PRISM-Net: Patient-specific reference-guided inter-breast symmetry matching for three-class breast DCE-MRI classification

2026-07-29

AI Summary

This study addresses the challenge of patient-specific background interference in three-class classification of breast DCE-MRI, where existing approaches often rely solely on unilateral or lesion-centric analysis and fail to explicitly model spatial correspondences between bilateral breasts. To overcome this limitation, the authors propose PRISM-Net, a registration-free bilateral analysis framework that, for the first time, leverages the contralateral breast as a patient-specific reference. By integrating bilateral feature matching with an asymmetry-aware attention mechanism, PRISM-Net adaptively models inter-breast correspondences to enhance the representation of discriminative asymmetry patterns. Evaluated on the ODELIA dataset, the method achieves a Macro AUC of 84.11±2.33 and a Micro AUC of 90.64±1.61 in in-distribution testing, significantly outperforming baseline models in external multi-institutional evaluations. Ablation studies further confirm the effectiveness of each proposed component.

Abstract

Breast DCE-MRI AI is increasingly being explored for breast-level classification of no-lesion, benign, and malignant findings, beyond conventional lesion-centered diagnosis. Within this broader diagnostic scope, however, patient-specific background variability remains a major source of imaging confounding across classification tasks. Existing approaches predominantly focus on unilateral or lesion-centric analysis, whereas bilateral methods offer limited explicit modeling of spatially adaptive cross-breast correspondence. We propose PRISM-Net, a registration-free bilateral framework that leverages contralateral breast features as patient-specific references for background-aware representation learning. PRISM-Net integrates bilateral feature matching and asymmetry-aware attention to establish adaptive inter-breast correspondence and enhance representations of discriminative asymmetric patterns. On ODELIA, Macro AUC, Micro AUC, and quadratic weighted kappa were $84.11 \pm 2.33$, $90.64 \pm 1.61$, and $60.94 \pm 5.64$ on the in-distribution test set, and $68.51 \pm 4.54$, $80.74 \pm 2.68$, and $43.45 \pm 7.10$ on the held-out institution, respectively, outperforming the evaluated baseline methods across the primary evaluation metrics. PRISM-Net further demonstrated performance on independent institutional and background-complexity evaluations. Ablation experiments revealed that both bilateral relation modeling and asymmetry-aware reweighting contributed to improved classification performance. These findings highlight patient-specific bilateral reference modeling as a clinically grounded strategy for DCE-MRI interpretation, improving asymmetric pattern discrimination through explicit modeling of background complexity.

Problem

• breast DCE-MRI
• inter-breast symmetry
• patient-specific variability
• background confounding
• bilateral correspondence

Innovation

• bilateral symmetry matching
• patient-specific reference
• asymmetry-aware attention
• registration-free framework
• background-aware representation learning