Sparse-View Reconstruction in Dental Computed Tomography by Using a Dictionary-Learning Based Method

• Published in: Journal of the Korean Physical Society Vol. 74; no. 1; pp. 57 - 62
• Main Authors: Kim, Guna, Park, Soyoung, Park, Chulkyu, Lee, Dongyeon, Lim, Younghwan, Kim, Kyuseok, Kim, Woosung, Cho, Hyosung, Seo, Changwoo, Lim, Hyunwoo, Lee, Hunwoo, Kang, Seokyoon, Park, Jeongeun, Jeon, Duhee
• Format: Journal Article
• Language: English
• Published: Seoul The Korean Physical Society 01.01.2019; Springer Nature B.V; 한국물리학회
• Subjects: Algorithms; Computation; Computed tomography; Computer simulation; Dictionaries; Image acquisition; Image quality; Image reconstruction; Learning; Learning theory; Mathematical and Computational Physics; Medical imaging; Particle and Nuclear Physics; Physics; Physics and Astronomy; Radiation dosage; Representations; Theoretical; Tomography; X ray tubes; 물리학; Sparse-view; Low radiation dosage; Dental computed tomography; Dictionary-learning
• ISSN: 0374-4884; 1976-8524
• DOI: 10.3938/jkps.74.57

In this study, we investigated sparse-view reconstruction in dental computed tomography (DCT) by using a dictionary-learning (DL)-based method to reduce excessive radiation dose to patients. In sparse-view DCT, only a small number (< 100) of projections, far less than what is required by the Nyquist sampling theory, are acquired from the imaging system and used for image reconstruction. DL is a representation learning theory that aims to find a sparse representation of the input signal in the form of a linear combination of basic elements (or atoms). We implemented a DL-based reconstruction algorithm and performed a systematic simulation and an experiment to evaluate the algorithm’s effectiveness for sparse-view reconstruction in DCT. DCT images were reconstructed using the three sparse-view projections of P30, P40, and P60, and their image qualities were quantitatively evaluated in terms of the intensity profile, the universal quality index, and the peak signal-to-noise ratio. The hardware system used in the experiment consisted of an X-ray tube, which was run at 90 kV p and 40 mA, and a flat-panel detector with a 388-μm pixel size. Our simulation and experimental results indicate that the DL-based method significantly reduced streak artifacts in the sparse-view DCT reconstruction when using P40, thus maintaining image quality.