arXiv subjects

Mohammad Soltaninezhad

Publications and source records attributed to Mohammad Soltaninezhad.

3 recordsLinked to original sources

arXiv2026

Physics-Informed Deep Learning Model for Cross-Modality Super-Resolution in Fluorescence Microscopy

Cross-modality image translation offers a route to super-resolution fluorescence microscopy from low-resolution images while reducing phototoxicity and instrumentation demands. However, purely data-driven models can produce visually plausible outputs that are inconsistent with optical image formation. Here, we propose a physics-informed generative adversarial network for confocal-to-STED image translation that incorporates microscope-specific point spread function information into the training objective. Simulated and experimentally measured PSFs were evaluated using a limited paired confocal-STED dataset of TOM20-labeled mitochondria in human primary M2 macrophages acquired across different experimental days. Performance was assessed using reference-based and non-reference-based image-quality metrics, together with complementary frequency- and distribution-sensitive analyses. The no-reference metrics probed physics-relevant image properties, including spatial-frequency content, contrast, and signal-to-noise behavior. PSF-guided models improved structural fidelity, reduced local deviations, and achieved closer agreement with STED references than non-PSF baselines, particularly in frequency-domain analyses. These results demonstrate that optical priors can improve the structural fidelity and physical plausibility of generative microscopy models for cross-modality super-resolution imaging.

cs.CV↗

arXiv2025

Lightweight CycleGAN Models for Cross-Modality Image Transformation and Experimental Quality Assessment in Fluorescence Microscopy

Lightweight deep learning models offer substantial reductions in computational cost and environmental impact, making them crucial for scientific applications. We present a lightweight CycleGAN for modality transfer in fluorescence microscopy (confocal to super-resolution STED/deconvolved STED), addressing the common challenge of unpaired datasets. By replacing the traditional channel-doubling strategy in the U-Net-based generator with a fixed channel approach, we drastically reduce trainable parameters from 41.8 million to approximately nine thousand, achieving superior performance with faster training and lower memory usage. We also introduce the GAN as a diagnostic tool for experimental and labeling quality. When trained on high-quality images, the GAN learns the characteristics of optimal imaging; deviations between its generated outputs and new experimental images can reveal issues such as photobleaching, artifacts, or inaccurate labeling. This establishes the model as a practical tool for validating experimental accuracy and image fidelity in microscopy workflows.

cs.CV↗

arXiv2025

Nano-chemical cell-surface evaluation in photothermal spectroscopic imaging of antimicrobial interaction in model system Bacillus subtilis & vancomycin

The power of photothermal spectroscopic imaging to visualize antimicrobial interaction on the surface of individual bacteria cells has been demonstrated on the model system Bacillus subtilis and vancomycin using mid-infrared photo-induced force microscopy (PiF-IR, also mid-IR PiFM). High-resolution PiF contrasts obtained by merging subsequent PiF-IR scans at two different illumination frequencies revealed chemical details of cell wall destruction after 30 and 60 min incubation with vancomycin with a spatial resolution of $\approx 5$ nm. This approach compensates local intensity variations induced by near-field coupling of the illuminating electric field with nanostructured surfaces, which appear in single-frequency contrasts in photothermal imaging methods, as shown by [Anindo et al., J. Phys. Chem C, 2025, 129, 4517]. Known spectral shifts associated with hydrogen bond formation between vancomycin and the N-acyl-D-Ala4-D-Ala5 termini in the peptidoglycan cell wall have been observed in chemometrics of PiF-IR spectra from treated and untreated Bacillus subtilis harvested after 30 min from the same experiment. Spectral signatures of the vancomyin interaction have been located in the piecrust of a progressing septum with $\approx 10$ nm resolution using PiF contrasts of three selected bands of a PiF-IR hyperspectral scan of an individual Bacillus subtilis cell harvested after 30 min incubation. Our results are complemented by a discussion of imaging artifacts and the influence of parameter settings supporting further development towards standardization in the application of PiF-IR for visualizing the chemical interaction of antibiotics on the surface of microbes with few nanometer resolution.

physics.bio-ph↗