Registration-Enhanced Segmentation Method for Prostate Cancer in Ultrasound Images

2025-02-02

AI Summary

To address the clinical bottlenecks of time-consuming and error-prone manual fusion in prostate cancer ultrasound diagnosis, this paper proposes a registration-guided end-to-end MRI-TRUS image fusion segmentation framework. The method jointly embeds deformable registration and multi-scale feature interaction into a unified segmentation network and incorporates an uncertainty-aware loss function to enable real-time, annotation-free precise tumor localization. By transcending conventional piecemeal multimodal fusion approaches, it significantly improves spatial consistency and robustness. Evaluated on 1,747 clinical cases from Stanford, the framework achieves a Dice coefficient of 0.212—substantially outperforming TRUS-only segmentation (0.117) and naive fusion (0.132), with statistical significance (p < 0.01). These results demonstrate both clinical feasibility and technical advancement in automated, registration-informed multimodal prostate tumor segmentation.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Segmentation
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Prostate cancer is a major cause of cancer-related deaths in men, where early detection greatly improves survival rates. Although MRI-TRUS fusion biopsy offers superior accuracy by combining MRI's detailed visualization with TRUS's real-time guidance, it is a complex and time-intensive procedure that relies heavily on manual annotations, leading to potential errors. To address these challenges, we propose a fully automatic MRI-TRUS fusion-based segmentation method that identifies prostate tumors directly in TRUS images without requiring manual annotations. Unlike traditional multimodal fusion approaches that rely on naive data concatenation, our method integrates a registration-segmentation framework to align and leverage spatial information between MRI and TRUS modalities. This alignment enhances segmentation accuracy and reduces reliance on manual effort. Our approach was validated on a dataset of 1,747 patients from Stanford Hospital, achieving an average Dice coefficient of 0.212, outperforming TRUS-only (0.117) and naive MRI-TRUS fusion (0.132) methods, with significant improvements (p $<$ 0.01). This framework demonstrates the potential for reducing the complexity of prostate cancer diagnosis and provides a flexible architecture applicable to other multimodal medical imaging tasks.

Problem

• Automatic Prostate Cancer Recognition
• Ultrasound Images
• Diagnostic Efficiency

Innovation

• Automatic Recognition
• MRI-TRUS Integration
• Clinical Validation