Model-based iterative reconstruction algorithms for low-dose X-ray computed tomography (CT) are computationally expensive. To address this problem, we recently proposed a deep convolutional neural network (CNN) for low-dose X-ray CT and won the second place in 2016 AAPM Low-Dose CT Grand Challenge. However, some of the textures were not fully recovered. To address this problem, here we propose a novel framelet-based denoising algorithm using wavelet residual network which synergistically combines the expressive power of deep learning and the performance guarantee from the framelet-based denoising algorithms. The new algorithms were inspired by the recent interpretation of the deep CNN as a cascaded convolution framelet signal representation. Extensive experimental results confirm that the proposed networks have significantly improved performance and preserve the detail texture of the original images.

Shin YJ, et al. Korean J Radiol. 2020 Jan;21:e15. https://doi.org/10.3348/kjr.2019.0413

Considerable interobserver variability exists in the assignment at CT of local resectability of pancreatic cancer, even amongst experienced radiologists. Background Accurate assessment of local resectability of pancreatic cancer at initial workup is critical to determine the most appropriate management strategy among up-front operation, neoadjuvant ...

This prospective study demonstrated that PET/MRI with dedicated rectal and liver MRI in patients with newly diagnosed advanced rectal cancers performs better than contrast material–enhanced CT in a... BackgroundThe performance of PET/MRI in the determination of distant metastases (M stage) in rectal cancer relative to the current practice with contrast material–enhanced CT is largely unknown.Pur...

Among four hepatocellular carcinoma diagnosis guidelines and by using MRI with hepatobiliary contrast agent, Eastern guidelines offered higher sensitivity whereas Western guidelines provided higher specificity in patients with cirrhosis and in those with chronic hepatitis B.