Direct and indirect strategies of deep-learning-based attenuation correction for general purpose and dedicated cardiac SPECT

Purpose Deep-learning-based attenuation correction (AC) for SPECT includes both indirect and direct approaches. Indirect approaches generate attenuation maps (mu-maps) from emission images, while direct approaches predict AC images directly from non-attenuation-corrected (NAC) images without R-maps. For dedicated cardiac SPECT scanners with CZT detectors, indirect approaches are challenging due to the limited field-of-view (FOV). In this work, we aim to 1) first develop novel indirect approaches to improve the AC performance for dedicated SPECT; and 2) compare the AC performance between direct and indirect approaches for both general purpose and dedicated SPECT. Methods For dedicated SPECT, we developed strategies to predict truncated mu-maps from NAC images reconstructed with a small matrix, or full mu-maps from NAC images reconstructed with a large matrix using 270 anonymized clinical studies scanned on a GE Discovery NM/CT 570c SPECT/CT. For general purpose SPECT, we implemented direct and indirect approaches using 400 anonymized clinical studies scanned on a GE NM/CT 850c SPECT/CT. NAC images in both photopeak and scatter windows were input to predict mu-maps or AC images. Results For dedicated SPECT, the averaged normalized mean square error (NMSE) using our proposed strategies with full mu-maps was 1.20 +/- 0.72% as compared to 2.21 +/- 1.17% using the previous direct approaches. The polar map absolute percent error (APE) using our approaches was 3.24 +/- 2.79% (R-2 = 0.9499) as compared to 4.77 +/- 3.96% (R-2 =0.9213) using direct approaches. For general purpose SPECT, the averaged NMSE of the predicted AC images using the direct approaches was 2.57 +/- 1.06% as compared to 1.37 +/- 1.16% using the indirect approaches. Conclusions We developed strategies of generating R-maps for dedicated cardiac SPECT with small FOV. For both general purpose and dedicated SPECT, indirect approaches showed superior performance of AC than direct approaches.

Automated summary

The purpose of this study was to develop novel indirect approaches to improve the attenuation correction (AC) performance for dedicated single photon emission computed tomography (SPECT) and compare the AC performance between direct and indirect approaches for both general purpose and dedicated SPECT. The results showed that indirect approaches demonstrated superior AC performance compared to direct approaches for both types of SPECT.