Improving Neuropathological Reconstruction Fidelity via AI Slice Imputation

2026-01-31

AI Summary

This study addresses the challenge of degraded anatomical fidelity in three-dimensional brain reconstructions from histological sections under high anisotropy—such as with thick slices—which often results in either overly coarse or excessively smoothed structures. To overcome this, the authors propose a computationally efficient deep learning-based super-resolution method that performs slice interpolation on anisotropic reconstructions to produce anatomically consistent isotropic volumes. The model is trained on domain-randomized synthetic data, enabling it to generalize across diverse sectioning protocols without requiring real annotated data and to maintain robustness even with large slice thicknesses. Experimental results demonstrate that the interpolated volumes significantly improve Dice scores for automated segmentation—particularly in cortical and white matter regions—and yield superior performance in cortical surface reconstruction and registration to MRI atlases.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Learning with Manifolds
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Neuropathological analyses benefit from spatially precise volumetric reconstructions that enhance anatomical delineation and improve morphometric accuracy. Our prior work has shown the feasibility of reconstructing 3D brain volumes from 2D dissection photographs. However these outputs sometimes exhibit coarse, overly smooth reconstructions of structures, especially under high anisotropy (i.e., reconstructions from thick slabs). Here, we introduce a computationally efficient super-resolution step that imputes slices to generate anatomically consistent isotropic volumes from anisotropic 3D reconstructions of dissection photographs. By training on domain-randomized synthetic data, we ensure that our method generalizes across dissection protocols and remains robust to large slab thicknesses. The imputed volumes yield improved automated segmentations, achieving higher Dice scores, particularly in cortical and white matter regions. Validation on surface reconstruction and atlas registration tasks demonstrates more accurate cortical surfaces and MRI registration. By enhancing the resolution and anatomical fidelity of photograph-based reconstructions, our approach strengthens the bridge between neuropathology and neuroimaging. Our method is publicly available at https://surfer.nmr.mgh.harvard.edu/fswiki/mri_3d_photo_recon

Problem

• neuropathological reconstruction
• anisotropic volumes
• slice imputation
• anatomical fidelity
• 3D brain reconstruction

Innovation

• slice imputation
• super-resolution
• anisotropic-to-isotropic reconstruction
• domain-randomized synthetic data
• neuropathological 3D reconstruction