MP-MNCA: Morphology-Prior Masked Neighbor Cross-Attention for Efficient Spatial Domain Identification
Abstract
Spatial transcriptomics jointly captures molecular state, tissue morphology, and spatial organization, yet spatial-domain methods are typically compared only at late training checkpoints, obscuring differences in convergence efficiency. We introduce MP-MNCA, a morphology-prior masked neighbor cross-attention framework that preserves the full 3,000 dimensional highly-variable-gene representation while selectively routing molecular information across spatial neighbors, with histological similarity incorporated as a continuous attention prior under a self-supervised masked neighbor-contrastive objective. Across 12 heterogeneous human dorsolateral prefrontal cortex (DLPFC) sections, MP-MNCA is evaluated against established spatial-domain baselines using both convergence trajectories and epoch-wise spatial-domain visualizations. Our results show that MP-MNCA (i) reaches coherent spatial-domain structure in substantially fewer training epochs, as reflected quantitatively by convergence curves and qualitatively by progressive spatial grids, and (ii) maintains strong clustering quality, achieving a mean peak refined ARI of 0.546 versus 0.549 for the strongest baseline (STAIG), while attaining the highest mean refined NMI of 0.657 versus 0.640. Moreover, MP-MNCA outperforms STAIG on 7 of 12 sections in ARI and 11 of 12 in NMI, demonstrating faster convergence without sacrificing spatial-domain quality.
Related
- Feature-aware attention convolutional neural network for efficient pulmonary fibrosis classification from chest CT images with FPGA deployment
- TiLCA-Net: nuclei segmentation and classification in pathological images via task-specialized attention and efficient decoding
- Hybrid feature pyramid attention and capsule network (FpaNet+CapsNet) for enhanced spatial and contextual feature extraction for improved brain tumor segmentation
- Preserving RNA integrity and morphology in whole rat allograft hindlimb sections: an optimized protocol for spatial transcriptomics and immunofluorescence
- FSE-CNN: Fusion of Training-Trajectory Neural Evidence and Spatial-Scale Morphology for Cross-Cohort Brain MRI Classification
BibTeX
@misc{chitra2026mpmnca,
title = {{MP-MNCA: Morphology-Prior Masked Neighbor Cross-Attention for Efficient Spatial Domain Identification}},
author = {Sidharthan Sivacoumar Chitra and Sanjeev Manivannan},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.16212},
eprint = {2610.16212},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.16212},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - MP-MNCA: Morphology-Prior Masked Neighbor Cross-Attention for Efficient Spatial Domain Identification
AU - Sidharthan Sivacoumar Chitra
AU - Sanjeev Manivannan
PY - 2026
DA - 2026/10/12
PB - arXiv
DO - 10.48550/arxiv.2610.16212
UR - https://arxiv.org/abs/2610.16212
AB - Spatial transcriptomics jointly captures molecular state, tissue morphology, and spatial organization, yet spatial-domain methods are typically compared only at late training checkpoints, obscuring differences in convergence efficiency. We introduce MP-MNCA, a morphology-prior masked neighbor cross-attention framework that preserves the full 3,000 dimensional highly-variable-gene representation while selectively routing molecular information across spatial neighbors, with histological similarity incorporated as a continuous attention prior under a self-supervised masked neighbor-contrastive objective. Across 12 heterogeneous human dorsolateral prefrontal cortex (DLPFC) sections, MP-MNCA is evaluated against established spatial-domain baselines using both convergence trajectories and epoch-wise spatial-domain visualizations. Our results show that MP-MNCA (i) reaches coherent spatial-domain structure in substantially fewer training epochs, as reflected quantitatively by convergence curves and qualitatively by progressive spatial grids, and (ii) maintains strong clustering quality, achieving a mean peak refined ARI of 0.546 versus 0.549 for the strongest baseline (STAIG), while attaining the highest mean refined NMI of 0.657 versus 0.640. Moreover, MP-MNCA outperforms STAIG on 7 of 12 sections in ARI and 11 of 12 in NMI, demonstrating faster convergence without sacrificing spatial-domain quality.
ER -