Acute Myeloid Leukemia Diagnosed by Convolutional Neural Networks

Scientists have now shown that deep learning algorithms perform similar to human experts when classifying blood samples from patients suffering from acute myeloid leukemia (AML). Their proof of concept study paves the way for an automated, standardized and on-hand sample analysis in the near future.

Scientists from the Helmholtz Zentrum München (Neuherberg, Germany) and their colleagues compiled an annotated image dataset of over 18,000 white blood cells, use it to train a convolutional neural network for leukocyte classification and evaluate the network’s performance by comparing to inter- and intra-expert variability. They used images which were extracted from blood smears of 100 patients suffering from the aggressive blood disease AML and 100 controls. The new AI-driven approach was then evaluated by comparing its performance with the accuracy of human experts.

The network classifies the most important cell types with high accuracy. It also allowed the investigators to decide two clinically relevant questions with human-level performance: (1) if a given cell has blast character and (2) if it belongs to the cell types normally present in non-pathological blood smears. The result showed that the AI-driven solution is able to identify diagnostic blast cells at least as good as a trained cytologist expert.

Carsten Marr, PhD, a computational stem cell biologists and the senior author of the study, said, “To bring our approach to clinics, digitization of patients' blood samples has to become routine. Algorithms have to be trained with samples from different sources to cope with the inherent heterogeneity in sample preparation and staining. Together with our partners we could prove that deep learning algorithms show a similar performance as human cytologists. In a next step, we will evaluate how well other disease characteristics, such as genetic mutations or translocations, can be predicted with this new AI-driven method.”

The authors concluded that their approach holds the potential to be used as a classification aid for examining much larger numbers of cells in a smear than can usually is done by a human expert. This will allow clinicians to recognize malignant cell populations with lower prevalence at an earlier stage of the disease. The study was published on November 12, 2019 in the journal Nature Machine Intelligence.

Related Links:
Helmholtz Zentrum München