Reducing scan time in 177Lu planar scintigraphy using convolutional neural network: A Monte Carlo simulation study

Purpose: The aim of this study was to reduce scan time in [sup.177]Lu planar scintigraphy through the use of convolutional neural network (CNN) to facilitate personalized dosimetry for [sup.177]Lu‐based peptide receptor radionuclide therapy. Methods: The CNN model used in this work was based on DenseNet, and the training and testing datasets were generated from Monte Carlo simulation. The CNN input images (IMG[sub.input]) consisted of [sup.177]Lu planar scintigraphy that contained 10–90% of the total photon counts, while the corresponding full‐count images (IMG[sup.100%]) were used as the CNN label images. Two‐sample t‐test was conducted to compare the difference in pixel intensities within region of interest between IMG[sup.100%] and CNN output images (IMG[sub.output]). Results: No difference was found in IMG[sub.output] for rods with diameters ranging from 13 to 33 mm in the Derenzo phantom with a target‐to‐background ratio of 20:1, while statistically significant differences were found in IMG[sub.output] for the 10‐mm diameter rods when IMG[sub.input] containing 10% to 60% of the total photon counts were denoised. Statistically significant differences were found in IMG[sub.output] for both right and left kidneys in the NCAT phantom when IMG[sub.input] containing 10% of the total photon counts were denoised. No statistically significant differences were found in IMG[sub.output] for any other source organs in the NCAT phantom. Conclusion: Our results showed that the proposed method can reduce scan time by up to 70% for objects larger than 13 mm, making it a useful tool for personalized dosimetry in [sup.177]Lu‐based peptide receptor radionuclide therapy in clinical practice.