High-resolution hyperspectral pathology images contain fine-grained two-dimensional spatial information and spectral dimensional information, which is of great significance for accurate diagnosis. To this end, we propose a pathological hyperspectral image fusion method based on the space-spectrum cascade differential network. In this method, high-resolution hyperspectral pathological images are reconstructed by cascading spatial-spectral modules. Each space-spectrum module utilizes differential methods to design spatial edge loss and spectral edge loss, which helps constrain and optimize the model in stages. This enables the organic fusion of pathological hyperspectral images and multispectral images. The model experimented on the pathological image dataset, and the four evaluation indexes RMSE, PSNR, ERGAS, and SAM of the fusion images reached 4.593 7, 32.328 0, 4.668 3 and 3.635 4, respectively. These results demonstrate that the fusion method based on the space-spectrum cascade differential network can achieve fine fusion of pathological images with rich details, providing a reference for multispectral image fusion.
DIJ, YINS J, MAS, et al. Multi⁃focus image fusion based on superpixel and guided filter[J]. Journal of Measurement Science and Instrumentation, 2023, 14(3): 290-298.
[2]
SHAHDOOSTIH R, JAVAHERIN.Pansharpening of clustered MS and pan images considering mixed pixels[J].IEEE Geoscience and Remote Sensing Letters, 2017, 14(6): 826-830.
[3]
PANDITV R, BHIWANIR J.Component substitution based fusion of worldview imagery[C]//10th International Conference on Computing, Communication and Networking Technologies, 2019: 1-7.
[4]
VIVONEG, RESTAINOR, LICCIARDIG, et al.Multiresolution analysis and component substitution techniques for hyperspectral pansharpening[C]//IEEE Geoscience and Remote Sensing Symposium, 2014: 2649-2652.
[5]
LUX, ZHANGJ, ZHANGY.An improved non-subsampled contourlet transform-based hybrid pan-sharpening algorithm[C]//IEEE International Geoscience and Remote Sensing Symposium, 2017: 3393-3396.
[6]
LIUJ, WUZ, XIAOL, et al.A truncated matrix decomposition for hyperspectral image super-resolution[J].IEEE Transactions on Image Processing, 2020, 29: 8028-8042.
[7]
AKHTARN, SHAFAITF, MIANA.Sparse spatio-spectral representation for hyperspectral image super-resolution[M].Computer Vision⁃ECCV 2014. Cham: Springer International Publishing, 2014: 63-78.
[8]
DONGW, FUF, SHIG, et al.Hyperspectral image super-resolution via non-negative structured sparse representation[J].IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society, 2016, 25(5): 2337-2352.
[9]
ZAREM, HELFROUSHM S, KAZEMIK, et al.Hyperspectral and multispectral image fusion using coupled non-negative tucker tensor decomposition[J].Remote Sensing, 2021, 13(15): 2930.
[10]
XUY, WUZ, CHANUSSOTJ, et al.Nonlocal coupled tensor CP decomposition for hyperspectral and multispectral image fusion[J].IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(1): 348-362.
[11]
KILMERM E, BRAMANK, HAON, et al.Third-order tensors as operators on matrices: a theoretical and computational framework with applications in imaging[J].SIAM Journal on Matrix Analysis and Applications, 2013, 34(1): 148-172.
[12]
OSELEDETSI V.Tensor-train decomposition[J].SIAM Journal on Scientific Computing, 2011, 33(5): 2295-2317.
[13]
PALSSONF, SVEINSSONJ R, ULFARSSONM O.Multispectral and hyperspectral image fusion using a 3D-convolutional neural network[J].IEEE Geoscience and Remote Sensing Letters, 2017, 14(5): 639-643.
[14]
YUANQ, WEIY, MENGX, et al.A multiscale and multidepth convolutional neural network for remote sensing imagery pan-sharpening[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(3): 978-989.
[15]
LIUX, LIUQ, WANGY.Remote sensing image fusion based on two-stream fusion network[J].Information Fusion, 2020, 55: 1-15.
[16]
XUS, AMIRAO, LIUJ, et al.HAM-MFN: hyperspectral and multispectral image multiscale fusion network with rap loss[J].IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(7): 4618-4628.
[17]
ZHANGX, HUANGW, WANGQ, et al.SSR-NET: spatial-spectral reconstruction network for hyperspectral and multispectral image fusion[J].IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(7): 5953-5965.
[18]
LIUS, LIUS, ZHANGS, et al.SSAU-Net: a spectral-spatial attention-based u-net for hyperspectral image fusion[J].IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5542116.
[19]
RANR, DENGL J, JIANGT X, et al.GuidedNet: a general CNN fusion framework via high-resolution guidance for hyperspectral image super-resolution[J].IEEE Transactions on Cybernetics, 2023, 53(7): 4148-4161.
[20]
HANX H, SHIB, ZHENGY.SSF-CNN: spatial and spectral fusion with cnn for hyperspectral image super-resolution[C]//25th IEEE International Conference on Image Processing, 2018: 2506-2510.