SAVER: Stochastic Adaptive Variance-Driven Exploration and Reconstruction for Low-Dose Computed Tomography
Organizations: Graduate School of Chemical Sciences and Engineering, Hokkaido University, Kita 13 Nishi 8, Kita-ku, Sapporo, Hokkaido 060-8628, Japan. · Research Center of Mathematics for Social Creativity, Research Institute for Electronic Science, Hokkaido University, Kita 20 Nishi 10, Kita-ku, Sapporo, Hokkaido 001-0020, Japan · Institute for Chemical Reaction Design and Discovery (WPI-ICReDD), Hokkaido University, Kita 21 Nishi 10, Kita-ku, Sapporo, Hokkaido 001-0021, Japan. · Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan. · RIKEN Center for Advanced Intelligence Project (AIP), 1-4-1 Nihonbashi, Chuo-ku, Tokyo 103-0027, Japan. · Department of Computer Science, Institute of Systems and Information Engineering, University of Tsukuba, Tsukuba 305-8573, Japan. · International Center for Synchrotron Radiation Innovation Smart (SRIS), Tohoku University, Sendai, Miyagi 980-8577, Japan. · Institute of Multidisciplinary Research for Advanced Materials (IMRAM), Tohoku University, Sendai, Miyagi 980-8577, Japan. · Department of Finemechanics, Graduate School of Engineering, Tohoku University, Sendai, Miyagi 980-8579, Japan. · Graduate School of Dentistry, Tohoku University, Sendai, Miyagi 980-8575, Japan.
Abstract
Computed Tomography (CT) is indispensable in clinical diagnostics, yet minimizing radiation dose without compromising image quality remains a critical challenge. Conventional low-dose protocols often rely on fixed, uniform angular sampling, independent of the underlying structural complexity of organs of individual patients. We propose ``Stochastic Adaptive Variance-Driven Exploration and Reconstruction'' (SAVER), an adaptive data acquisition framework that selects projection angles in real-time based on the statistical variance of acquired data. Utilizing a Softmax-based stochastic scheduling scheme with simulated annealing, SAVER prioritizes directions with high structural information while maintaining necessary exploration. Numerical experiments across 8 diverse phantoms demonstrate that SAVER achieves consistently higher reconstruction fidelity than conventional random sampling, particularly for objects with high structural anisotropy. Furthermore, the proposed method exhibits robust performance under significant measurement noise. By dynamically reallocating radiation dose to the most informative projections, SAVER provides a mathematically-grounded approach to maximize diagnostic quality per unit of radiation dose, marking a shift toward sample-dependent, data-driven CT acquisition.