PRISM-Net: Patient-specific reference-guided inter-breast symmetry matching for three-class breast DCE-MRI classification
Year: 2026
Type: preprint
Abstract: Breast DCE-MRI classification of breast sides as no lesion, benign, or malignant is complicated by substantial patient-specific variation in breast anatomy, tissue composition, and physiological enhancement. Although radiologists routinely use the contralateral breast as an internal reference, computational bilateral comparison remains challenging because corresponding contralateral regions are not anatomically identical and bilateral differences are not necessarily pathological. We propose PRISM-Net, a registration-free bilateral framework that treats the contralateral breast as an approximate patient-specific reference. PRISM-Net learns complementary target-appearance and reference-conditioned deviation representations. Adaptive patch-level matching constructs content-dependent contralateral references in a shared feature space without voxel-wise registration, while local-contrast reweighting emphasizes focal deviations over diffuse bilateral mismatch. The resulting deviation features are integrated with intrinsic target-side appearance through residual cross-attention and aggregated across slices for breast-side classification. On ODELIA, PRISM-Net achieved Macro AUC, Micro AUC, and quadratic weighted kappa values of 84.11 ± 2.33, 90.64 ± 1.61, and 60.94 ± 5.64 on the in-distribution test set, and 68.51 ± 4.54, 80.74 ± 2.68, and 43.45 ± 7.10 on the held-out institution, respectively, yielding the highest point estimates among the evaluated methods across the primary metrics. PRISM-Net also demonstrated favorable performance on an independent institutional cohort and background-complexity subsets, while ablation experiments supported the contributions of adaptive reference matching and focal deviation modeling. These findings support patient-specific contralateral reference learning as a clinically grounded strategy for breast DCE-MRI classification under heterogeneous background conditions.
Source: Research Square
Authors: Boya Zhang(Conceptualization, Data curation, Formal analysis, Funding acquisition, Investigation, Methodology, Validation, Writing – original draft), Shuaiwen Zhou(Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Software, Validation, Visualization, Writing – original draft), Di Kong(Conceptualization, Methodology, Supervision, Writing – review & editing), Mingxu Wang(Data curation), Wenbiao Du(Data curation), Yiman Zhong(Data curation), Yuexin Duan(Data curation), Xiawei Yue(Data curation), Liuquan Cheng(Conceptualization, Project administration, Resources, Supervision), Xiru Li(Funding acquisition, Project administration, Resources, Supervision)
Language: English
Topic: MRI in cancer diagnosis
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Keywords: breast cancer classification, cross-attention
Open Access status: green
OpenAlex ID: W7171822292
