English

Stabilizing Deep Tomographic Reconstruction

Image and Video Processing 2021-09-14 v5 Computer Vision and Pattern Recognition Machine Learning

Abstract

Tomographic image reconstruction with deep learning is an emerging field, but a recent landmark study reveals that several deep reconstruction networks are unstable for computed tomography (CT) and magnetic resonance imaging (MRI). Specifically, three kinds of instabilities were reported: (1) strong image artefacts from tiny perturbations, (2) small features missing in a deeply reconstructed image, and (3) decreased imaging performance with increased input data. On the other hand, compressed sensing (CS) inspired reconstruction methods do not suffer from these instabilities because of their built-in kernel awareness. For deep reconstruction to realize its full potential and become a mainstream approach for tomographic imaging, it is thus critically important to meet this challenge by stabilizing deep reconstruction networks. Here we propose an Analytic Compressed Iterative Deep (ACID) framework to address this challenge. ACID synergizes a deep reconstruction network trained on big data, kernel awareness from CS-inspired processing, and iterative refinement to minimize the data residual relative to real measurement. Our study demonstrates that the deep reconstruction using ACID is accurate and stable, and sheds light on the converging mechanism of the ACID iteration under a Bounded Relative Error Norm (BREN) condition. In particular, the study shows that ACID-based reconstruction is resilient against adversarial attacks, superior to classic sparsity-regularized reconstruction alone, and eliminates the three kinds of instabilities. We anticipate that this integrative data-driven approach will help promote development and translation of deep tomographic image reconstruction networks into clinical applications.

Keywords

Cite

@article{arxiv.2008.01846,
  title  = {Stabilizing Deep Tomographic Reconstruction},
  author = {Weiwen Wu and Dianlin Hu and Wenxiang Cong and Hongming Shan and Shaoyu Wang and Chuang Niu and Pingkun Yan and Hengyong Yu and Varut Vardhanabhuti and Ge Wang},
  journal= {arXiv preprint arXiv:2008.01846},
  year   = {2021}
}

Comments

78 pages, 30 figures, 149 references

R2 v1 2026-06-23T17:38:47.103Z