Abstract
Multi-wavelength transmission imaging provides a possibility for early breast cancer detection. However, due to the strong scattering effect of light source in the transmission process of biological tissue, there exist many difficulties in the heterogeneous identification of multi-wavelength images. In this paper, a multi-wavelength images frequency fusion method based on regional variance significance and regional space energy weighting is proposed to improve the accuracy of heterogeneous detection. Firstly, the acquisition experiment of phantom multi-wavelength transmission images is designed. And R\G\B three-channel wavelength images are extracted from multi-wavelength images as an example to realize subsequent image fusion. Secondly, frame accumulation technique and second-order Butterworth filter are used to improve the signal-to-noise ratio of images and suppress the noise of images. Then, after homomorphic filtering, it is found that the same frequency domain of images is connected, which is not conducive to the recognition of heterogeneity in image. In order to break the connectivity of images in the same frequency domain and improve the accuracy of heterogeneous detection, the regional variance significance and the regional space energy weighting fusion strategies are used to reconstruct the low-frequency and high-frequency fusion images respectively. Finally, the heterogeneous detection results of the proposed image fusion method and the state-of-the-art methods in the multi-wavelength image are compared. The experimental results show that compared with the state-of-the-art image fusion methods, the fusion method proposed in this paper can identify the location of heterogeneous region more accurately and significantly improve the contrast between heterogeneous region and normal region in the fusion image. In conclusion, the fusion algorithm not only effectively realizes the recognition of heterogeneity in multi-wavelength images, but also promotes the potential application of multi-wavelength transmission image in early breast cancer detection.
Highlights
Breast cancer, as a high incidence disease, has caused great threat to women’s health and life [1]
Aiming at the problem of ambiguity of heterogeneous region in multi-wavelength transmission images, this paper proposes a fusion method of multi-wavelength images in the frequency domain to realize the detection of heterogeneous region
After homomorphic filtering, it is found that the same frequency domain is connected in the multi-wavelength images, which is not conducive to the detection of heterogeneous region
Summary
As a high incidence disease, has caused great threat to women’s health and life [1]. In order to achieve the heterogeneous region detection in multi-spectral transmission images, a reasonable multi-wavelength images fusion method can be established according to the frequency distribution of each wavelength image to enhance the information degree of heterogeneous region. Yang et al presented a novel multi-wavelength image fusion method based onnonsubsampled contourlet transform (NSCT), which fused the coefficients of low frequency and high frequency sub-bands of image respectively by sum-modified-Laplacian and local Log-Gabor energy [32]. The above-mentioned image fusion methods, whether achieving local signal enhancement in a specific region or a specific frequency domain, are based on the association relationship of reconstructed image data. A multi-wavelength transmission images fusion method in the frequency domain is proposed to realize the detection of heterogeneity.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have