Deep learning enhanced ultra-fast SPECT/CT bone scan in patients with suspected malignancy: quantitative assessment and clinical performance

Abstract

<i>Objectives</i>. To evaluate the clinical performance of deep learning-enhanced ultrafast single photon emission computed tomography/computed tomography (SPECT/CT) bone scans in patients with suspected malignancy.<i>Approach</i>. In this prospective study, 102 patients with potential malignancy were enrolled and underwent a 20 min SPECT/CT and a 3 min SPECT scan. A deep learning model was applied to generate algorithm-enhanced images (3 min DL SPECT). The reference modality was the 20 min SPECT/CT scan. Two reviewers independently evaluated general image quality, Tc-99m MDP distribution, artifacts, and diagnostic confidence of 20 min SPECT/CT, 3 min SPECT/CT, and 3 min DL SPECT/CT images. The sensitivity, specificity, accuracy, and interobserver agreement were calculated. The lesion maximum standard uptake value (SUV_max) of the 3 min DL and 20 min SPECT/CT images was analyzed. The peak signal-to-noise ratio (PSNR) and structure similarity index measure (SSIM) were evaluated.<i>Main results</i>. The 3 min DL SPECT/CT images showed significantly superior general image quality, Tc-99m MDP distribution, artifacts, and diagnostic confidence than the 20 min SPECT/CT images (<i>P</i>< 0.0001). The diagnostic performance of the 20 min and 3 min DL SPECT/CT images was similar for reviewer 1 (paired<i>X</i>²= 0.333,<i>P</i>= 0.564) and reviewer 2 (paired<i>X</i>²= 0.05,<i>P</i>= 0.823). The diagnosis results for the 20 min (kappa = 0.822) and 3 min DL (kappa = 0.732) SPECT/CT images showed high interobserver agreement. The 3 min DL SPECT/CT images had significantly higher PSNR and SSIM than the 3 min SPECT/CT images (51.44 versus 38.44,<i>P</i>< 0.0001; 0.863 versus 0.752,<i>P</i>< 0.0001). The SUV_maxof the 3 min DL and 20 min SPECT/CT images showed a strong linear relationship (<i>r</i>= 0.991;<i>P</i>< 0.0001).<i>Significance.</i>Ultrafast SPECT/CT with a 1/7 acquisition time can be enhanced by a deep learning method to achieve comparable image quality and diagnostic value to those of standard acquisition.