mlsanityData to 14 Oct 2026

Reconstruction of three-dimensional shapes of normal and disease-related erythrocytes from partial observations using multi-fidelity neural networks

arXiv 2511.14962 ↗First posted 18 Nov 2025physics.comp-ph cs.LG eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

Reconstruction of 3D erythrocyte or red blood cell (RBC) morphology from partial observations, such as microscope images, is essential for understanding the physiology of RBC aging and the pathology of various RBC disorders. In this study, we propose a multi-fidelity neural network (MFNN) approach to fuse high-fidelity cross-sections of an RBC, with a morphologically similar low-fidelity reference 3D RBC shape to recover its full 3D surface. The MFNN predictor combines a convolutional neural network trained on low-fidelity reference RBC data with a feedforward neural network that captures nonlinear morphological correlations, and augments training with surface area and volume constraints for regularization in the low-fidelity branch. This approach is theoretically grounded by a topological homeomorphism between a sphere and 3D RBC surfaces, with training data generated by dissipative particle dynamics simulations of stomatocyte-discocyte-echinocyte transformation. Benchmarking across diverse RBC shapes observed in normal and aged populations, our results show that the MFNN predictor can reconstruct complex RBC morphologies with over 95% coordinate accuracy when provided with at least two orthogonal cross-sections. It is observed that informative oblique cross-sections intersecting spicule tips of echinocytes improve both local and global feature reconstruction, highlighting the value of feature-aware sampling. Our study further evaluates the influence of sampling strategies, shape dissimilarity, and noise, showing enhanced robustness under physically constrained training. Altogether, these results demonstrate the capability of MFNN to reconstruct the 3D shape of normal and aged RBCs from partial cross-sections as observed in conventional microscope images, which could facilitate the quantitative analysis of RBC morphological parameters in normal and disease-related RBC samples.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 81 references that are in the map. First posted on arXiv 18 Nov 2025.

Builds on

10 of 81 references.

References · 10

  1. 2018Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problemscited by 147
  2. 2020Multi-fidelity Bayesian Neural Networks: Algorithms and Applicationscited by 59
  3. 2022A Diffusion Model Predicts 3D Shapes from 2D Microscopy Imagescited by 24
  4. 2022Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D Reconstructioncited by 14
  5. 2023Euler Characteristic Transform Based Topological Loss for Reconstructing 3D Images from Single 2D Slicescited by 6
  6. 2022Physics-informed ConvNet: Learning Physical Field from a Shallow Neural Networkcited by 5
  7. 2024Identifying heterogeneous micromechanical properties of biological tissues via physics-informed neural networkscited by 5
  8. 2017OpenRBC: A Fast Simulator of Red Blood Cells at Protein Resolutioncited by 2
  9. 2024Single-shot reconstruction of three-dimensional morphology of biological cells in digital holographic microscopy using a physics-driven neural networkcited by 1
  10. 2025Automatic Classification of Circulating Blood Cell Clusters based on Multi-channel Flow Cytometry Imagingcited by 1

Built on by

Not cited yet.