Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis
This addresses radiation risk reduction in medical imaging for patients, but appears incremental as it builds on existing deep learning and compressed sensing methods.
The paper tackles the problem of streaking artifacts and high computational cost in compressed sensing CT reconstruction from sparse projection views by proposing a deep residual learning approach that estimates and subtracts artifacts, resulting in significantly better image quality and orders of magnitude faster speed.
Recently, compressed sensing (CS) computed tomography (CT) using sparse projection views has been extensively investigated to reduce the potential risk of radiation to patient. However, due to the insufficient number of projection views, an analytic reconstruction approach results in severe streaking artifacts and CS-based iterative approach is computationally very expensive. To address this issue, here we propose a novel deep residual learning approach for sparse view CT reconstruction. Specifically, based on a novel persistent homology analysis showing that the manifold of streaking artifacts is topologically simpler than original ones, a deep residual learning architecture that estimates the streaking artifacts is developed. Once a streaking artifact image is estimated, an artifact-free image can be obtained by subtracting the streaking artifacts from the input image. Using extensive experiments with real patient data set, we confirm that the proposed residual learning provides significantly better image reconstruction performance with several orders of magnitude faster computational speed.