Automatic image analysis can help increase productivity through process automation and improve healthcare through standardization and development of new computer-based methods.
Once the immunohistochemistry slide is digitized, computer algorithms can be applied to quantitate the staining pattern. The most commonly used is HER2 analysis for breast carcinoma. P53 staining of transitional cell carcinoma of the bladder is another example.
Computer algorithms are also available for cell ploidy and rare event analysis, such as metastatic carcinoma in bone marrow.
Algorithm Catalog (from Aperio Systems)
We provide a growing suite of flexible and affordable algorithms that can be tailored to meet your needs in a wide variety of applications, as listed below
Positive Pixel Count
A multi-purpose algorithm that measures area and intensities for two stains.
Color Deconvolution
A sophisticated and easy to use multi-purpose algorithm that accurately separates the image to show the actual contribution of each stain and quantifies the area and intensities of the stains (the professional version of our Positive Pixel Count algorithm).
IHC Nuclear
The IHC (ImmunoHistoChemistry) Nuclear image analysis algorithm is optimized for ER (Estrogen Receptor), PR (Progesterone Receptor), Ki-67, and P53 stained breast tissue slides, but can also be used for other tissue types and nuclear stains. The algorithm detects the nuclear staining for the individual nuclei and quantifies their intensity. Nuclei are classified as 0, 1+, 2+, and 3+ based on their intensity. The percentage of positive stained nuclei, the average staining intensity of the positive nuclei as a score of 0, 1+, 2+, or 3+ and the percentages of 0, 1+, 2+, and 3+ nuclei are determined.
IHC Membrane
The IHC (ImmunoHistoChemistry) Membrane image analysis algorithm is optimized for HER2 (Human Epidermal growth factor Receptor 2) stained breast tissue slides but can also be used for other tissue types and membrane stains. The algorithm detects the membrane staining for the individual cells and quantifies their intensity and completeness. Cells are classified as 0, 1+, 2+, and 3+ based on their intensity and completeness. Based on the percentages of 0, 1+, 2+, and 3+ cells, a score of 0, 1+, 2+, or 3+ is determined according to the HER2 scoring scheme.
Micromet
A rare event detection algorithm, Micromet is specifically designed to detect micrometastasis of tumor cells found in circulating blood.
