Mindpeak, a European provider in computational pathology, announced that it has received CE-IVD Mark for BreastIHC, an Artificial Intelligence software that detects and quantifies breast cancer cells, for primary diagnosis. The CE-IVD Mark makes the software available to pathology practices across Europe and helps overcome the challenge of an increasing demand for cancer diagnostics.
Hamburg, Germany based Mindpeak is the first company to receive approval for a Deep Learning solution which can distinguish between tumorous and non-tumorous structures on a cellular level. The CE-IVD Mark for in-vitro-diagnostic medical devices confirms that BreastIHC complies with all essential health and safety requirements of all applicable EU directives. “We are very excited about the CE Mark as it allows us to empower pathologists to gain efficiency and increased accuracy in primary diagnosis”, explains Mindpeak CEO and founder Felix Faber.
The detection and quantification of immunohistochemically stained breast tumor cells is one of the most critical tasks for a pathologist as the diagnosis directly impacts the treatment decision for the patient. The task itself is – without AI Support – tedious and error prone, also a result of the increasing pressure pathologists are exposed to due to an increasing number of cancer cases. Studies show that even the best pathologists differ in diagnosis in a significant proportion of patients which can be up to a fifth of cases1.
BreastIHC is a plug-and-play solution that enables pathology laboratories to immediately detect, classify and quantify breast cancer cells without the need for complex set-up and calibration procedures. BreastIHC 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 the scoring in the tumor microenvironment. “Our algorithm has proven in various tests that it works reliably under a wide range of laboratory conditions and can increase reporting speed and throughput enormously,” says Faber.
The company, founded by Faber and Dr Tobias Lang, has been developing image recognition software for pathologists with the help of artificial intelligence since 2018. Partnering with several international laboratories and leading pathology service providers, Mindpeak is continuously expanding its product range and developing it into an indispensable component of the digitalized pathology workflow.
1 Chung et al. (2016), https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4804149/
