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

Multiple sclerosis is an inflammatory autoimmune demyelinating disease thatis characterized by lesions in the central nervous system. Typically, magneticresonance imaging (MRI) is used for tracking disease progression. Automaticimage processing methods can be used to segment lesions and derive quantitativelesion parameters. So far, methods have focused on lesion segmentation forindividual MRI scans. However, for monitoring disease progression,\textit{lesion activity} in terms of new and enlarging lesions between two timepoints is a crucial biomarker. For this problem, several classic methods havebeen proposed, e.g., using difference volumes. Despite their success forsingle-volume lesion segmentation, deep learning approaches are still rare forlesion activity segmentation. In this work, convolutional neural networks(CNNs) are studied for lesion activity segmentation from two time points. Forthis task, CNNs are designed and evaluated that combine the information fromtwo points in different ways. In particular, two-path architectures withattention-guided interactions are proposed that enable effective informationexchange between the two time point's processing paths. It is demonstrated thatdeep learning-based methods outperform classic approaches and it is shown thatattention-guided interactions significantly improve performance. Furthermore,the attention modules produce plausible attention maps that have a maskingeffect that suppresses old, irrelevant lesions. A lesion-wise false positiverate of 26.4% is achieved at a true positive rate of 74.2%, which is notsignificantly different from the interrater performance.

Multiple Sclerosis Lesion Activity Segmentation with Attention-Guided Two-Path CNNs