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/

Zendy Plus

Presents the zaia usage as premium feature

ZAIA

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the access of premium content as premium feature

Premium Content

Zendy Tools

Zendy Open

Lacunes of presumed vascular origin (lacunes) are associated with anincreased risk of stroke, gait impairment, and dementia and are a primaryimaging feature of the small vessel disease. Quantification of lacunes may beof great importance to elucidate the mechanisms behind neuro-degenerativedisorders and is recommended as part of study standards for small vesseldisease research. However, due to the different appearance of lacunes invarious brain regions and the existence of other similar-looking structures,such as perivascular spaces, manual annotation is a difficult, elaborative andsubjective task, which can potentially be greatly improved by reliable andconsistent computer-aided detection (CAD) routines.  In this paper, we propose an automated two-stage method using deepconvolutional neural networks (CNN). We show that this method has goodperformance and can considerably benefit readers. We first use a fullyconvolutional neural network to detect initial candidates. In the second step,we employ a 3D CNN as a false positive reduction tool. As the locationinformation is important to the analysis of candidate structures, we furtherequip the network with contextual information using multi-scale analysis andintegration of explicit location features. We trained, validated and tested ournetworks on a large dataset of 1075 cases obtained from two different studies.Subsequently, we conducted an observer study with four trained observers andcompared our method with them using a free-response operating characteristicanalysis. Shown on a test set of 111 cases, the resulting CAD system exhibitsperformance similar to the trained human observers and achieves a sensitivityof 0.974 with 0.13 false positives per slice. A feasibility study also showedthat a trained human observer would considerably benefit once aided by the CADsystem.

Deep Multi-scale Location-aware 3D Convolutional Neural Networks for Automated Detection of Lacunes of Presumed Vascular Origin