We at MetaSystems support cytogenetic laboratories to customize complex workflows for scalable work environments: from communication with external LIMS, sophisticated case and image management, automated metaphase finding, AI-based karyotyping, and reporting. MetaSystems has implemented state-of-the-art deep learning algorithms in its karyotyping software Ikaros. The patented method based on deep neural networks (DNN) replaces tedious manual processing steps. This innovation helps experts focus on the analysis.

Customers worldwide have already incorporated Ikaros' advanced tools into their workflows, and we are delighted to receive extensive positive feedback. Below, we share some of these field reports. Please note that the experiences described pertain to the specific implementation of Ikaros in the quoted users' laboratories and may not be universally applicable.

Our lab had the opportunity to be the first user to test the betaversion of MetaSystems’ new AI-based karyotyping software Ikaros. We experienced a time gain of up to 50% in the karyotype analysis of bone marrow metaphases. This enormous gain in efficiency allows us to keep pace with the ever-increasing workload in times of shortage of personnel resources.

Prof. Dr. Claudia Haferlach
MD from MLL (Münchner Leukämielabor GmbH, Germany)

MLL Münchner Leukämielabor highlighted our collaboration in its recent newsletter article titled “Chromosome Analysis 5.0 – Automation, Digitization and Artificial Intelligence”. The article emphasizes how artificial intelligence (AI) is moving chromosome analysis, also known as karyotyping, forward in clinical cytogenetics. Deep learning, an advance in the field of artificial intelligence, is pushing the frontiers in medicine and life sciences.

In the article, MLL states that they have been able to reduce the time to generate a karyogram from about two to three minutes with manual processing to circa 25 seconds with the AI-based algorithms, including subsequent review by cytogeneticists.

Chromosome analysis is a routine method in clinical cytogenetics and has been considered the "gold standard" in genetic diagnostics for decades, despite advances in whole-genome sequencing. In summary, the article concludes that “Automation and the use of AI have transformed chromosome analysis, which was considered to be a laborious process, into a faster and more sensitive method that remains highly relevant in many hematologic neoplasias.”

Read the full MLL article

The laboratory led by Head Senior Physician Prof. Dr. med. Gudrun Göhring at the Institute for Human Genetics at the MHH in Germany (Medizinische Hochschule Hannover), together with two of our colleagues, has published a research article in the scientific journal Cancer Genetics.

The authors investigated the patented chromosome classification based on artificial intelligence (U.S. patent no. 10,991,098) in our digital karyotyping software Ikaros. The presented study shows that advanced Deep Learning algorithms, the latest development in artificial intelligence, are able to suggest the correct chromosome class for 98.8% of chromosomes. The application of Deep Learning thus resulted in a time saving of 42% for the entire karyotyping workflow (DOI: 10.1016/j.cancergen.2021.11.005).

My former laboratory at Hannover Medical School supported MetaSystems in adapting the AI functionality to the segmentation and classification of fluorescent R-banding (Vajen et al, PMID 34839233). With the help of the adapted AI, we were able to save more than 40% processing time with the karyotyping software Ikaros. As the new head of amedes genetics, I am pleased to see that the cytogenetic laboratory is equipped with solutions by MetaSystems for metaphase finding, karyotyping and FISH as well.

Prof. Dr. Gudrun Göhring
Medical Director of Genetics
MVZ amedes genetics for interdisciplinary laboratory diagnostics
Hannover, Germany

Discover the full research article

Legal Note