Deep Learning-Based Computed Tomography Perfusion Mapping (DL-CTPM) for Pulmonary CT-to-Perfusion Translation.

Abstract

PURPOSE\nTo develop a deep learning-based computed tomography (CT) perfusion mapping (DL-CTPM) method that synthesizes lung perfusion images from CT images.\n\n\nMETHODS AND MATERIALS\nThis paper presents a retrospective analysis of the pulmonary technetium-99m-labeled macro-aggregated albumin (MAA) single-photon emission computed tomography (SPECT)/CT scans obtained from 73 patients at xx Hospital in Hong Kong in 2019. The left and right lung scans were separated to double the size of the dataset to 146. A three-dimensional attention residual neural network (ARNN) was constructed to extract textural features from the CT images and reconstruct corresponding functional images. Eighty-four samples were randomly selected for training and cross-validation, and the remaining 62 were used for model testing in terms of voxel-wise agreement and function-wise concordance. To assess the voxel-wise agreement, the Spearman s correlation coefficient (R) and structural similarity index measure (SSIM) between the images predicted by the DL-CTPM and the corresponding SPECT perfusion images were computed to assess the statistical and perceptual image similarities, respectively. To assess the function-wise concordance, the Dice similarity coefficient (DSC) was computed to determine the similarity of the low/high functional lung volumes.\n\n\nRESULTS\nThe evaluation of the voxel-wise agreement showed a moderate-to-high voxel value correlation (0.6733 ± 0.1728) and high structural similarity (0.7635 ± 0.0697) between the SPECT and DL-CTPM predicted perfusions. The evaluation of the function-wise concordance obtained an average DSC value of 0.8183 ± 0.0752 for high-functional lungs, ranging from 0.5819 to 0.9255, and 0.6501 ± 0.1061 for low-functional lungs, ranging from 0.2405 to 0.8212. Ninety-four percent of the test cases demonstrated high concordance (DSC > 0.7) between the high functional volumes contoured from the predicted and ground-truth perfusions.\n\n\nCONCLUSIONS\nWe developed a novel DL-CTPM method for estimating perfusion-based lung functional images from the CT domain using a 3D ARNN, which yielded moderate-to-high voxel-wise approximations of lung perfusion. To further contextualize these results toward future clinical application, a multi-institutional large-cohort study is warranted.