Improvement of image quality for pancreatic cancer using deep learning-generated virtual monochromatic images: Comparison with single-energy computed tomography.

PURPOSE To construct a deep convolutional neural network that generates virtual monochromatic images (VMIs) from single-energy computed tomography (SECT) images for improved pancreatic cancer imaging quality. MATERIALS AND METHODS Fifty patients with pancreatic cancer underwent a dual-energy CT simulation and VMIs at 77 and 60 keV were reconstructed. A 2D deep densely connected convolutional neural network was modeled to learn the relationship between the VMIs at 77 (input) and 60 keV (ground-truth). Subsequently, VMIs were generated for 20 patients from SECT images using the trained deep learning model. RESULTS The contrast-to-noise ratio was significantly improved (p < 0.001) in the generated VMIs (4.1 ± 1.8) compared to the SECT images (2.8 ± 1.1). The mean overall image quality (4.1 ± 0.6) and tumor enhancement (3.6 ± 0.6) in the generated VMIs assessed on a five-point scale were significantly higher (p < 0.001) than that in the SECT images (3.2 ± 0.4 and 2.8 ± 0.4 for overall image quality and tumor enhancement, respectively). CONCLUSIONS The quality of the SECT image was significantly improved both objectively and subjectively using the proposed deep learning model for pancreatic tumors in radiotherapy.