首页|Research from University of Shanghai for Science and Technology Yields New Study Findings on Pattern Recognition and Artificial Intelligence (DAGAN: A GAN Netwo rk for Image Denoising of Medical Images Using Deep Learning of Residual Attenti on ...)
Research from University of Shanghai for Science and Technology Yields New Study Findings on Pattern Recognition and Artificial Intelligence (DAGAN: A GAN Netwo rk for Image Denoising of Medical Images Using Deep Learning of Residual Attenti on ...)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Research findings on pattern recogniti on and artificial intelligence are discussed in a new report. According to news reporting from Shanghai, People's Republic of China, by NewsRx journalists, rese arch stated, "Medical images are susceptible to noise and artifacts, so denoisin g becomes an essential pre-processing technique for further medical image proces sing stages." The news reporters obtained a quote from the research from University of Shangha i for Science and Technology: "We propose a medical image denoising method based on dual-attention mechanism for generative adversarial networks (GANs). The met hod is based on a GAN model with fused residual structure and introduces a globa l skip-layer connection structure to balance the learning ability of the shallow and deep networks. The generative network uses a residual module containing cha nnel and spatial attention for efficient extraction of CT image features. The me an square error loss and perceptual loss are introduced to construct a composite loss function to optimize the model loss function, which helps to improve the i mage generation effect of the model. Experimental results on the LUNA dataset an d "the 2016 Low-Dose CT Grand Challenge" dataset show that DAGAN achieves the be st results in root mean square error (RMSE), structural similarity (SSIM) and pe ak signal-to-noise ratio (PSNR) when compared to the state-of-the-art methods."
University of Shanghai for Science and T echnologyShanghaiPeople's Republic of ChinaAsiaMachine LearningPattern Recognition and Artificial Intelligence
NETL
NSTL
