Predicting IHC staining classes of NF1 using features in the hematoxylin channel
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 propos...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | Journal of Pathology Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S215335392300010X |
| _version_ | 1811168484859576320 |
|---|---|
| author | Wei Zhang Mei Yee Koh Deepika Sirohi Jian Ying Ben J. Brintz Beatrice S. Knudsen |
| author_facet | Wei Zhang Mei Yee Koh Deepika Sirohi Jian Ying Ben J. Brintz Beatrice S. Knudsen |
| author_sort | Wei Zhang |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-10T16:26:59Z |
| format | Article |
| id | doaj.art-86f9ea1e2a0f4627a1b52e1e3235c35a |
| institution | Directory Open Access Journal |
| issn | 2153-3539 |
| language | English |
| last_indexed | 2024-04-10T16:26:59Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Pathology Informatics |
| spelling | doaj.art-86f9ea1e2a0f4627a1b52e1e3235c35a2023-02-09T04:14:00ZengElsevierJournal of Pathology Informatics2153-35392023-01-0114100196Predicting IHC staining classes of NF1 using features in the hematoxylin channelWei Zhang0Mei Yee Koh1Deepika Sirohi2Jian Ying3Ben J. Brintz4Beatrice S. Knudsen5Huntsman Cancer Institute BMP core, University of Utah, Salt Lake City, Utah 84108, USA; Department of Pathology, University of Utah, Salt Lake City, Utah 84108, USA; Corresponding authors.Department of Pharmacology and Toxicology, University of Utah, Salt Lake City, Utah 84108, USADepartment of Pathology, University of Utah, Salt Lake City, Utah 84108, USADepartment of Internal Medicine, University of Utah, Salt Lake City, Utah 84108, USADepartment of Internal Medicine, University of Utah, Salt Lake City, Utah 84108, USAHuntsman Cancer Institute BMP core, University of Utah, Salt Lake City, Utah 84108, USA; Department of Pathology, University of Utah, Salt Lake City, Utah 84108, USA; Corresponding authors.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.http://www.sciencedirect.com/science/article/pii/S215335392300010XQuPathCytoMapKidney cancerPrediction |
| spellingShingle | Wei Zhang Mei Yee Koh Deepika Sirohi Jian Ying Ben J. Brintz Beatrice S. Knudsen Predicting IHC staining classes of NF1 using features in the hematoxylin channel Journal of Pathology Informatics QuPath CytoMap Kidney cancer Prediction |
| title | Predicting IHC staining classes of NF1 using features in the hematoxylin channel |
| title_full | Predicting IHC staining classes of NF1 using features in the hematoxylin channel |
| title_fullStr | Predicting IHC staining classes of NF1 using features in the hematoxylin channel |
| title_full_unstemmed | Predicting IHC staining classes of NF1 using features in the hematoxylin channel |
| title_short | Predicting IHC staining classes of NF1 using features in the hematoxylin channel |
| title_sort | predicting ihc staining classes of nf1 using features in the hematoxylin channel |
| topic | QuPath CytoMap Kidney cancer Prediction |
| url | http://www.sciencedirect.com/science/article/pii/S215335392300010X |
| work_keys_str_mv | AT weizhang predictingihcstainingclassesofnf1usingfeaturesinthehematoxylinchannel AT meiyeekoh predictingihcstainingclassesofnf1usingfeaturesinthehematoxylinchannel AT deepikasirohi predictingihcstainingclassesofnf1usingfeaturesinthehematoxylinchannel AT jianying predictingihcstainingclassesofnf1usingfeaturesinthehematoxylinchannel AT benjbrintz predictingihcstainingclassesofnf1usingfeaturesinthehematoxylinchannel AT beatricesknudsen predictingihcstainingclassesofnf1usingfeaturesinthehematoxylinchannel |