In:
PLOS Digital Health, Public Library of Science (PLoS), Vol. 2, No. 3 ( 2023-3-15), p. e0000187-
Abstract:
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.
Type of Medium:
Online Resource
ISSN:
2767-3170
DOI:
10.1371/journal.pdig.0000187
DOI:
10.1371/journal.pdig.0000187.g001
DOI:
10.1371/journal.pdig.0000187.g002
DOI:
10.1371/journal.pdig.0000187.g003
DOI:
10.1371/journal.pdig.0000187.s001
DOI:
10.1371/journal.pdig.0000187.s002
DOI:
10.1371/journal.pdig.0000187.s003
DOI:
10.1371/journal.pdig.0000187.s004
DOI:
10.1371/journal.pdig.0000187.s005
DOI:
10.1371/journal.pdig.0000187.s006
DOI:
10.1371/journal.pdig.0000187.s007
DOI:
10.1371/journal.pdig.0000187.s008
Language:
English
Publisher:
Public Library of Science (PLoS)
Publication Date:
2023
detail.hit.zdb_id:
3106944-7
Bookmarklink