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/

Zendy Plus

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

Zendy Tools

Zendy Open

Bi-parametric magnetic resonance imaging (bpMRI) has become a pivotalmodality in the detection and diagnosis of clinically significant prostatecancer (csPCa). Developing AI-based systems to identify csPCa using bpMRI cantransform PCa management by improving efficiency and cost-effectiveness.However, current state-of-the-art methods using convolutional neural networks(CNNs) are limited in learning in-plane and three-dimensional spatialinformation from anisotropic images. Their performances also depend on theavailability of large, diverse, and well-annotated bpMRI datasets. We propose aZonal-aware Self-supervised Mesh Network (Z-SSMNet) that adaptively integratesmulti-dimensional (2D/2.5D/3D) convolutions to learn dense intra-sliceinformation and sparse inter-slice information of the anisotropic bpMRI in abalanced manner. A self-supervised learning (SSL) technique is proposed topre-train our network using large-scale unlabeled data to learn the appearance,texture, and structure semantics of bpMRI. It aims to capture both intra-sliceand inter-slice information during the pre-training stage. Furthermore, weconstrained our network to focus on the zonal anatomical regions to furtherimprove the detection and diagnosis capability of csPCa. We conducted extensiveexperiments on the PI-CAI dataset comprising 10000+ multi-center andmulti-scanner data. Our Z-SSMNet excelled in both lesion-level detection (APscore of 0.633) and patient-level diagnosis (AUROC score of 0.881), securingthe top position in the Open Development Phase of the PI-CAI challenge andmaintained strong performance, achieving an AP score of 0.690 and an AUROCscore of 0.909, and securing the second-place ranking in the Closed TestingPhase.

Z-SSMNet: Zonal-aware Self-supervised Mesh Network for Prostate Cancer Detection and Diagnosis with Bi-parametric MRI