English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Multimodal image registration has many applications in diagnostic medicalimaging and image-guided interventions, such as Transcatheter ArterialChemoembolization (TACE) of liver cancer guided by intraprocedural CBCT andpre-operative MR. The ability to register peri-procedurally acquired diagnosticimages into the intraprocedural environment can potentially improve theintra-procedural tumor targeting, which will significantly improve therapeuticoutcomes. However, the intra-procedural CBCT often suffers from suboptimalimage quality due to lack of signal calibration for Hounsfield unit, limitedFOV, and motion/metal artifacts. These non-ideal conditions make standardintensity-based multimodal registration methods infeasible to generate correcttransformation across modalities. While registration based on anatomicstructures, such as segmentation or landmarks, provides an efficientalternative, such anatomic structure information is not always available. Onecan train a deep learning-based anatomy extractor, but it requires large-scalemanual annotations on specific modalities, which are often extremelytime-consuming to obtain and require expert radiological readers. To tacklethese issues, we leverage annotated datasets already existing in a sourcemodality and propose an anatomy-preserving domain adaptation to segmentationnetwork (APA2Seg-Net) for learning segmentation without target modality groundtruth. The segmenters are then integrated into our anatomy-guided multimodalregistration based on the robust point matching machine. Our experimentalresults on in-house TACE patient data demonstrated that our APA2Seg-Net cangenerate robust CBCT and MR liver segmentation, and the anatomy-guidedregistration framework with these segmenters can provide high-qualitymultimodal registrations. Our code is available athttps://github.com/zhou/APA2Seg-Net.

Anatomy-guided Multimodal Registration by Learning Segmentation without  Ground Truth: Application to Intraprocedural CBCT/MR Liver Segmentation and  Registration