PuSH - Publikationsserver des Helmholtz Zentrums München

Hehr, M. ; Sadafi, A. ; Matek, C. ; Lienemann, P. ; Pohlkamp, C.* ; Haferlach, T.* ; Spiekermann, K.* ; Marr, C.

Explainable AI identifies diagnostic cells of genetic AML subtypes.

PLOS Digit Health 2:e0000187 (2023)
Verlagsversion DOI PMC
Open Access Gold
Creative Commons Lizenzvertrag
Explainable AI is deemed essential for clinical applications as it allows rationalizing model predictions, helping to build trust between clinicians and automated decision support tools. We developed an inherently explainable AI model for the classification of acute myeloid leukemia subtypes from blood smears and found that high-attention cells identified by the model coincide with those labeled as diagnostically relevant by human experts. Based on over 80,000 single white blood cell images from digitized blood smears of 129 patients diagnosed with one of four WHO-defined genetic AML subtypes and 60 healthy controls, we trained SCEMILA, a single-cell based explainable multiple instance learning algorithm. SCEMILA could perfectly discriminate between AML patients and healthy controls and detected the APL subtype with an F1 score of 0.86±0.05 (mean±s.d., 5-fold cross-validation). Analyzing a novel multi-attention module, we confirmed that our algorithm focused with high concordance on the same AML-specific cells as human experts do. Applied to classify single cells, it is able to highlight subtype specific cells and deconvolve the composition of a patient's blood smear without the need of single-cell annotation of the training data. Our large AML genetic subtype dataset is publicly available, and an interactive online tool facilitates the exploration of data and predictions. SCEMILA enables a comparison of algorithmic and expert decision criteria and can present a detailed analysis of individual patient data, paving the way to deploy AI in the routine diagnostics for identifying hematopoietic neoplasms.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Korrespondenzautor
ISSN (print) / ISBN 2767-3170
e-ISSN 2767-3170
Zeitschrift PLOS Digit Health
Quellenangaben Band: 2, Heft: 3, Seiten: , Artikelnummer: e0000187 Supplement: ,
Verlag PLOS
Nichtpatentliteratur Publikationen
Begutachtungsstatus Peer reviewed
Institut(e) Institute of Computational Biology (ICB)
Institute of AI for Health (AIH)