Summary of Single-shot Reconstruction Of Three-dimensional Morphology Of Biological Cells in Digital Holographic Microscopy Using a Physics-driven Neural Network, by Jihwan Kim et al.
Single-shot reconstruction of three-dimensional morphology of biological cells in digital holographic microscopy using a physics-driven neural network
by Jihwan Kim, Youngdo Kim, Hyo Seung Lee, Eunseok Seo, Sang Joon Lee
First submitted to arxiv on: 30 Sep 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG); Optics (physics.optics); Quantitative Methods (q-bio.QM)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed MorpHoloNet model integrates physics-driven and coordinate-based neural networks to reconstruct 3D morphology from a single-shot hologram using digital in-line holographic microscopy (DIHM). The model simulates the optical diffraction of coherent light through a 3D phase shift distribution, minimizing the loss between simulated and input holograms. Compared to existing DIHM methods, MorpHoloNet enables direct reconstruction without requiring multiple phase-shifted holograms or angle scanning. The performance is validated by reconstructing 3D morphologies and refractive index distributions from synthetic and experimental holograms of ellipsoids and biological cells. MorpHoloNet also reconstructs spatiotemporal variations in 3D translational and rotational behaviors and morphological deformations of biological cells from consecutive single-shot holograms. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary MorpHoloNet is a new way to make 3D images of tiny living things like cells using just one special kind of camera called digital in-line holographic microscopy (DIHM). Right now, it’s hard to get good 3D pictures of these small things because the cameras can’t capture all the details. MorpHoloNet is a computer program that uses math and science to create better images from single shots taken with DIHM. This means we don’t need to take multiple pictures or use special techniques to get the best results. The new way works so well that it can even show how cells move and change shape over time. |
Keywords
» Artificial intelligence » Spatiotemporal
