Deep learning approach for accurate prostate cancer identification and stratification using combined immunostaining of cytokeratin, p63, and racemase

Prognostic Impact of H19/Cell Adhesion Molecules Circuitry on Prostate Cancer Biopsy

INTRODUCTION

Metastatic prostate cancer (PCa) presents a significant challenge in oncology due to its high mortality rate and the absence of effective biomarkers for predicting patient outcomes. Building on previous research that highlighted the critical role of the long noncoding RNA (lncRNA) H19 and cell adhesion molecules in promoting tumor progression under hypoxia and estrogen stimulation, this study aimed to assess the potential of these components as prognostic biomarkers for PCa at the biopsy stage.

METHODS

This research utilized immunohistochemistry and droplet digital PCR to analyze formalin-fixed paraffin-embedded (FFPE) biopsies, focusing on specific markers within the H19/cell adhesion molecules pathway.

RESULTS

A novel multivariate analysis led to a "BioScore", a composite biomarker score to predict disease progression. This score is based on evaluating five key markers: the expression levels of Hypoxia-Inducible Factor 2 Alpha (HIF-2α), endothelial Nitric Oxide Synthase (eNOS), β4 integrin, E-cadherin transcript (CDH1), and lncRNA H19. The criteria for the "BioScore" involve identifying three out of these five markers, combining elevated levels of HIF-2α, eNOS, β4 integrin, and CDH1 with reduced H19 expression.

CONCLUSIONS

This finding suggests the possibility of identifying, at the time of biopsy, PCa patients at higher risk of metastasis based on dysregulation in the H19/cell adhesion molecules circuitry. This study provides a valuable opportunity for early intervention in managing PCa, potentially contributing to personalized treatment strategies.

SEG-LUS: A novel ultrasound segmentation method for liver and its accessory structures based on muti-head self-attention

Although liver ultrasound (US) is quick and convenient, it presents challenges due to patient variations. Previous research has predominantly focused on computer-aided diagnosis (CAD), particularly for disease analysis. However, characterizing liver US images is complex due to structural diversity and a limited number of samples. Normal liver US images are crucial, especially for standard section diagnosis. This study explicitly addresses Liver US standard sections (LUSS) and involves detailed labeling of eight anatomical structures. We propose SEG-LUS, a US image segmentation model for the liver and its accessory structures. In SEG-LUS, we have adopted the shifted windows feature encoder combined with the cross-attention mechanism to adapt to capturing image information at different scales and resolutions and address context mismatch and sample imbalance in the segmentation task. By introducing the UUF module, we achieve the perfect fusion of shallow and deep information, making the information retained by the network in the feature extraction process more comprehensive. We have improved the Focal Loss to tackle the imbalance of pixel-level distribution. The results show that the SEG-LUS model exhibits significant performance improvement, with mPA, mDice, mIOU, and mASD reaching 85.05%, 82.60%, 74.92%, and 0.31, respectively. Compared with seven state-of-the-art semantic segmentation methods, the mPA improves by 5.32%. SEG-LUS is positioned to serve as a crucial reference for research in computer-aided modeling using liver US images, thereby advancing the field of US medicine research.