Retrospective study of deep learning to reduce noise in non-contrast head CT images

作者：Kelvin Wong, Jonathon Cummock, Yunjie He, Rahul Ghosh, John Volpi, Stephen T.C. Wong · 发表于：Computerized Medical Imaging and Graphics · 年份：2021 · DOI：10.1016/j.compmedimag.2021.101996 · 被引用次数：17 · 研究领域：Acute Ischemic Stroke Management、Advanced X-ray and CT Imaging、Digital Radiography and Breast Imaging

PURPOSE: Presented herein is a novel CT denoising method uses a skip residual encoder-decoder framework with group convolutions and a novel loss function to improve the subjective and objective image quality for improved disease detection in patients with acute ischemic stroke (AIS). MATERIALS AND METHODS: In this retrospective study, confirmed AIS patients with full-dose NCCT head scans were randomly selected from a stroke registry between 2016 and 2020. 325 patients (67 ± 15 years, 176 men) were included. 18 patients each with 4-7 NCCTs performed within 5-day timeframe (83 total scans) were used for model training; 307 patients each with 1-4 NCCTs performed within 5-day timeframe (380 total scans) were used for hold-out testing. In the training group, a mean CT was created from the patient's co-registered scans for each input CT to train a rotation-reflection equivariant U-Net with skip and residual connections, as well as a group convolutional neural network (SRED-GCNN) using a custom loss function to remove image noise. Denoising performance was compared to the standard Block-matching and 3D filtering (BM3D) method and RED-CNN quantitatively and visually. Signal-to-noise ratio (SNR) and contrast-to-noise (CNR) were measured in manually drawn regions-of-interest in grey matter (GM), white matter (WM) and deep grey matter (DG). Visual comparison and impact on spatial resolution were assessed through phantom images. RESULTS: SRED-GCNN reduced the original CT image noise sign...