Automatic Contrast Generation from Contrastless Computed Tomography

Autores da FMUP

• Fábio Sousa Nunes

  Autor

• Jennifer Mâncio Silva

  Autor

• Ricardo Manuel Alves Monteiro Fontes De Carvalho

  Autor

Participantes de fora da FMUP

• Domingues, Ruben
• Coimbra, Miguel
• Pedrosa, Joao
• Renna, Francesco

Unidades de investigação

• Cirurgia e Fisiologia

• Laboratório Associado RISE- Rede de Investigação em Saúde

  

  Investigador

  Fernando Carlos De Landér Schmitt

• RISE-Health

  

  Investigador

  Fernando Carlos De Landér Schmitt

Abstract

The use of contrast-enhanced computed tomography (CTCA) for detection of coronary artery disease (CAD) exposes patients to the risks of iodine contrast-agents and excessive radiation, increases scanning time and healthcare costs. Deep learning generative models have the potential to artificially create a pseudo-enhanced image from non-contrast computed tomography (CT) scans. In this work, two specific models of generative adversarial networks (GANs) - the Pix2Pix-GAN and the Cycle-GAN - were tested with paired non-contrasted CT and CTCA scans from a private and public dataset. Furthermore, an exploratory analysis of the trade-off of using 2D and 3D inputs and architectures was performed. Using only the Structural Similarity Index Measure (SSIM) and the Peak Signal-to-Noise Ratio (PSNR), it could be concluded that the Pix2Pix-GAN using 2D data reached better results with 0.492 SSIM and 16.375 dB PSNR. However, visual analysis of the output shows significant blur in the generated images, which is not the case for the Cycle-GAN models. This behavior can be captured by the evaluation of the Fr ` echet Inception Distance (FID), that represents a fundamental performance metric that is usually not considered by related works in the literature.

Keywords

• Algorithms; Coronary Artery Disease; Health Care Costs; Humans; Image Processing, Computer-Assisted; Iodine; Tomography, X-Ray Computed; Computerized tomography; Deep learning; Diagnosis; Diseases; Economic and social effects; Image enhancement; Iodine; Medical imaging; Signal to noise ratio; iodine; Computed tomography scan; Contrast-enhanced; Coronary artery disease; Health care costs; Iodine contrast agents; Peak signal to noise ratio; Scanning time; Similarity indices; Structural similarity; Time cost; algorithm; coronary artery disease; diagnostic imaging; health care cost; human; image processing; procedures; x-ray computed tomography; Generative adversarial networks