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

Registration of brain scans with pathologies is difficult, yet importantresearch area. The importance of this task motivated researchers to organizethe BraTS-Reg challenge, jointly with IEEE ISBI 2022 and MICCAI 2022conferences. The organizers introduced the task of aligning pre-operative tofollow-up magnetic resonance images of glioma. The main difficulties areconnected with the missing data leading to large, nonrigid, and noninvertibledeformations. In this work, we describe our contributions to both the editionsof the BraTS-Reg challenge. The proposed method is based on combined deeplearning and instance optimization approaches. First, the instance optimizationenriches the state-of-the-art LapIRN method to improve the generalizability andfine-details preservation. Second, an additional objective function weightingis introduced, based on the inverse consistency. The proposed method is fullyunsupervised and exhibits high registration quality and robustness. Thequantitative results on the external validation set are: (i) IEEE ISBI 2022edition: 1.85, and 0.86, (ii) MICCAI 2022 edition: 1.71, and 0.86, in terms ofthe mean of median absolute error and robustness respectively. The methodscored the 1st place during the IEEE ISBI 2022 version of the challenge and the3rd place during the MICCAI 2022. Future work could transfer the inverseconsistency-based weighting directly into the deep network training.

Unsupervised Method for Intra-patient Registration of Brain Magnetic  Resonance Images based on Objective Function Weighting by Inverse  Consistency: Contribution to the BraTS-Reg Challenge