Efficient Registration of Pathological Images: A Joint PCA/Image-Reconstruction Approach
This addresses the problem of efficient and accurate image registration for medical imaging with pathologies, but it is incremental as it builds on existing Low-rank/Sparse methods.
The paper tackled the challenge of registering pathological images by proposing an efficient alternative to Low-rank/Sparse decomposition, which captures normal tissue appearance with PCA and avoids blurring through an integrated model for pathology removal and image reconstruction, showing utility on synthetic and BRATS 2015 data.
Registration involving one or more images containing pathologies is challenging, as standard image similarity measures and spatial transforms cannot account for common changes due to pathologies. Low-rank/Sparse (LRS) decomposition removes pathologies prior to registration; however, LRS is memory-demanding and slow, which limits its use on larger data sets. Additionally, LRS blurs normal tissue regions, which may degrade registration performance. This paper proposes an efficient alternative to LRS: (1) normal tissue appearance is captured by principal component analysis (PCA) and (2) blurring is avoided by an integrated model for pathology removal and image reconstruction. Results on synthetic and BRATS 2015 data demonstrate its utility.