Hybrid Multi-Dimensional MRI Prostate Cancer Detection via Hadamard Network-Based Bias Correction and Residual Networks

2026-04-18

AI Summary

This study addresses the challenges of intensity inhomogeneity caused by bias fields in multiparametric MRI (mp-MRI) for prostate cancer and the limited performance of existing AI approaches. To this end, the authors propose HBR-Net-18, a two-stage framework: first, a novel Hadamard U-Net—adapted for the first time to mp-MRI—is employed to correct bias fields across six parametric maps; second, lesion regions are classified using a ResNet-18 architecture that integrates both 2D and 3D inter-slice contextual information. By incorporating physically informed autoencoder-generated parametric maps, a large overlapping patch strategy, and multidimensional spatial context modeling, the method achieves a favorable balance between sensitivity and specificity, significantly outperforming conventional radiomics and baseline CNN models.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Magnetic Resonance Imaging (MRI) is vital for prostate cancer (PCa) diagnosis. While advanced techniques such as Hybrid Multi-dimensional MRI (HM-MRI) have enhanced diagnostic capabilities, the significant need remains for robust, automated Artificial Intelligence (AI)-based detection methods. In this study, we combine quantitative HM-MRI of tissue composition with an AI-based neural network. We propose the Hadamard-Bias Network plus ResNet18 (HBR-Net-18), a two-stage AI framework for PCa detection. In the first stage, a Hadamard U-Net-based algorithm suppresses intensity inhomogeneities (bias fields) across six parametric HM-MRI maps generated via a Physics-Informed Autoencoder (PIA). In the second stage, a Residual Network (ResNet-18) performs patch-level classification. The framework utilizes overlapping 11-by-11 patches, incorporating both 2D intra-slice and 3D inter-slice (adjacent-slice) information to improve spatial consistency. Our experimental results demonstrate that HB-Net achieves balanced sensitivity and specificity, significantly outperforming conventional radiomics-based approaches and baseline CNN models, highlighting its potential for clinical deployment.

Problem

• prostate cancer
• Hybrid Multi-dimensional MRI
• bias correction
• AI-based detection
• intensity inhomogeneity

Innovation

• Hadamard U-Net
• Hybrid Multi-dimensional MRI
• Bias Field Correction
• ResNet-18
• Physics-Informed Autoencoder