Related Experiment Video
Updated: Aug 9, 2025
Multiplexed Fluorescent Immunohistochemical Staining, Imaging, and Analysis in Histological Samples of Lymphoma
Published on: January 9, 2019
Predicting IHC staining classes of NF1 using features in the hematoxylin channel
Wei Zhang1,2, Mei Yee Koh3, Deepika Sirohi2
1Huntsman Cancer Institute BMP core, University of Utah, Salt Lake City, Utah 84108, USA.
Insights
Hematoxylin staining features can predict Neurofibromin (NF1) expression in kidney tissues. This method uses standard hematoxylin and eosin slides, offering broad applicability for IHC label prediction.
Area of Science:
- Digital pathology
- Computational biology
- Cancer research
Background:
- Immunohistochemistry (IHC) traditionally uses antibody staining and hematoxylin counterstaining to identify cell types.
- Hematoxylin staining reveals cell morphology and differs between cell types.
- Predicting IHC labels directly from hematoxylin features is an underexplored area.
Purpose of the Study:
- To investigate the feasibility of predicting Neurofibromin (NF1) IHC labels using only hematoxylin staining features.
- To develop and validate computational models for this prediction task.
- To assess the broad applicability of this approach in digital pathology.
Main Methods:
- Utilized a dataset of 7.2 million cells from benign and kidney cancer tissue microarrays.
- Extracted morphology and hematoxylin (H&M) features using QuPath software.
- Performed clustering analysis with CytoMap and trained XGBoost models for NF1 stain class prediction.
Main Results:
- Achieved prediction accuracies for NF1 staining classes ranging from 70% to 90% across different kidney tissue types.
- Reported precision-recall areas under the curve (PRAUC) for NF1-high, NF1-low, and NF1-negative classes.
- Identified minimum cellular hematoxylin staining intensity as the most important predictive feature.
Conclusions:
- Demonstrated the feasibility of predicting NF1 expression solely from hematoxylin staining features.
- Validated the use of open-source software for this predictive workflow.
- Highlighted the broad applicability of the method for regular H&E and IHC slides.
Abstract:
Immunohistochemistry (IHC) highlights specific cell types in tissues and traditionally involves antibody staining together with a hematoxylin counterstain. The intensity and pattern of hematoxylin staining differs between cell types and reveals morphological characteristics of cells. Here, we propose that features in the hematoxylin stain can be used to predict IHC labels, such as Neurofibromin (encoded by the gene NF1). The dataset consists of 7.2 million cells from benign and kidney cancer cores in a tissue microarray. Morphology and hematoxylin (H&M) features defined within QuPath are subjected to a clustering analysis in CytoMap. H&M features are also used to train 4 different XGBoost models to predict high, low, and negative NF1 stain classes in benign renal tubules, clear cell (ccRCC), papillary (PRCC), and chromophobe (ChRCC) renal carcinoma. The prediction accuracies of NF1 staining classes in benign, ccRCC, ChRCC, and PRCC range between 70% and 90% with areas under the precision recall curve PRAUCNF1-high = 0.82+0.12, PRAUCNF1-low = 0.62+0.25, and PRAUCNF1-negative = 0.83+0.16. The most important feature for predicting the NF1 class involves the minimum cellular hematoxylin staining intensity. Together, these results demonstrate the feasibility to predict NF1 expression solely from features in hematoxylin staining using open source software. Since the hematoxylin features can be obtained from regular H&E and IHC slides, the proposed workflow has broad applicability.
More Related Videos
08:40Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
Published on: April 8, 2016
07:32Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis
Published on: April 12, 2024
