Low dose positron emission tomography emulation from decimated high statistics: A clinical validation study

Abstract

Purpose The fundamental nature of positron emission tomography (PET), as an event detection system, provides some flexibility for data handling, including retrospective data manipulation. The reorganization of acquisition data allows the emulation of new scans arising from identical radiotracer spatial distributions, but with different statistical compositions, and is especially useful for evaluating the stability and reproducibility of reconstruction algorithms or when investigating extremely low count conditions. This approach is ubiquitous in the research literature but has only been validated, from the point of view of the noise properties, with numerical simulations and phantom data. We present here the first experiment comparing PET images of the same human subjects generated with two separate injections of radiotracer, using actual low dose (LD) data to validate a randomly decimated emulation from a standard dose scan. A key point of the work is focused on the randoms fractions, which scale differently than the trues at varying activity levels. Methods Eleven patients with non‐small cell lung cancer were enrolled in the study. Each imaging session consisted of two independent FDG‐PET/CT scans: a LD scan followed by a standard dose (SD) scan. Images were first reconstructed, using filtered back‐projection (FBP) and OSEM incorporating time‐of‐flight information and point‐spread function modeling (PSFTOF), from the LD and SD datasets comprising all counts from each scanned bed position. The number of true counts was recorded for all LD scans, and independent, count‐matched emulations (ELD) were reconstructed from the SD data. Noise distribution within the liver and standardized uptake value reproducibility within a population of contoured, tracer‐avid lesion volumes were evaluated across scans and statistics. Results The randoms fraction estimates were 17.4 ± 1.6% (14.9‐19.4) in the LD data and 42 ± 2.3% (37.1‐45.5) in the SD data. Eleven lesions were identified and volumes of interest were generated with a 50% threshold isocontour for each lesion, in every image. The distributions of metabolic volumes, means and maxima defined by the contoured volumes‐of‐interest (VOIs) were similar between the LD and SD sets. A two‐tailed, matched t‐test was performed on the populations of region statistics for both LD and ELD reconstructions, and the t‐statistics were 1.1 (P = 0.267) and ‐0.22 (P = 0.828) for the background liver VOIs and ‐0.54 (P = 0.603) and 0.23 (P = 0.821) for the lesion VOIs, for FBP and PSFTOF respectively. In every test, the null hypothesis that the two populations had the same mean could not be rejected at the 5% significance level. Conclusions Our results demonstrate that clinical LD PET scans can indeed be accurately emulated by the statistical decimation of standard dose scans, and this was achieved through validation by images generated with unbiased random coincidence estimations.

Study of low-dose PET image recovery using supervised learning with CycleGAN

“…10% and 30% counts of original scan, where generated by randomly discarding events in FDPET list mode data. Although the 10% and 30% images were generated by emulated low-count scans, however, those images have comparable quality with actual low-dose scan, and confirmed by the recent work [40]. By this way, FDPET and LDPET images are spatially aligned.…”

Convolutional neural networks for improving image quality with noisy PET data

“…The full PET datasets were used to emulate lower count levels through random list mode decimation [29] according to 9 predefined levels: 20, 15, 10, 7.5, 5, 2, 1, 0.5, and 0.25 million trues-independent realizations were generated at each count level, resulting in approximately 270 reduced-count datasets for every fullcount set. All images were then reconstructed with OSEM, corrected for attenuation and scatter and incorporating time-of-flight information and point-response modeling, for 2 iterations and 21 subsets.…”

Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy

“…The presence of high noise levels in PET images adversely impacts lesion detectability and quantitative accuracy (by introducing noise-induced bias) leading to uncertainties in clinical diagnosis and staging of disease. Moreover, there are strong incentives to reduce injected activities of positron-emitting tracers in longitudinal and pediatric PET imaging studies, which further increases noise magnitude (Schaefferkoetter et al 2019 ). Conventional post-reconstruction denoising methods tend to degrade the spatial resolution, which might hamper lesion detectability and identification of radiotracer uptake patterns.…”