Skip to main content Skip to main menu
UF Health University of Florida
Computational Microscopy Imaging Laboratory Section of Quantitative Health in the Department of Medicine
join us
Research Overview

Computational Renal Pathology

A schematic diagram showing biological mechanisms.

A Comprehensive Multi-modal Atlas that Defines Spatially Resolved versus Unresolved Repair States and Mechanisms in Human Kidney Disease

We integrated single-cell, spatial transcriptomic, and multi-omic data from over 350 patients and 1.7 million cells, this resource identifies key cellular states, regulatory networks, and candidate therapeutic targets associated with unresolved injury and disease progression.

Illustrations depicting medical and biological concepts. A globe, a test tube with a red liquid, a kidney, and human figures are shown. Below the kidney are two male and two female gender symbols.

Correlating Reference Kidney Morphometry with Patient Demographics & Creatinine

We leverage the unique benefits of panoptic segmentation to perform the largest ever quantitation of reference kidney morphometry. Kidney features were found to vary with age and sex; and glomeruli size may intricately link to creatinine, defying prior notions.

A graphic with a stylized kidney icon and a downward trending arrow. Text reads "Podometrics could predict ESKD development in DN."

PodoCount: Labeled Podocyte Quantification Tool

We have developed PodoCount, an automated tool for podocyte detection and three-dimensional quantification from histologic sections of renal tissue biopsy whole slide images (WSIs) with podocytes labeled using immunohistochemistry labels.

Microscopic view of kidney tissue with highlighted areas. The image shows a magnified section of a glomerulus, a filtering unit in the kidney, surrounded by tubules. Green circles highlight specific cells or structures within the tissue. A red square frames a highly magnified portion of the glomerulus.

PodoSighter: Label-Free Podocyte Detection

We have developed PodoSighter, a cloud-based tool for automated, label-free podocyte detection and three-dimensional quantification from periodic acid-Schiff-stained histologic sections of renal tissue biopsy WSIs.

Microscopic view of a blood vessel surrounded by brain tissue. The vessel is outlined in green, and contains red blood cells. Several circular structures are circled in red within the brain tissue, and one is circled in yellow. The image has a pinkish-purple hue.

Computational Segmentation and Quantification of Interstital Fibrosis, Tubular Atrophy, & Glomerulosclerosis

A machine learning (ML) pipeline is developed to conduct reliable, digital, and automated detection of interstitial fibrosis and tubular atrophy (IFTA).

Five microscopic images of kidney tissue are arranged horizontally. Black arrows point from each image to the corresponding 'G1, G2, G3...' symbolsm all added together to produce single sum. The final image has an equals sign following the plus signs and letter 'G'.

Computational Segmentation and Classification of Diabetic Glomerulosclerosis

We developed a digital pipeline to classify renal biopsies from patients with diabetic nephropathy (DN). We combined traditional image analysis with modern machine learning to efficiently capture important structures, minimize manual effort and supervision, and enforce biologic prior information onto our model.

Microscopic view of kidney tissue with four areas highlighted by green boxes. The tissue is stained pink and contains numerous small, rounded structures resembling coiled tubes and clusters. The highlighted areas show different regions within the kidney's functional units, with varying levels of detail in the tubular structures.

Supervised Computational Detection of Glomeruli in Renal Biopsies

We have developed a supervised computational pipeline to detect glomeruli from digital renal biopsy WSIs.

Microscopic view of kidney tissue stained with hematoxylin and eosin. Several glomeruli, circled in green, appear as tangled, ball-like structures. The surrounding tissue shows a network of tubules and blood vessels. The image is dominated by shades of pink and purple.

Unsupervised Computational Labeling of Glomerular Textural Boundaries in Renal Pathology

We have developed an unsupervised automated quantification of glomerulus from digital renal biopsy WSIs.