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

Multi-parametric magnetic resonance imaging (mpMRI) plays an increasinglyimportant role in the diagnosis of prostate cancer. Various computer-aideddetection algorithms have been proposed for automated prostate cancer detectionby combining information from various mpMRI data components. However, thereexist other features of mpMRI, including the spatial correlation between voxelsand between-patient heterogeneity in the mpMRI parameters, that have not beenfully explored in the literature but could potentially improve cancer detectionif leveraged appropriately. This paper proposes novel voxel-wise Bayesianclassifiers for prostate cancer that account for the spatial correlation andbetween-patient heterogeneity in mpMRI. Modeling the spatial correlation ischallenging due to the extreme high dimensionality of the data, and we considerthree computationally efficient approaches using Nearest Neighbor GaussianProcess (NNGP), knot-based reduced-rank approximation, and a conditionalautoregressive (CAR) model, respectively. The between-patient heterogeneity isaccounted for by adding a subject-specific random intercept on the mpMRIparameter model. Simulation results show that properly modeling the spatialcorrelation and between-patient heterogeneity improves classification accuracy.Application to in vivo data illustrates that classification is improved byspatial modeling using NNGP and reduced-rank approximation but not the CARmodel, while modeling the between-patient heterogeneity does not furtherimprove our classifier. Among our proposed models, the NNGP-based model isrecommended considering its robust classification accuracy and highcomputational efficiency.

Bayesian Spatial Models for Voxel-wise Prostate Cancer Classification Using Multi-parametric MRI Data