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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The diagnosis of prostate cancer is challenging due to the heterogeneity ofits presentations, leading to the over diagnosis and treatment ofnon-clinically important disease. Accurate diagnosis can directly benefit apatient's quality of life and prognosis. Towards addressing this issue, wepresent a learning model for the automatic identification of prostate cancer.While many prostate cancer studies have adopted Raman spectroscopy approaches,none have utilised the combination of Raman Chemical Imaging (RCI) and otherimaging modalities. This study uses multimodal images formed from stainedDigital Histopathology (DP) and unstained RCI. The approach was developed andtested on a set of 178 clinical samples from 32 patients, containing a range ofnon-cancerous, Gleason grade 3 (G3) and grade 4 (G4) tissue microarray samples.For each histological sample, there is a pathologist labelled DP - RCI imagepair. The hypothesis tested was whether multimodal image models can outperformsingle modality baseline models in terms of diagnostic accuracy. Binarynon-cancer/cancer models and the more challenging G3/G4 differentiation wereinvestigated. Regarding G3/G4 classification, the multimodal approach achieveda sensitivity of 73.8% and specificity of 88.1% while the baseline DP modelshowed a sensitivity and specificity of 54.1% and 84.7% respectively. Themultimodal approach demonstrated a statistically significant 12.7% AUCadvantage over the baseline with a value of 85.8% compared to 73.1%, alsooutperforming models based solely on RCI and median Raman spectra. Featurefusion of DP and RCI does not improve the more trivial task of tumouridentification but does deliver an observed advantage in G3/G4 discrimination.Building on these promising findings, future work could include the acquisitionof larger datasets for enhanced model generalization.

Feature Fusion of Raman Chemical Imaging and Digital Histopathology using Machine Learning for Prostate Cancer Detection