tetano
Editor, Senior Moderator
Sci Rep
. 2024 Apr 16;14(1):8766.
doi: 10.1038/s41598-024-59239-5. Automated quantification of avian influenza virus antigen in different organs
Maria Landmann[SUP] 1 [/SUP], David Scheibner[SUP] 2 [/SUP], Marcel Gischke[SUP] 2 [/SUP], Elsayed M Abdelwhab[SUP] 2 [/SUP], Reiner Ulrich[SUP] 3 [/SUP]
Affiliations
As immunohistochemistry is valuable for determining tissue and cell tropism of avian influenza viruses (AIV), but time-consuming, an artificial intelligence-based workflow was developed to automate the AIV antigen quantification. Organ samples from experimental AIV infections including brain, heart, lung and spleen on one slide, and liver and kidney on another slide were stained for influenza A-matrixprotein and analyzed with QuPath: Random trees algorithms were trained to identify the organs on each slide, followed by threshold-based quantification of the immunoreactive area. The algorithms were trained and tested on two different slide sets, then retrained on both and validated on a third set. Except for the kidney, the best algorithms for organ selection correctly identified the largest proportion of the organ area. For most organs, the immunoreactive area assessed following organ selection was significantly and positively correlated to a manually assessed semiquantitative score. In the validation set, intravenously infected chickens showed a generally higher percentage of immunoreactive area than chickens infected oculonasally. Variability between the slide sets and a similar tissue texture of some organs limited the ability of the algorithms to select certain organs. Generally, suitable correlations of the immunoreactivity data results were achieved, facilitating high-throughput analysis of AIV tissue tropism.
. 2024 Apr 16;14(1):8766.
doi: 10.1038/s41598-024-59239-5. Automated quantification of avian influenza virus antigen in different organs
Maria Landmann[SUP] 1 [/SUP], David Scheibner[SUP] 2 [/SUP], Marcel Gischke[SUP] 2 [/SUP], Elsayed M Abdelwhab[SUP] 2 [/SUP], Reiner Ulrich[SUP] 3 [/SUP]
Affiliations
- PMID: 38627481
- DOI: 10.1038/s41598-024-59239-5
As immunohistochemistry is valuable for determining tissue and cell tropism of avian influenza viruses (AIV), but time-consuming, an artificial intelligence-based workflow was developed to automate the AIV antigen quantification. Organ samples from experimental AIV infections including brain, heart, lung and spleen on one slide, and liver and kidney on another slide were stained for influenza A-matrixprotein and analyzed with QuPath: Random trees algorithms were trained to identify the organs on each slide, followed by threshold-based quantification of the immunoreactive area. The algorithms were trained and tested on two different slide sets, then retrained on both and validated on a third set. Except for the kidney, the best algorithms for organ selection correctly identified the largest proportion of the organ area. For most organs, the immunoreactive area assessed following organ selection was significantly and positively correlated to a manually assessed semiquantitative score. In the validation set, intravenously infected chickens showed a generally higher percentage of immunoreactive area than chickens infected oculonasally. Variability between the slide sets and a similar tissue texture of some organs limited the ability of the algorithms to select certain organs. Generally, suitable correlations of the immunoreactivity data results were achieved, facilitating high-throughput analysis of AIV tissue tropism.