Conditioning generative latent optimization for sparse-view computed tomography image reconstruction

The issue of delivered doses during computed tomography (CT) scans encouraged sparser sets of X-ray projection, severely degrading reconstructions from conventional methods. Although most deep learning approaches benefit from large supervised datasets, they cannot generalize to new acquisition protocols (geometry, source/detector specifications). To address this issue, we developed a method working without training data and independently of experimental setups. In addition, our model may be initialized on small unsupervised datasets to enhance reconstructions.

We propose a conditioned generative latent optimization (cGLO) in which a decoder reconstructs multiple slices simultaneously with a shared objective. It is tested on full-dose sparse-view CT for varying projection sets: (a) without training data against Deep Image Prior (DIP) and (b) with training datasets of multiple sizes against state-of-the-art score-based generative models (SGMs). Peak signal-to-noise ratio (PSNR) and structural SIMilarity (SSIM) metrics are used to quantify reconstruction quality.

cGLO demonstrates better SSIM than SGMs (between $+0.034$ and $+0.139$ ) and has an increasing advantage for smaller datasets reaching a $+6.06\mathrm{dB}$ PSNR gain. Our strategy also outperforms DIP with at least a $+1.52\mathrm{dB}$ PSNR advantage and peaks at $+3.15\mathrm{dB}$ with fewer angles. Moreover, cGLO does not create artifacts or structural deformations contrary to DIP and SGMs.

We propose a parsimonious and robust reconstruction technique offering similar to better performances when compared with state-of-the-art methods regarding full-dose sparse-view CT. Our strategy could be readily applied to any imaging reconstruction task without any assumption about the acquisition protocol or the quantity of available data.