Artifacts Reduction Using Multi-Scale Feature Attention Network in Compressed Medical Images
Source abstract
Abstract
Medical image compression is one of the essential technologies to facilitate real-time medical data transmission in remote healthcare applications. In general, image compression can introduce undesired coding artifacts, such as blocking artifacts and ringing effects. In this paper, we proposed a Multi-Scale Feature Attention Network (MSFAN) with two essential parts, which are multi-scale feature extraction layers and feature attention layers to efficiently remove coding artifacts of compressed medical images. Multi-scale feature extraction layers have four Feature Extraction (FE) blocks. Each FE block consists of five convolution layers and one CA block for weighted skip connection. In order to optimize the proposed network architectures, a variety of verification tests were conducted using validation dataset. We used Computer Vision Center-Clinic Database (CVC-ClinicDB) consisting of 612 colonoscopy medical images to evaluate the enhancement of image restoration. The proposed MSFAN can achieve improved PSNR gains as high as 0.25 and 0.24 dB on average compared to DnCNN and DCSC, respectively.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Data Compression Techniques · Image and Signal Denoising Methods · Advanced Image Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (39)
Show source-provided references
1. The JPEG still picture compression standard10.1109/30.125072 ↗
2. Image super-resolution using deep convolutional networks10.1109/TPAMI.2015.2439281 ↗
3. Accurate image super-resolution using very deep convolutional networks
4. Enhanced deep residual networks for single image super-resolution
5. Image super-resolution using dense skip connections
6. Photo-realistic single image super-resolution using a generative adversarial network
7. Residual dense network for image super-resolution
8. Image super-resolution using very deep residual channel attention networks
9. Compression artifacts reduction by a deep convolutional network
10. Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration10.1109/TPAMI.2016.2596743 ↗
11. Beyond a Gaussian denoiser: Residual learning of deep cnn for image denoising10.1109/TIP.2017.2662206 ↗
12. DMCNN: Dual-domain multi-scale convolutional neural network for compression artifacts removal
13. Jpeg artifacts reduction via deep convolutional sparse coding
14. A convolutional neural network approach for post-processing in HEVC intra coding
15. A new HEVC in-loop filter based on multi-channel long-short-term dependency residual networks
16. A switchable deep learning approach for in-loop filtering in video coding
17. S. Anwar, M. Tahir, C. Li, A. Mian, F. S. Khan et al., “Image colorization: A survey and dataset,” arXiv preprint, 2020. https://arxiv.org/abs/2008.10774.
18. Popwicz · Color Image and Video Enhancement · 2015 · 1 · 34510.1007/978-3-319-09363-5_12 ↗
19. A comprehensive benchmark for single image compression artifact reduction10.1109/TIP.2020.3007828 ↗
20. Deep learning on image denoising: An overview10.1016/j.neunet.2020.07.025 ↗
21. Deep residual learning for image recognition
22. Densely connected convolutional networks
23. Long short term memory recurrent neural network classifier for intrusion detection
24. I. Sutskever, O. Vinyals and Q. V. Le, “Sequence to sequence learning with neural networks,” arXiv preprint, 2014. https://arxiv.org/abs/1409.3215.
25. F. Yu and V. Koltun, “Multi-scale context aggregation by dilated convolutions,” arXiv preprint, 2015. https://arxiv.org/abs/1511.07122.
26. Squeeze-and-excitation networks
27. Batch normalization: accelerating deep network training by reducing internal covariate shift
28. Efficient color artifact removal algorithm based on high-efficiency video coding (HEVC) for high-dynamic range video sequences10.1109/ACCESS.2020.2984012 ↗
29. Overview of the high efficiency video coding (HEVC) standard10.1109/TCSVT.2012.2221191 ↗
30. Deepgesture: Deep learning-based gesture recognition scheme using motion sensors10.1016/j.displa.2018.08.001 ↗
31. Efficient facial expression recognition algorithm based on hierarchical deep neural network structure10.1109/ACCESS.2019.2907327 ↗
32. Deep joint spatiotemporal network (DJSTN) for efficient facial expression recognition10.3390/s20071936 ↗
33. Fight detection in hockey videos using deep network
34. Deep BLSTM-gRU model for monthly rainfall prediction: A case study of simtokha, Bhutan10.3390/rs12193174 ↗
35. D. P. Kingma and K. Ba, “Adam: A method for stochastic optimization,” arXiv preprint, 2014. https://arxiv.org/abs/1412.6980.
36. A. M. Saxe, J. L. McClelland, L. James and S. Ganguli, “Exact solutions to the nonlinear dynamics of learning in deep linear neural networks,” arXiv preprint, 2013. https://arxiv.org/abs/1312.6120.
37. WM-Dova maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians10.1016/j.compmedimag.2015.02.007 ↗
38. Image quality assessment: From error visibility to structural similarity10.1109/TIP.2003.819861 ↗
39. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics