Hybrid-View Attention Network for Clinically Significant Prostate Cancer Classification in Transrectal Ultrasound

TL;DR

This paper introduces a hybrid-view attention network that combines CNN and transformer architectures to improve the classification of clinically significant prostate cancer in 3D transrectal ultrasound images, addressing the limitations of ultrasound imaging.

Contribution

The paper presents a novel hybrid-view attention network that leverages intra-view and cross-view attention mechanisms along with adaptive feature fusion for better prostate cancer classification.

Findings

Outperforms existing methods on in-house dataset

Effective integration of transverse and sagittal views

Demonstrates significant ablation study improvements

Abstract

Prostate cancer (PCa) is a leading cause of cancer-related mortality in men, and accurate identification of clinically significant PCa (csPCa) is critical for timely intervention. Transrectal ultrasound (TRUS) is widely used for prostate biopsy; however, its low contrast and anisotropic spatial resolution pose diagnostic challenges. To address these limitations, we propose a novel hybrid-view attention (HVA) network for csPCa classification in 3D TRUS that leverages complementary information from transverse and sagittal views. Our approach integrates a CNN-transformer hybrid architecture, where convolutional layers extract fine-grained local features and transformer-based HVA models global dependencies. Specifically, the HVA comprises intra-view attention to refine features within a single view and cross-view attention to incorporate complementary information across views. Furthermore, a hybrid-view adaptive fusion module dynamically aggregates features along both channel and spatial dimensions, enhancing the overall representation. Experiments are conducted on an in-house dataset containing 590 subjects who underwent prostate biopsy. Comparative and ablation results prove the efficacy of our method. The code is available at https://github.com/mock1ngbrd/HVAN.