Notice

One BMIPL’s paper, “Unsupervised Training Of Deep Low-Dose CT Reconstruction Without Full-Dose CT Images,” by Kwanyoung Kim, Shakarim Soltanayev and Se Young Chun has been accepted to IEEE Journal of Selected Topics In Signal Processing (IF 6.688). Kwanyoung Kim is about to finish his MS program at BMIPL, UNIST, and Shakarim Soltanayev finished his MS program at BMIPL, UNIST, last year. IEEE Journal of Selected Topics In Signal Processing is one of the top journals in signal processing. Almost all works on low-dose CT reconstruction using deep neural networks require clean ground truth images with high radiation dose. Our work proposed unsupervised training methods only with low-dose CT measurements and demonstrated its feasibility with synthetic low-dose CT measurements.