Search

Abstract Background Convolutional neural networks (CNNs), applied to baseline [18F]-FDG PET/CT maximum intensity projections (MIPs), show potential for treatment outcome prediction in diffuse large B-cell lymphoma (DLBCL). The aim of this study is to investigate the robustness of CNN predictions to different image reconstruction protocols. Baseline [18F]FDG PET/CT scans were collected from 20 DLBCL patients. EARL1, EARL2 and high-resolution (HR) protocols were applied per scan, generating three images with different image qualities. Image-based transformation was applied by blurring EARL2 and HR images to generate EARL1 compliant images using a Gaussian filter of 5 and 7 mm, respectively. MIPs were generated for each of the reconstructions, before and after image transformation. An in-house developed CNN predicted the probability of tumor progression within 2 years for each MIP. The difference in probabilities per patient was then calculated between both EARL2 and HR with respect to EARL1 (delta probabilities or ΔP). We compared these to the probabilities obtained after aligning the data with ComBat using the difference in median and interquartile range (IQR). Results CNN probabilities were found to be sensitive to different reconstruction protocols (EARL2 ΔP: median = 0.09, interquartile range (IQR) = [0.06, 0.10] and HR ΔP: median = 0.1, IQR = [0.08, 0.16]). Moreover, higher resolution images (EARL2 and HR) led to higher probability values. After image-based and ComBat transformation, an improved agreement of CNN probabilities among reconstructions was found for all patients. This agreement was slightly better after image-based transformation (transformed EARL2 ΔP: median = 0.022, IQR = [0.01, 0.02] and transformed HR ΔP: median = 0.029, IQR = [0.01, 0.03]). Conclusion Our CNN-based outcome predictions are affected by the applied reconstruction protocols, yet in a predictable manner. Image-based harmonization is a suitable approach to harmonize CNN predictions across image reconstruction protocols.

Abstract Convolutional neural networks (CNNs) may improve response prediction in diffuse large B-cell lymphoma (DLBCL). The aim of this study was to investigate the feasibility of a CNN using maximum intensity projection (MIP) images from 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) baseline scans to predict the probability of time-to-progression (TTP) within 2 years and compare it with the International Prognostic Index (IPI), i.e. a clinically used score. 296 DLBCL 18F-FDG PET/CT baseline scans collected from a prospective clinical trial (HOVON-84) were analysed. Cross-validation was performed using coronal and sagittal MIPs. An external dataset (340 DLBCL patients) was used to validate the model. Association between the probabilities, metabolic tumour volume and Dmaxbulk was assessed. Probabilities for PET scans with synthetically removed tumors were also assessed. The CNN provided a 2-year TTP prediction with an area under the curve (AUC) of 0.74, outperforming the IPI-based model (AUC = 0.68). Furthermore, high probabilities (> 0.6) of the original MIPs were considerably decreased after removing the tumours (

Abstract Background [18F]FDG PET-based metabolic tumor volume (MTV) is a promising prognostic marker for lymphoma patients. The aim of this study is to assess the sensitivity of several MTV segmentation methods to variations in image reconstruction methods and the ability of ComBat to improve MTV reproducibility. Methods Fifty-six lesions were segmented from baseline [18F]FDG PET scans of 19 lymphoma patients. For each scan, EARL1 and EARL2 standards and locally clinically preferred reconstruction protocols were applied. Lesions were delineated using 9 semiautomatic segmentation methods: fixed threshold based on standardized uptake value (SUV), (SUV = 4, SUV = 2.5), relative threshold (41% of SUVmax [41M], 50% of SUVpeak [A50P]), majority vote-based methods that select voxels detected by at least 2 (MV2) and 3 (MV3) out of the latter 4 methods, Nestle thresholding, and methods that identify the optimal method based on SUVmax (L2A, L2B). MTVs from EARL2 and locally clinically preferred reconstructions were compared to those from EARL1. Finally, different versions of ComBat were explored to harmonize the data. Results MTVs from the SUV4.0 method were least sensitive to the use of different reconstructions (MTV ratio: median = 1.01, interquartile range = [0.96–1.10]). After ComBat harmonization, an improved agreement of MTVs among different reconstructions was found for most segmentation methods. The regular implementation of ComBat (‘Regular ComBat’) using non-transformed distributions resulted in less accurate and precise MTV alignments than a version using log-transformed datasets (‘Log-transformed ComBat’). Conclusion MTV depends on both segmentation method and reconstruction methods. ComBat reduces reconstruction dependent MTV variability, especially when log-transformation is used to account for the non-normal distribution of MTVs.

Abstract Purpose Recently, updated EARL specifications (EARL2) have been developed and announced. This study aims at investigating the impact of the EARL2 specifications on the quantitative reads of clinical PET–CT studies and testing a method to enable the use of the EARL2 standards whilst still generating quantitative reads compliant with current EARL standards (EARL1). Methods Thirteen non-small cell lung cancer (NSCLC) and seventeen lymphoma PET–CT studies were used to derive four image datasets—the first dataset complying with EARL1 specifications and the second reconstructed using parameters as described in EARL2. For the third (EARL2F6) and fourth (EARL2F7) dataset in EARL2, respectively, 6 mm and 7 mm Gaussian post-filtering was applied. We compared the results of quantitative metrics (MATV, SUVmax, SUVpeak, SUVmean, TLG, and tumor-to-liver and tumor-to-blood pool ratios) obtained with these 4 datasets in 55 suspected malignant lesions using three commonly used segmentation/volume of interest (VOI) methods (MAX41, A50P, SUV4). Results We found that with EARL2 MAX41 VOI method, MATV decreases by 22%, TLG remains unchanged and SUV values increase by 23–30% depending on the specific metric used. The EARL2F7 dataset produced quantitative metrics best aligning with EARL1, with no significant differences between most of the datasets (p>0.05). Different VOI methods performed similarly with regard to SUV metrics but differences in MATV as well as TLG were observed. No significant difference between NSCLC and lymphoma cancer types was observed. Conclusions Application of EARL2 standards can result in higher SUVs, reduced MATV and slightly changed TLG values relative to EARL1. Applying a Gaussian filter to PET images reconstructed using EARL2 parameters successfully yielded EARL1 compliant data.