Page Not Found
Number of positive and negative tumor cells; quantitative score.
Step 1: Open or upload the Ki-67, ER or PR image / whole-slide image.
Please note that images work best at 20-40x resolution.
Step 2: Select the region of interest for analysis and see that it only takes a couple of seconds to process.
Step 3: Adapt the positivity threshold to fit your assessment.
You can change the classification of a single cell just clicking on it once and BreastIHC will automatically update the result. Double click on a cell or on an empty area to add or remove cells. Select a specific area to analyse and the quantification will only be applied to the selected area.
Step 4: Get your score results on the left side menu.
Proprietary AI model for cell detection in nuclear IHC-stainings based on convolutional neural networks.
Standard personal working machine. Minimum requirements: 32 bit Processor Intel Core i5 or better; 4 GB RAM.
All major whole slide image formats (tif, mrxs, etc.), png, jpg/jpeg
Breast, Cell quantification, Cell detection, Nuclear IHC, Breast Cancer, Nuclei detection, Ki-67, Deep learning, Artificial Intelligence, Image analysis.
BreastIHC detects and classifies cells into positively stained tumor and unstained tumor cells. One of its great advantages is its ability to differentiate between tumorous and non-tumorous structures, improving your scoring in the tumor microenvironment
BreastIHC reliability is unique: it provides accurate results even in challenging contexts as it was developed with typical lab-specific variations in mind, such as slide preparation, staining and imaging
BreastIHC supports a broad range of scanners and cameras and can easily be integrated into existing workflows