How Artificial Intelligence Can Help Diagnose Leukemia
Oncology Times · 2021
hairy cell leukemia: As seen by artificial intelligence, each marker is coded in a different color. This is a hairy cell leukemia that is so rare that only a few large laboratories regularly receive such samples for diagnosis.The presence of cancer of the lymphatic system is often determined by analyzing samples from the blood or bone marrow. A team led by Peter Krawitz, MD, from the Institute for Genomic Statistics and Bioinformatics at the University Hospital Bonn in Germany, had already shown in 2020 that artificial intelligence (AI) can help with the diagnosis of such lymphomas and leukemias. The technology fully utilizes the potential of all measurement values and increases the speed as well as the objectivity of the analyses compared to established processes. The method has now been further developed so that even smaller laboratories can benefit from this freely accessible machine learning method—an important step towards clinical practice. The study has now been published in the journal Patterns (2021; doi: 10.1016/j.patter.2021.100351). 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 related leukemias. If such a cancer of the lymphatic system is suspected, the physician takes a blood or bone marrow sample and sends it to specialized laboratories. This is where flow cytometry comes in. Flow cytometry is a method in which the blood cells flow past measurement sensors at high speed. The properties of the cells can be detected depending on their shape, structure, or coloring. Detection and accurate characterization of pathological cells is important when making a diagnosis. The laboratories use antibodies that dock to the surface of the cells and are coupled to 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. These data are then typically analyzed on 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,” noted Krawitz. “That's why it's usually too costly to thoroughly sift through the entire dataset.” For this reason, Krawitz, together with the bioinformaticians Nanditha Mallesh and Max Zhao, investigated how AI can be used to analyze cytometry data. The team considered more than 30,000 datasets from patients with B-cell lymphoma to train AI. “AI takes full advantage of the data and increases the speed and objectivity of diagnoses,” stated Mallesh, research lead author. The result of the AI evaluations is a suggested diagnosis that still needs to be verified by the physician. In the process, the AI provides indications of conspicuous cells. Artificial Intelligence Results Blood samples and cytometer data were obtained from the Munich Leukemia Laboratory, the Charité-Universitätsmedizin Berlin, the University Hospital Erlangen, and the Bonn University Hospital. Specialists from these institutions examined the results of AI. “The gold standard is diagnosis by hematologists, which can also take into account results of additional tests,” Krawitz said. “The point of using AI is not to replace physicians, but to make the best use of the information contained in the data.” The great new feature of the AI now presented lies in the possibility of knowledge transfer; particularly, smaller laboratories that cannot afford their own bioinformatics expertise and may also have too few samples to develop their own AI from scratch can benefit from this. After a short training phase, during which the AI learns the specifics of the new laboratory, it can then draw on knowledge derived from many thousands of datasets. All raw data and the complete software are open source and therefore freely accessible. In addition, a web service has been developed that makes AI usable even for users without bioinformatics expertise. The team sees huge potential in this technology. The researchers therefore also want to collaborate with major manufacturers of analytics equipment and software to further advance the use of AI. In the case of B-cell lymphomas, for example, genetic and cytomorphological data are also collected to confirm the diagnoses. “If we succeed in using AI for these methods as well, we would have an even more powerful tool,” noted Krawitz, who is also a member of the Cluster of Excellence ImmunoSensation2 at the University of Bonn. The AI developed can in principle also be used for diagnoses of rheumatic diseases, which are often also based on flow cytometric data. Finding Immune Cell Changes in Lymphoplasmacytic Lymphoma A new study by researchers at Winship Cancer Institute of Emory University finds that cancer-associated mutations originate in blood progenitor cells, leading to distinct changes in both cancer and non-cancer immune cells in Waldenstrom macroglobulinemia (WM), a type of non-Hodgkin lymphoma, and its precursor IgM monoclonal gammopathy of undetermined significance. The study by Madhav V. Dhodapkar, MBBS, Kavita M. Dhodapkar, MD, and their colleagues, “Aberrant extrafollicular B cells, immune dysfunction, myeloid inflammation and MyD88-mutant progenitors precede Waldenstrom macroglobulinemia,” was published in Blood Cancer Discovery, a journal of the American Association for Cancer Research (2021; doi: 10.1158/2643-3230.BCD-21-0043). Madhav V. Dhodapkar, MBBS, is the Anise McDaniel Brock Chair and Georgia Research Alliance Eminent Scholar in Cancer Innovation and Professor in the Department of Hematology and Medical Oncology at Emory University School of Medicine. Kavita M. Dhodapkar, MD, is Professor in the Department of Pediatrics, Emory University School of Medicine, and at the Aflac Cancer and Blood Disorders Center at Children's Healthcare of Atlanta. WM, also known as lymphoplasmacytic lymphoma, is the result of growth of cancer cells in the bone marrow producing large amounts of an abnormal protein called macroglobulin. Most cases of WM are characterized by mutation in a gene called MYD88 and lead to cancerous accumulation of mature immune cells called B cells. “When we applied several high-content profiling approaches to study samples from these patients, we were surprised to find out that not only were tumor cells highly abnormal, but so were non-tumor cells,” said Kavita Dhodapkar. “This led us to suspect that perhaps the mutations are already present in earlier blood progenitors that give rise to both cancer and non-cancer cells.” Examining individual cells with a combination of high-dimensional approaches and genome sequencing of subpopulations, the researchers show that WM and its precursor, IgM gammopathy—a distinct disorder featuring an abnormal protein in the blood—originate in the backdrop of several alterations in non-cancer cells, as well as MYD88 mutations in blood progenitors. These alterations include inflammation in the bone marrow, as well as depletion of naïve B and T cells, and instead, increase in a distinct type of B cells called extrafollicular B cells. “The data in this paper have several potential implications for origins and therapy of WM,” said Madhav Dhodapkar. “They provide an example of how cancer-associated mutations can impact not just the cancer cells, but also non-cancer cells in the tumor milieu. They also provide evidence for host immune system to tackle these lesions, which may lead to new immune therapies.”