AI can help diagnose B-cell lymphomas and associated leukemias

The presence of cancer of the lymphatic system is often determined by testing samples of blood or bone marrow. A team led by Professor Peter Krawitz from the University of Bonn had already shown in 2020 that artificial intelligence can help in the diagnosis of such lymphomas and leukemias. The technology fully utilizes the potential of all measurement values ​​and increases the speed and objectivity of analyzes against established processes. The method has now been developed so that even the smallest laboratories can benefit from this freely accessible machine learning method – an important step towards clinical practice. The study has just been published in the journal “Patterns”.

The lymph nodes become swollen, there is weight loss and fatigue, as well as fevers and infections – these are typical symptoms of malignant B-cell lymphomas and associated leukemias. If such cancer of the lymphatic system is suspected, the doctor will take a sample of blood or bone marrow and send it to specialized laboratories. This is where flow cytometry comes in. Flow cytometry is a method in which blood cells pass by measuring sensors at high speed. The properties of cells can be detected based on their shape, structure or staining. Detection and precise characterization of pathological cells is important in diagnosis.

Laboratories use “antibodies” which attach to the surface of cells and are coupled with fluorescent dyes. Such markers can also be used to detect small differences between cancer cells and healthy blood cells. Flow cytometry generates large amounts of data. On average, more than 50,000 cells are measured per sample. This data is then generally analyzed on the screen by plotting the expression of the markers used against each other.

But with 20 markers, the doctor would already have to compare about 150 two-dimensional images. That’s why it’s usually too expensive to sift through the entire dataset. “

Teacher. Dr. Peter Krawitz, Institute for Genomic Statistics and Bioinformatics, University Hospital Bonn

For this reason, Krawitz, together with bioinformaticians Nanditha Mallesh and Max Zhao, investigated how artificial intelligence can be used to analyze cytometry data. The team examined more than 30,000 datasets of patients with B-cell lymphoma to train artificial intelligence (AI). “AI takes full advantage of data and increases the speed and objectivity of diagnostics,” says lead author Nanditha Mallesh. The result of AI assessments is a suggested diagnosis that still needs to be verified by the doctor. In the process, the AI ​​provides indications of visible cells.

Experts have examined the results of artificial intelligence

Blood samples and cytometric data were obtained from the Munich Leukemia Laboratory (MLL), Charité – Universitätsmedizin Berlin, University Hospital Erlangen and University Hospital Bonn. Specialists from these institutions examined the results of artificial intelligence. “The gold standard is diagnosis by hematologists, who may also take into account the results of additional tests,” Krawitz said. “The purpose of using AI is not to replace doctors, but to get the most out of the information in the data.” The big novelty of AI now presented is the possibility of knowledge transfer: especially smaller labs that cannot afford their own bioinformatics expertise and may also have too few samples to develop their own AI from scratch can benefit. After a short training phase, during which the AI ​​learns the specifics of the new lab, it can then draw on knowledge from several thousand datasets.

All raw data and the complete software are open source and therefore freely accessible. Additionally, res Mechanicala GmbH, which participated in the study, developed a web service that makes artificial intelligence usable even for users without bioinformatics expertise. “With https://hema.to we want to enable the exchange of anonymized flow cytometry data between laboratories and thus create the conditions for an even higher quality of diagnostics”, explains Dr Hannes Lüling of res Mechanicala .

Great potential

The team sees enormous potential in this technology. The researchers therefore also wish to collaborate with the main manufacturers of analysis equipment and software to further advance the use of artificial intelligence. In the case of B cell lymphomas, for example, genetic and cytomorphological data are also collected to confirm the diagnoses. “If we can successfully use AI for these methods as well, we will have an even more powerful tool,” says Krawitz, who is also a member of the University of Bonn’s ImmunoSensation2 cluster of excellence. The developed artificial intelligence can in principle also be used for diagnoses of rheumatic diseases, which are often also based on flow cytometry data.

The first author, Nanditha Mallesh, will present the results of the study at the annual meeting of the German Society of Hematology and Medical Oncology in Berlin in early October.