Direct inference of Patlak parametric images in whole-body PET/CT imaging using convolutional neural networks

Purpose

This study proposed and investigated the feasibility of estimating Patlak-derived influx rate constant (K_i) from standardized uptake value (SUV) and/or dynamic PET image series.

Methods

Whole-body ¹⁸F-FDG dynamic PET images of 19 subjects consisting of 13 frames or passes were employed for training a residual deep learning model with SUV and/or dynamic series as input and K_i-Patlak (slope) images as output. The training and evaluation were performed using a nine-fold cross-validation scheme. Owing to the availability of SUV images acquired 60 min post-injection (20 min total acquisition time), the data sets used for the training of the models were split into two groups: “With SUV” and “Without SUV.” For “With SUV” group, the model was first trained using only SUV images and then the passes (starting from pass 13, the last pass, to pass 9) were added to the training of the model (one pass each time). For this group, 6 models were developed with input data consisting of SUV, SUV plus pass 13, SUV plus passes 13 and 12, SUV plus passes 13 to 11, SUV plus passes 13 to 10, and SUV plus passes 13 to 9. For the “Without SUV” group, the same trend was followed, but without using the SUV images (5 models were developed with input data of passes 13 to 9). For model performance evaluation, the mean absolute error (MAE), mean error (ME), mean relative absolute error (MRAE%), relative error (RE%), mean squared error (MSE), root mean squared error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) were calculated between the predicted K_i-Patlak images by the two groups and the reference K_i-Patlak images generated through Patlak analysis using the whole acquired data sets. For specific evaluation of the method, regions of interest (ROIs) were drawn on representative organs, including the lung, liver, brain, and heart and around the identified malignant lesions.

Results

The MRAE%, RE%, PSNR, and SSIM indices across all patients were estimated as 7.45 ± 0.94%, 4.54 ± 2.93%, 46.89 ± 2.93, and 1.00 ± 6.7 × 10⁻⁷, respectively, for models predicted using SUV plus passes 13 to 9 as input. The predicted parameters using passes 13 to 11 as input exhibited almost similar results compared to the predicted models using SUV plus passes 13 to 9 as input. Yet, the bias was continuously reduced by adding passes until pass 11, after which the magnitude of error reduction was negligible. Hence, the predicted model with SUV plus passes 13 to 9 had the lowest quantification bias. Lesions invisible in one or both of SUV and K_i-Patlak images appeared similarly through visual inspection in the predicted images with tolerable bias.

Conclusion

This study concluded the feasibility of direct deep learning-based approach to estimate K_i-Patlak parametric maps without requiring the input function and with a fewer number of passes. This would lead to shorter acquisition times for WB dynamic imaging with acceptable bias and comparable lesion detectability performance.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-022-05867-w.

Comparison of TG-43 dosimetric parameters of brachytherapy sources obtained by three different versions of MCNP codes

Monte Carlo simulations are widely used for calculation of the dosimetric parameters of brachytherapy sources. MCNP4C2, MCNP5, MCNPX, EGS4, EGSnrc, PTRAN, and GEANT4 are among the most commonly used codes in this field. Each of these codes utilizes a cross-sectional library for the purpose of simulating different elements and materials with complex chemical compositions. The accuracies of the final outcomes of these simulations are very sensitive to the accuracies of the cross-sectional libraries. Several investigators have shown that inaccuracies of some of the cross section files have led to errors in 125I and 103Pd parameters. The purpose of this study is to compare the dosimetric parameters of sample brachytherapy sources, calculated with three different versions of the MCNP code - MCNP4C, MCNP5, and MCNPX. In these simulations for each source type, the source and phantom geometries, as well as the number of the photons, were kept identical, thus eliminating the possible uncertainties. The results of these investigations indicate that for low-energy sources such as 125I and 103Pd there are discrepancies in gL(r) values. Discrepancies up to 21.7% and 28% are observed between MCNP4C and other codes at a distance of 6 cm for 103Pd and 10 cm for 125I from the source, respectively. However, for higher energy sources, the discrepancies in gL(r) values are less than 1.1% for 192Ir and less than 1.2% for 137Cs between the three codes.