Deep-Learning Generation of Synthetic Intermediate Projections Improves ¹⁷⁷Lu SPECT Images Reconstructed with Sparsely Acquired Projections

Abstract

The aims were to decrease 177 Lu-SPECT (single-photon emission computed tomography) acquisition time by reducing the number of projections and to circumvent image degradation by adding deep learning-generated synthesized projections. Method: We constructed a deep convolutional U-structured network for generating synthetic intermediate projections (CUSIP). The number of SPECT investigations was 352 for training, 37 for validation, and 15 for testing. The input was every fourth projection of 120 acquired SPECT projections, i.e., 30 projections. The output was 30 synthetic intermediate projections (SIPs) per CUSIP. SPECT images were reconstructed with 120 or 30 projections, or 120 projections where 90 SIPs were generated from the 30 projections (30-120SIP); using 3 CUSIPs. The reconstructions were performed with two ordered subset expectation maximization (OSEM) algorithms: attenuation-corrected (AC)-OSEM, and attenuation, scatter, and collimator response-corrected (ASCC)-OSEM. Image quality of SIPs and SPECT images were quantitatively evaluated with root mean square error, peak signal-to-noise-ratio (PSNR), and structural similarity (SSIM) index metrics. From a Jaszczak SPECT Phantom, the recovery and signal-to-noise ratio (SNR) were determined. In addition, an experienced observer qualitatively assessed the SPECT image quality of the test set. Kidney activity concentrations, as determined from the different SPECT images, were compared. Results: The generated SIPs had a mean SSIM value of 0.926 (0.061). For AC-OSEM, the reconstruction with 30-120SIP had higher SSIM (0.993 vs. 0.989; p<0.001) and PSNR (49.5 vs. 47.2; p<0.001) values than the reconstruction with 30 projections. ASCC-OSEM had higher SSIM and PSNR values than AC-OSEM (p<0.001). There was a minor loss in recovery for the 30-120SIP set, but SNR was clearly improved compared to the 30-projection set. The observer assessed 27/30

Artificial Intelligence Clinical Application in Prostate Cancer Molecular Imaging

“…Furthermore, in the theragnostic PC field, AI may improve the workflow as preliminarily described in the literature. 61,62 Data availability, privacy-concerns, lack of transparent, standardized, and universal procedural agreement are limiting the development of AI approaches. But there are preliminary attempts to override these limitations, 63 and fully automated processing and high-level computer interpretation of imaging are nowadays becoming a reality.…”

Evaluation of the Spatial Resolution in Monte Carlo-Based Spect/Ct Reconstruction of 111in-Octreotide Images

“…This will be included in future studies. Furthermore, decreasing the noise level in 111 In SPECT/CT imaging by adding synthetic intermediate projections, which was successfully accomplished for 177 Lu SPECT images ( 19 ) , would also be relevant to explore further for 111 In SPECT images.…”

Improvements of 111in Spect Images Reconstructed With Sparsely Acquired Projections by Deep Learning Generated Synthetic Projections

“…In the present study, we used our recently constructed deep neural network: the deep Convolutional U-net–shaped neural network for generation of Synthetic Intermediated Projections (CUSIP) ( 7 ) . We use three trained CUSIP for generating 90 SIPs from 30 acquired projections.…”