Medical image super-resolution method based on dense blended attention network
This work addresses medical image super-resolution for improved diagnostic clarity, but it appears incremental as it builds on existing dense networks and attention mechanisms.
The paper tackles the problem of severe blurring in medical image super-resolution due to lack of high-frequency details, proposing a method based on dense neural networks and blended attention that improves PSNR by 0.05-11.25 dB and SSIM by 0.6-14.04% compared to mainstream methods.
In order to address the issue that medical image would suffer from severe blurring caused by the lack of high-frequency details in the process of image super-resolution reconstruction, a novel medical image super-resolution method based on dense neural network and blended attention mechanism is proposed. The proposed method adds blended attention blocks to dense neural network(DenseNet), so that the neural network can concentrate more attention to the regions and channels with sufficient high-frequency details. Batch normalization layers are removed to avoid loss of high-frequency texture details. Final obtained high resolution medical image are obtained using deconvolutional layers at the very end of the network as up-sampling operators. Experimental results show that the proposed method has an improvement of 0.05db to 11.25dB and 0.6% to 14.04% on the peak signal-to-noise ratio(PSNR) metric and structural similarity index(SSIM) metric, respectively, compared with the mainstream image super-resolution methods. This work provides a new idea for theoretical studies of medical image super-resolution reconstruction.