Related Experiment Video
Updated: Nov 22, 2025
Analyses of Proteinuria, Renal Infiltration of Leukocytes, and Renal Deposition of Proteins in Lupus-prone MRL/lpr Mice
Published on: June 8, 2022
Quantifying the effects of biopsy fixation and staining panel design on automatic instance segmentation of immune
Madeleine S Durkee1, Rebecca Abraham2, Junting Ai2
1University of Chicago, Committee on Medical Physics, Department of Radiology, Chicago, Illinois, United States.
Insights
Automated segmentation of immune cells in lupus nephritis (LuN) kidney biopsies is improved using two markers per cell. Sample fixation impacts cell size and segmentation performance, with formalin-fixed, paraffin-embedded (FFPE) samples showing reduced cell dimensions.
Area of Science:
- Nephrology
- Immunology
- Computational Pathology
Background:
- Lupus nephritis (LuN) is a chronic kidney disease with poorly understood cellular mechanisms driving progression to kidney failure.
- Automated instance segmentation of immune cells in immunofluorescence images offers a method to investigate cellular interactions in LuN.
Purpose of the Study:
- To quantify the impact of sample fixation and staining panel design on automated immune cell segmentation and characterization in LuN.
- To evaluate the performance of convolutional neural networks (CNNs) for immune cell segmentation under different experimental conditions.
Main Methods:
- CNNs were trained for multi-class instance segmentation of immune cells in fluorescence confocal images of LuN biopsies.
- Three datasets were utilized to assess the effects of fixation methods (fresh-frozen vs. FFPE) and staining panel design (one-marker vs. two-marker per cell).
Main Results:
- CNNs trained on two-marker panels achieved high sensitivity (0.87-0.91) and specificity (0.82-0.88).
- Training with a one-marker panel resulted in reduced sensitivity (0.72).
- FFPE samples exhibited significantly smaller cell sizes and intercellular distances compared to fresh-frozen samples (p < 0.0001).
Conclusions:
- Sample fixation significantly alters cell size and intercellular distances in LuN biopsies.
- Utilizing two markers per cell for subset identification enhances CNN sensitivity compared to single-marker approaches, improving automated immune cell analysis in LuN.
Significance:
Lupus nephritis (LuN) is a chronic inflammatory kidney disease. The cellular mechanisms by which LuN progresses to kidney failure are poorly characterized. Automated instance segmentation of immune cells in immunofluorescence images of LuN can probe these cellular interactions.
Aim:
Our specific goal is to quantify how sample fixation and staining panel design impact automated instance segmentation and characterization of immune cells.
Approach:
Convolutional neural networks (CNNs) were trained to segment immune cells in fluorescence confocal images of LuN biopsies. Three datasets were used to probe the effects of fixation methods on cell features and the effects of one-marker versus two-marker per cell staining panels on CNN performance.
Results:
Networks trained for multi-class instance segmentation on fresh-frozen and formalin-fixed, paraffin-embedded (FFPE) samples stained with a two-marker panel had sensitivities of 0.87 and 0.91 and specificities of 0.82 and 0.88, respectively. Training on samples with a one-marker panel reduced sensitivity (0.72). Cell size and intercellular distances were significantly smaller in FFPE samples compared to fresh frozen (Kolmogorov-Smirnov, p ≪ 0.0001).
Conclusions:
Fixation method significantly reduces cell size and intercellular distances in LuN biopsies. The use of two markers to identify cell subsets showed improved CNN sensitivity relative to using a single marker.
