Multimodal medical image registration via common representations learning and differentiable geometric constraints. Issue 6 (1st March 2019)

• Record Type: Journal Article
• Authors: Liu, Cong; Ma, Longhua; Lu, Zheming; Jin, Xiance; Xu, Jingyun
• Is Part Of: Electronics letters. Volume 55:Issue 6(2019)
• Page Start: 316
• Page End: 318
• Publication Date: 2019-03-01
• Subjects: image registration -- medical image processing -- learning (artificial intelligence) -- image representation -- convolutional neural nets -- optimisation -- geometry; multimodal medical image registration -- differentiable geometric constraints -- strong geometric constraints -- image representations -- differentiable spatial transformer -- geometric consensus -- end‐to‐end model optimisation -- plausible representation -- representations learning -- deep network approaches -- semantic space -- convolutional features -- object fragments; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2018.6713
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : Multimodal medical image registration remains a challenging problem when strong appearance variations and imprecise alignment exist in images. Previous deep network approaches cannot handle such a high degree of variability and prohibit the use of strong geometric constraints. The authors introduce a novel deep architecture that not only produces image representations that are well‐suited for this challenging task, but also leverages knowledge of the geometry constraints for robust registration. By enforcing the representations of different modalities living in a common semantic space, they obtain convolutional features tending to respond to object parts consistently across modality. This yields a unique description for all object fragments and allows the end user to know the model's decision process, whereas most existing models remain unclear and difficult to explain. By using the differentiable spatial transformer to compensate transform, they integrate geometric consensus into the cost function to enable end‐to‐end model optimisation which has not yet been exploited before. The authors evaluate their method on a very challenging medical image dataset. Experiments demonstrate that the proposed method provides a plausible representation and outperforms state‐of‐the‐art approaches by a significant margin.