Comparative Analysis of Stain-Free Fourier Ptychographic Microscopy and Traditional Histopathological Light Microscopy in Renal Membranous Nephropathy
Valentino, M.; Bianco, V.; D'Ambrosio, G.; Paulli, M.; Smaldone, G.; Brancato, V.; Miccio, L.; Salvatore, M.; Gambacorta, M.; Ferraro, P.
Show abstract
BackgroundHistology remains a cornerstone in the diagnosis and prognosis of renal diseases, with histopathological analysis of kidney tissue being crucial for understanding renal pathophysiology. The availability of multiple stained sections is essential for conducting a comprehensive histopathological analysis and achieving an accurate diagnosis. Recently, Fourier Ptychographic Microscopy (FPM) earned a spot among the most promising microscopy techniques. The ability to provide high-resolution, quantitative phase-contrast images over a wide area, particularly in a stain-free mode, makes FPM highly appealing to experts in histopathology. Since renal pathologies are characterized by subtle morphological changes encoded in tissue slides, phase maps obtained using FPM are well-suited for providing detailed, high-contrast images of tissue structures. Thus, FPM provides a quantitative imaging tool that can be descriptive of the sample and/or expressive of the disease. MethodsIn this study, we explore FPM capability to image pathological kidney tissue, enabling pathologists to select regions of interest within the intricate architecture of renal tissue and zoom in to observe minute submicron structures, ranging from overall tissue organization and glomeruli distribution to individual cell membranes. Attention is focused on membranous glomerulonephritis since it is a nephropathy highly dependent on histological examination. ResultsThe comparative analysis between FPM and traditional light microscopy showed a difference in thickness of glomerular basal membranes between healthy kidney tissues and those affected by membranous glomerulonephritis (MG). Moreover, the results reported in our investigation revealed better glomerular membranes contrast in FPM images with respect to the H&E-stained images. ConclusionsOur study shows the broad potential of FPM in characterizing hallmarks of MG disease even in stain-free tissue slides.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Renal tubular function and morphology revealed in kidney without labeling using three-dimensional dynamic optical coherence tomography 95%
- CluSA: Clustering-based Spatial Analysis framework through Graph Neural Network for Chronic Kidney Disease Prediction using Histopathology Images 95%
- Method for in vivo assessment of cancer tissue inhomogeneity and accurate histology-like morphological segmentation based on Optical Coherence Elastography 94%
Similar papers in this journal
- Photonic chip-based multimodal super-resolution microscopy for histopathological assessment of cryopreserved tissue sections 92%
- GANscan: continuous scanning microscopy using deep learning deblurring 92%
- Rapid label-free identification of pathogenic bacteria species from a minute quantity 1 exploiting three-dimensional quantitative phase imaging and artificial neural network 92%
Similar papers in this journal
- One-Shot phase-recovery using a Cellphone RGB Camera on a Jamin-Lebedeff Microscope 94%
- Probabilistic Optically-Selective Single-molecule Imaging Based Localization Encoded (POSSIBLE) Microscopy for Ultra-superresolution Imaging of Dendra2-HA transfected NIH3T3 cells 94%
- FalseColor-Python: a rapid intensity-leveling and digital-staining package for fluorescence-based slide-free digital pathology 94%
Similar papers in this journal
- Creating virtual H&E images using samples imaged on a commercial CODEX platform 92%
- Using an Anomaly Detection Approach for the Segmentation of Colorectal Cancer Tumors in Whole Slide Images 92%
- Enhancing Liver Fibrosis Measurement: Deep Learning and Uncertainty Analysis Across Multi-Centre Cohorts 91%
Similar papers in this journal
- Automatic colorectal cancer screening using deep-learning on spatial light interference microscopy data 93%
- Two-color live-cell STED nanoscopy by click labeling with cell-permeable fluorophores 91%
- Highly sensitive and multiplexed in situ protein profiling with cleavable fluorescent streptavidin 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.