Stabilizing deep tomographic reconstruction: Part A. Hybrid framework and experimental results

Patterns

Varut Vardhanabhuti¹  Wenxiang Cong²  Pingkun Yan³  Dianlin Hu⁴  Weiwen Wu⁵  Shaoyu Wang⁵  Chuang Niu⁵  Ge Wang⁵  Hengyong Yu⁶  Hongming Shan⁷ 

[1] Computer Engineering, University of Massachusetts Lowell, Lowell, MA, USA;Department of Diagnostic Radiology, Li Ka Shing Faculty of Medicine, University of Hong Kong, Hong Kong SAR, China;Institute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai, China;School of Biomedical Engineering, Sun Yat-sen University, Shenzhen, Guangdong, China;Biomedical Imaging Center, Center for Biotechnology and Interdisciplinary Studies, Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA;;Department of Electrical &The Laboratory of Image Science and Technology, Southeast University, Nanjing, China;

关键词: DSML 2: Proof-of-concept: Data science output has been formulated, implemented, and tested for one domain/problem;   

DOI  :  

来源: DOAJ

【 摘 要 】

Summary: A recent PNAS paper reveals that several popular deep reconstruction networks are unstable. Specifically, three kinds of instabilities were reported: (1) strong image artefacts from tiny perturbations, (2) small features missed in a deeply reconstructed image, and (3) decreased imaging performance with increased input data. Here, we propose an analytic compressed iterative deep (ACID) framework to address this challenge. ACID synergizes a deep network trained on big data, kernel awareness from compressed sensing (CS)-inspired processing, and iterative refinement to minimize the data residual relative to real measurement. Our study demonstrates that the ACID reconstruction is accurate, is stable, and sheds light on the converging mechanism of the ACID iteration under a bounded relative error norm assumption. ACID not only stabilizes an unstable deep reconstruction network but also is resilient against adversarial attacks to the whole ACID workflow, being superior to classic sparsity-regularized reconstruction and eliminating the three kinds of instabilities. The bigger picture: Tomographic image reconstruction with deep learning has been a rapidly emerging field since 2016. Recently, a PNAS paper revealed that several well-known deep reconstruction networks are unstable for computed tomography (CT) and magnetic resonance imaging (MRI), and, in contrast, compressed sensing (CS)-inspired reconstruction methods are stable because of their theoretically proven property known as “kernel awareness.” Therefore, for deep reconstruction to realize its full potential and become a mainstream approach for tomographic imaging, it is critically important to stabilize deep reconstruction networks. Here, we propose an analytic compressed iterative deep (ACID) framework to synergize deep learning and compressed sensing through iterative refinement. We anticipate that this integrative model-based data-driven approach will promote the development and translation of deep tomographic image reconstruction networks.

【 授权许可】

Unknown