients with Advanced Non-Small-Cell Lung Cancer

“…Moreover, these studies identified parameters reflecting tumor heterogeneity, albeit not identical to the predictive RFs identified in our study. Possible explanations are the above-mentioned differences in inclusion criteria, patient cohort, and segmentation for RFs of total tumor burden in baseline PET-CT. An advantage of PET RFs is their reproducibility and robustness to all degrading factors [ 17 ].…”

“…The extraction of high-throughput digital and quantitative imaging information and its conversion from encrypted imaging data to mineable numerical data allows its Radiomics analysis. Radiomics represents a groundbreaking new technique to analyze radiological data including the use of artificial intelligence that provides important insights into cancer phenotype and tumor heterogeneity [ 16 , 17 , 18 ]. In contrast to results on standard imaging assessment, several recently published studies found promising results on radiomic feature (RF)-based analysis in oncologic imaging for outcome prediction in several entities, including markers of tumor heterogeneity [ 16 , 19 , 20 , 21 ].…”

Modelo radiómico con PSMA-PET para la discriminación de pacientes con cáncer de próstata de alto riesgo

“…En general, el porcentaje de radiómicas robustas que hemos obtenido en 68 Ga-PSMA-PET (38%) ha sido menor que el observado previamente para radiómicas de TC robustas con respecto a distintos equipos (45%), 24 como era de esperar dada la peor resolución y dado el mayor ruido asociados con la imagen PET. En previas investigaciones, las características radiómicas que en este estudio han dado lugar a modelos radiómicos han demostrado ser también robustas a la presencia de artefactos en los mapas TC para la corrección de atenuación 25 y al movimiento de la lesión. 26 Además, todas excepto QVL2, han demostrado ser comparables para distintos métodos automáticos de segmentación de lesiones heterogéneas, 25,26 lo que favorece la reproducibilidad de los modelos.…”

“…En previas investigaciones, las características radiómicas que en este estudio han dado lugar a modelos radiómicos han demostrado ser también robustas a la presencia de artefactos en los mapas TC para la corrección de atenuación 25 y al movimiento de la lesión. 26 Además, todas excepto QVL2, han demostrado ser comparables para distintos métodos automáticos de segmentación de lesiones heterogéneas, 25,26 lo que favorece la reproducibilidad de los modelos.…”

Nuclear medicine radiomics in digestive system tumors: Concept, applications, challenges, and future perspectives

“…In order to prevent misinterpretation of the descriptive models developed based on PET images, the variability of PET‐based RFs should be addressed properly. [ 78 ] Extensive studies are currently underway on the acquisition of dynamic PET data, which encompasses dynamic whole‐body imaging, as well as on the extraction of RFs from various imaging modalities.…”