Computed tomography reconstruction using deep image prior and learned reconstruction methods. (2nd September 2020)

• Record Type: Journal Article
• Authors: Baguer, Daniel Otero; Leuschner, Johannes; Schmidt, Maximilian
• Is Part Of: Inverse problems. Volume 36:Number 9(2020)
• Publication Date: 2020-09-02
• Subjects: inverse problems -- deep learning -- computed tomography -- deep image prior -- neural networks; Inverse problems (Differential equations) -- Periodicals; 515.357
• DOI: 10.1088/1361-6420/aba415
• Languages: English
• ISSNs: 0266-5611

Abstract

Abstract: In this paper we describe an investigation into the application of deep learning methods for low-dose and sparse angle computed tomography using small training datasets. To motivate our work we review some of the existing approaches and obtain quantitative results after training them with different amounts of data. We find that the learned primal-dual method has an outstanding performance in terms of reconstruction quality and data efficiency. However, in general, end-to-end learned methods have two deficiencies: (a) a lack of classical guarantees in inverse problems and (b) the lack of generalization after training with insufficient data. To overcome these problems, we introduce the deep image prior approach in combination with classical regularization and an initial reconstruction. The proposed methods achieve the best results in the low-data regime in three challenging scenarios.