Mitigation of noise-induced bias of PET radiomic features.

INTRODUCTION: One major challenge in PET radiomics is its sensitivity to noise. Low signal-to-noise ratio (SNR) affects not only the precision but also the accuracy of quantitative metrics extracted from the images resulting in noise-induced bias. This phantom study aims to identify the radiomic features that are robust to noise in terms of precision and accuracy and to explore some methods that might help to correct noise-induced bias. METHODS: A phantom containing three 18F-FDG filled 3D printed inserts, reflecting heterogeneous tracer uptake and realistic tumor shapes, was used in the study. The three different phantom inserts were filled and scanned with three different tumor-to-background ratios, simulating a total of nine different tumors. From the 40-minute list-mode data, ten frames each for 5 s, 10 s, 30 s, and 120 s frame duration were reconstructed to generate images with different noise levels. Under these noise conditions, the precision and accuracy of the radiomic features were analyzed using intraclass correlation coefficient (ICC) and similarity distance metric (SDM) respectively. Based on the ICC and SDM values, the radiomic features were categorized into four groups: poor, moderate, good, and excellent precision and accuracy. A "difference image" created by subtracting two statistically equivalent replicate images was used to develop a model to correct the noise-induced bias. Several regression methods (e.g., linear, exponential, sigmoid, and power-law) were tested. The best fitting model was chosen based on Akaike information criteria. RESULTS: Several radiomic features derived from low SNR images have high repeatability, with 68% of radiomic features having ICC ≥ 0.9 for images with a frame duration of 5 s. However, most features show a systematic bias that correlates with the increase in noise level. Out of 143 features with noise-induced bias, the SDM values were improved based on a regression model (53 features to excellent and 67 to good) indicating that the noise-induced bias of these features can be, at least partially, corrected. CONCLUSION: To have a predictive value, radiomic features should reflect tumor characteristics and be minimally affected by noise. The present study has shown that it is possible to correct for noise-induced bias, at least in a subset of the features, using a regression model based on the local image noise estimates.

Noise sensitivity of 89Zr-Immuno-PET radiomics based on count-reduced clinical images.

PURPOSE: Low photon count in 89Zr-Immuno-PET results in images with a low signal-to-noise ratio (SNR). Since PET radiomics are sensitive to noise, this study focuses on the impact of noise on radiomic features from 89Zr-Immuno-PET clinical images. We hypothesise that 89Zr-Immuno-PET derived radiomic features have: (1) noise-induced variability affecting their precision and (2) noise-induced bias affecting their accuracy. This study aims to identify those features that are not or only minimally affected by noise in terms of precision and accuracy. METHODS: Count-split 89Zr-Immuno-PET patient scans from previous studies with three different 89Zr-labelled monoclonal antibodies were used to extract radiomic features at 50% (S50p) and 25% (S25p) of their original counts. Tumour lesions were manually delineated on the original full-count 89Zr-Immuno-PET scans. Noise-induced variability and bias were assessed using intraclass correlation coefficient (ICC) and similarity distance metric (SDM), respectively. Based on the ICC and SDM values, the radiomic features were categorised as having poor [0, 0.5), moderate [0.5, 0.75), good [0.75, 0.9), or excellent [0.9, 1] precision and accuracy. The number of features classified into these categories was compared between the S50p and S25p images using Fisher's exact test. All p values < 0.01 were considered statistically significant. RESULTS: For S50p, a total of 92% and 90% features were classified as having good or excellent ICC and SDM respectively, while for S25p, these decreased to 81% and 31%. In total, 148 features (31%) showed robustness to noise with good or moderate ICC and SDM in both S50p and S25p. The number of features classified into the four ICC and SDM categories between S50p and S25p was significantly different statistically. CONCLUSION: Several radiomic features derived from low SNR 89Zr-Immuno-PET images exhibit noise-induced variability and/or bias. However, 196 features (43%) that show minimal noise-induced variability and bias in S50p images have been identified. These features are less affected by noise and are, therefore, suitable candidates to be further studied as prognostic and predictive quantitative biomarkers in 89Zr-Immuno-PET studies.

Image Quality and Semiquantitative Measurements on the Biograph Vision PET/CT System: Initial Experiences and Comparison with the Biograph mCT.

In May 2018, the Biograph Vision PET/CT system was installed at the University Medical Center Groningen. This study evaluated the initial experiences with this new PET/CT system in terms of perceived image quality and semiquantitative analysis in comparison to the Biograph mCT as a reference. Methods: In total, 20 oncologic patients were enrolled and received a single 3 MBq/kg injected dose of 18F-FDG followed by a dual-imaging PET scan. Ten patients were scanned on the Biograph mCT first, whereas the other 10 patients were scanned on the Biograph Vision first. The locally preferred clinically reconstructed images were blindly reviewed by 3 nuclear medicine physicians and scored (using a Likert scale of 1-5) on tumor lesion demarcation, overall image quality, and image noise. In addition, these clinically reconstructed images were used for semiquantitative analysis by measurement of SUVs in tumor lesions. Images acquired using reconstructions conform with the European Association of Nuclear Medicine Research Ltd. (EARL) specifications were also used for measurements of SUV in tumor lesions and healthy tissues for comparison between systems. Results: The 18F-FDG dose received by the 14 men and 6 women (age range, 36-84; mean ± SD, 61 ± 16 y) ranged from 145 to 405 MBq (mean ± SD, 268 ± 59.3). Images acquired on the Biograph Vision were scored significantly higher on tumor lesion demarcation, overall image quality, and image noise than images acquired on the Biograph mCT (P < 0.001). The overall interreader agreement showed a Fleiss κ of 0.61 (95% confidence interval, 0.53-0.70). Furthermore, the SUVs in tumor lesions and healthy tissues agreed well (within 95%) between PET/CT systems, particularly when EARL-compliant reconstructions were used on both systems. Conclusion: In this initial study, the Biograph Vision showed improved image quality compared with the Biograph mCT in terms of lesion demarcation, overall image quality, and visually assessed signal-to-noise ratio. The 2 systems are comparable in semiquantitatively assessed image biomarkers in both healthy tissues and tumor lesions. Improved quantitative performance may, however, be feasible using the clinically optimized reconstruction settings.