Affiliation:
1. Anjalai Ammal Mahalingam Engineering College, Thiruvarur, India
Abstract
The DR (digital radiography) images may be obscured due to noise interference, improper exposure, and the excessive thickness of human tissues, resulting in indistinct edges and reduced contrast. An image-enhancement algorithm based on wavelet multiscale decomposition is proposed to address the shortcomings of existing single-scale image-enhancement algorithms. The proposed algorithm is taking advantage of the interpolation, smoothness and normalization properties. Next a multiscale interpolation wavelet operator is constructed to divide the image into several sub-images from high frequency to low frequency, and to perform different multi-scale wavelet transforms on the detailed image of each channel. So that the most subtle and diagnostically useful information in the image can be effectively enhanced. Moreover, the image will not be over-enhanced and combined with the high contrast sensitivity of the human eye’s visual system in smooth regions, different attenuation coefficients are used for different regions to achieve the purpose of suppressing noise while enhancing details.
Reference20 articles.
1. [1] A. Johnson et al., "Deep learning-based segmentation of brain tumours in MRI scans," Medical Image Analysis, vol. 45, pp. 1-13, 2018, doi: 10.1016/j.media.2018.03.007.
2. [2] A. Sharma and S. Singh, "Computer-aided diagnosis of breast cancer using mammography images and artificial intelligence," Journal of X-Ray Science and Technology, vol. 28, no. 5, pp. 871-887, 2020, doi: 10.3233/XST-190569
3. [3] A. Gupta et al., "Deep learning-based automated detection of COVID-19 from chest CT images," Medical Physics, vol. 48, no. 2, pp. 898-909, 2021, doi: 10.1002/mp 14698.
4. [4] B. Chen et al., "Automatic identification of retinal diseases in OCT images using deep learning," Computers in Biology and Medicine, vol. 103, pp. 124-132, 2018, doi: 10.1016/j.compbiomed.2018.10.005.
5. [5] G. Wang et al., "Deep learning for tumour grading and morphotype prediction in breast cancer," Medical Physics, vol. 44, no. 12, pp. 5810-5820, 2017, doi: 10.1002/mp.12513.