Search papers, labs, and topics across Lattice.
This study introduces PRISM-Net, a novel registration-free bilateral framework for classifying breast DCE-MRI images into no-lesion, benign, and malignant categories by utilizing contralateral breast features as patient-specific references. By integrating bilateral feature matching and asymmetry-aware attention, PRISM-Net effectively models inter-breast correspondence, addressing the confounding effects of patient-specific background variability. The model achieved impressive performance metrics, including a Macro AUC of 84.11 on the in-distribution test set, significantly outperforming existing methods and demonstrating its robustness across diverse institutional evaluations.
PRISM-Net leverages patient-specific bilateral references to enhance breast DCE-MRI classification, achieving superior performance in distinguishing between benign and malignant findings.
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.
