Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

AI-based leukemia detection in routine diagnostic blood smear data

Project description

Routine leukaemia diagnosis using AI

Peripheral blood smears remain a cornerstone in diagnosing haematologic neoplasms, providing rapid and valuable insights that guide further diagnostic steps. However, since neoplastic transformations typically originate in the bone marrow, they may not appear as detectable abnormalities in peripheral blood, posing a diagnostic challenge. Funded by the European Research Council, the LeukoScreen project develops an explainable transformer-based AI model to classify haematologic malignancies based on peripheral blood cytomorphology. The focus is on real-world patient data, which introduce additional heterogeneity and complexity. The goal is to optimise the model’s calibrated prediction probabilities, reduce the false discovery rate without missing acute leukaemia cases, and thereby minimise unnecessary bone marrow aspirations.

Objective

Acute promyelocytic leukemia is an extremely aggressive blood cancer where immediate diagnosis can determine life or death. The diagnostic state of the art is manual inspection of a patient’s blood smear under the microscope by trained cytologists. It is prone to human error and time consuming - a risk factor in notoriously understaffed laboratories. Supporting clinical decisions with AI will drastically increase diagnostic speed and accuracy, benefit patient survival, and free up valuable expert time. This is particularly important for cytological and histological analysis, whose market size is expected to rise by a compounded annual growth rate of 14.7% in coming years. Yet, so far, the proof of concept that AI can be effectively employed for leukemia detection in routine diagnostics is missing.

I will leverage the methodological advancements in deep learning and explainable AI, the skills of my ERC CoG funded research group, and the expertise and data of the Munich Leukemia Laboratory (MLL), the largest leukemia laboratory in Europe and my long standing industry partner. Together, we will develop and implement LeukoScreen, an AI-based software to automatically identify and flag up acute leukemia cases from MLL’s routine laboratory input. This will decrease the diagnosis to treatment time of critical leukemia cases at reduced costs and staffing. Specifically, we will (i) deploy a real-world dataset from the routine input of the MLL, (ii) train and evaluate our algorithm for transparent decision making on routine diagnostic blood smears, (iii) quantify the gain in sensitivity, specificity, and speed by comparing LeukoScreen with the currently used manual workflow at MLL, and (iv) jointly develop a commercialization strategy for the exploitation of results.

This AI approach to support disease detection will save patients’ lives, change the paradigm of cytologic workflows, and create capacities in overburdened diagnostics.

Fields of science (EuroSciVoc)

Programme(s)

Topic(s)

Funding Scheme

HORIZON-ERC-POC - HORIZON ERC Proof of Concept Grants

See all projects funded under this funding scheme

Call for proposal

(opens in new window) ERC-2022-POC2

See all projects funded under this call

Host institution

HELMHOLTZ ZENTRUM MUENCHEN DEUTSCHES FORSCHUNGSZENTRUM FUER GESUNDHEIT UND UMWELT GMBH
Net EU contribution
€ 135 000,00
Address
INGOLSTADTER LANDSTRASSE 1
85764 Neuherberg
Germany
Region
Bayern Oberbayern München, Landkreis
Activity type
Research Organisations
Links
Total cost
No data

Beneficiaries (2)