文件列表:

Ejemplo_BKSVD_v2.m (2136, 2022-02-18)
Example_norm.png (987519, 2022-02-18)
FastLaplace.m (8298, 2022-02-18)
FastLaplaceAddSigmaIn.m (5936, 2022-02-18)
MB_BKSVD4SD.m (4138, 2022-02-18)
MB_EBKSVD4SD.m (3210, 2022-02-18)
MI_MB_BKSVD4SD.m (824, 2022-02-18)
MI_MB_EBKSVD4SD.m (825, 2022-02-18)
MI_MB_EBKSVD4SD_old.m (4946, 2022-02-18)
MLandini.mat (246, 2022-02-18)
Normaliza.m (422, 2022-02-18)
PintaCT.m (962, 2022-02-18)
PintaMatriz.m (206, 2022-02-18)
Reference.jpg (46735, 2022-02-18)
SaveResults.m (969, 2022-02-18)
col2img.m (392, 2022-02-18)
computeAdjustMetrics.m (872, 2022-02-18)
computeRMSE.m (373, 2022-02-18)
dictNM.m (81, 2022-02-18)
directDeconvolve.m (143, 2022-02-18)
hist1.Results.mat (289903, 2022-02-18)
hist1.jpg (8590, 2022-02-18)
hist1_M.mat (225, 2022-02-18)
hist2.Results.mat (329270, 2022-02-18)
hist2.jpg (10075, 2022-02-18)
hist2_M.mat (225, 2022-02-18)
hist3.Results.mat (294639, 2022-02-18)
hist3.jpg (8550, 2022-02-18)
hist3_M.mat (225, 2022-02-18)
img2col.m (284, 2022-02-18)
od2rgb.m (55, 2022-02-18)
rgb2od.m (82, 2022-02-18)
saturate.m (137, 2022-02-18)
sparseRecovery.m (557, 2022-02-18)
spdiag.m (732, 2022-02-18)
ssim_index.m (5715, 2022-02-18)

# BKSVD Bayesian K-SVD for H and E blind color deconvolution. Applications to stain normalization, data augmentation and cancer classification https://doi.org/10.1016/j.compmedimag.2022.102048 Fernando Perez-Bueno, Juan G. Serra, Miguel Vega, Javier Mateos, Rafael Molina, Aggelos K. Katsaggelos, Bayesian K-SVD for H and E blind color deconvolution. Applications to stain normalization, data augmentation and cancer classification, Computerized Medical Imaging and Graphics, 2022, 102048, ISSN 0895-6111, https://doi.org/10.1016/j.compmedimag.2022.102048. (https://www.sciencedirect.com/science/article/pii/S0895611122000210) ## Abstract Stain variation between images is a main issue in the analysis of histological images. These color variations, produced by different staining protocols and scanners in each laboratory, hamper the performance of computer-aided diagnosis (CAD) systems that are usually unable to generalize to unseen color distributions. Blind color deconvolution techniques separate multi-stained images into single stained bands that can then be used to reduce the generalization error of CAD systems through stain color normalization and/or stain color augmentation. In this work, we present a Bayesian modeling and inference blind color deconvolution framework based on the K-Singular Value Decomposition algorithm. Two possible inference procedures, variational and empirical Bayes are presented. Both provide the automatic estimation of the stain color matrix, stain concentrations and all model parameters. The proposed framework is tested on stain separation, image normalization, stain color augmentation, and classification problems. Keywords: Bayesian modelling; Histological images; Blind Color Deconvolution; Stain Normalization ## Citation @article{PEREZBUENO2022102048, title = {Bayesian K-SVD for H and E blind color deconvolution. Applications to stain normalization, data augmentation and cancer classification}, journal = {Computerized Medical Imaging and Graphics}, pages = {102048}, year = {2022}, issn = {0895-6111}, doi = {https://doi.org/10.1016/j.compmedimag.2022.102048}, url = {https://www.sciencedirect.com/science/article/pii/S0895611122000210}, author = {Fernando Perez-Bueno and Juan G. Serra and Miguel Vega and Javier Mateos and Rafael Molina and Aggelos K. Katsaggelos}, keywords = {Bayesian modelling, Histological images, Blind Color Deconvolution, Stain Normalization} }

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：