Deep learning‐based combination of [18F]‐FDG PET and CT images for producing pulmonary perfusion image

Abstract Background The main application of [18F] FDG‐PET ( 18 FDG‐PET) and CT images in oncology is tumor identification and quantification. Combining PET and CT images to mine pulmonary perfusion information for functional lung avoidance radiation therapy (FLART) is desirable but remains challenging. Purpose To develop a deep‐learning‐based (DL) method to combine 18 FDG‐PET and CT images for producing pulmonary perfusion images (PPI). Methods Pulmonary technetium‐99 m‐labeled macroaggregated albumin SPECT (PPI SPECT ), 18 FDG‐PET, and CT images obtained from 53 patients were enrolled. CT and PPI SPECT images were rigidly registered, and registration displacement was subsequently used to align 18 FDG‐PET and PPI SPECT images. The left/right lung was separated and rigidly registered again to improve the registration accuracy. A DL model based on 3D Unet architecture was constructed to directly combine multi‐modality 18 FDG‐PET and CT images for producing PPI (PPI DLM ). 3D Unet architecture was used as the basic architecture, and the input was expanded from a single‐channel to a dual‐channel to combine multi‐modality images. For comparative evaluation, 18 FDG‐PET images were also used alone to generate PPI DLPET . Sixty‐seven samples were randomly selected for training and cross‐validation, and 36 were used for testing. The Spearman correlation coefficient ( r s ) and multi‐scale structural similarity index measure (MS‐SSIM) between PPI DLM /PPI DLPET and PPI SPECT were computed to assess the statistical and perceptual image similarities. The Dice similarity coefficient (DSC) was calculated to determine the similarity between high‐/low‐ functional lung (HFL/LFL) volumes. Results The voxel‐wise r s and MS‐SSIM of PPI DLM /PPI DLPET were 0.78 ± 0.04/0.57 ± 0.03, 0.93 ± 0.01/0.89 ± 0.01 for cross‐validation and 0.78 ± 0.11/0.55 ± 0.18, 0.93 ± 0.03/0.90 ± 0.04 for testing. PPI DLM /PPI DLPET achieved averaged DSC values of 0.78 ± 0.03/0.64 ± 0.02 for HFL and 0.83 ± 0.01/0.72 ± 0.03 for LFL in the training dataset and 0.77 ± 0.11/0.64 ± 0.12, 0.82 ± 0.05/0.72 ± 0.06 in the testing dataset. PPI DLM yielded a stronger correlation and higher MS‐SSIM with PPI SPECT than PPI DLPET ( p < 0.001). Conclusions The DL‐based method integrates lung metabolic and anatomy information for producing PPI and significantly improved the accuracy over methods based on metabolic information alone. The generated PPI DLM can be applied for pulmonary perfusion volume segmentation, which is potentially beneficial for FLART treatment plan optimization.