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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Quantitative medical image computing (radiomics) has been widely applied tobuild prediction models from medical images. However, overfitting is asignificant issue in conventional radiomics, where a large number of radiomicfeatures are directly used to train and test models that predict genotypes orclinical outcomes. In order to tackle this problem, we propose an unsupervisedlearning pipeline composed of an autoencoder for representation learning ofradiomic features and a Gaussian mixture model based on minimum message lengthcriterion for clustering. By incorporating probabilistic modeling, diseaseheterogeneity has been taken into account. The performance of the proposedpipeline was evaluated on an institutional MRI cohort of 108 patients withcolorectal cancer liver metastases. Our approach is capable of automaticallyselecting the optimal number of clusters and assigns patients into clusters(imaging subtypes) with significantly different survival rates. Our methodoutperforms other unsupervised clustering methods that have been used forradiomics analysis and has comparable performance to a state-of-the-art imagingbiomarker.

Unsupervised Clustering of Quantitative Imaging Phenotypes using Autoencoder and Gaussian Mixture Model