Work

Optical pickup unit-based fluorescence microscope with autofocus and deep learning capabilities

Year: 2024

Type: article

Abstract: An autofocus , cost-effective fluorescence microscope instrument is made using a commercially available Blu-ray disc optical pickup head (OPU). This ABFM consists of the optical path , system control and the operation program. The optical path performs both optical imaging and optical autofocus by using a specially designed dichroscope and the focus error signal (FES) technique integrated in the OPU. Because of the autofocusing function, the fluorescent images captured by ABFM with a resolution of 1.0 µm with a 5X objective lens are obtained. Fluorescence images of human corneal epithelial cell-transformed (HCE-T) cells with fluorophore 4,6-diamino-2-phenyl indole (DAPI) are measured by the ABFM, whose result was comparable to those measured by a Nikon ECLIPSE Ti-S fluorescence microscope and a Leica STELLARIS 5 laser scanning confocal microscope (Leica LSCM). A special deep learning model (Deep Fourier Generative Adversarial Network, DFGAN) was trained to enhance the resolution of the HCE-T, improving the resolution by 21 %. Thus, this ABFM can be used as an alternative to commercial fluorescence microscopes for imaging biological samples in the development of cost-effective, high-performance fluorescence microscopy systems.

Source: Biomedical Analysis

DOI: 10.1016/j.bioana.2024.07.001

Authors: Yuankai Zhao, Siliang Guo, Xiaolu Ma, Lingling Zhang, Xiaochun Li

Institution: Taiyuan University of Technology

Language: English

Topic: Advanced Fluorescence Microscopy Techniques

Subfield: Biophysics

Field: Biochemistry, Genetics and Molecular Biology

Domain: Life Sciences

Open Access status: diamond

Funders: National Natural Science Foundation of China, Shanxi Scholarship Council of China, Natural Science Foundation of Shanxi Province, Taiyuan University of Technology

Awards: G3486055633, G3868668768, G4037059245, G4190247557, G6030201310