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

Anomaly detection for Magnetic Resonance Images (MRIs) can be solved withunsupervised methods by learning the distribution of healthy images andidentifying anomalies as outliers. In presence of an additional dataset ofunlabelled data containing also anomalies, the task can be framed as asemi-supervised task with negative and unlabelled sample points. Recently, inAlbu et al., 2020, we have proposed a slice-wise semi-supervised method fortumour detection based on the computation of a dissimilarity function in thelatent space of a Variational AutoEncoder, trained on unlabelled data. Thedissimilarity is computed between the encoding of the image and the encoding ofits reconstruction obtained through a different autoencoder trained only onhealthy images. In this paper we present novel and improved results for ourmethod, obtained by training the Variational AutoEncoders on a subset of theHCP and BRATS-2018 datasets and testing on the remaining individuals. We showthat by training the models on higher resolution images and by improving thequality of the reconstructions, we obtain results which are comparable withdifferent baselines, which employ a single VAE trained on healthy individuals.As expected, the performance of our method increases with the size of thethreshold used to determine the presence of an anomaly.

Improved Slice-wise Tumour Detection in Brain MRIs by Computing Dissimilarities between Latent Representations