Morphological and molecular breast cancer profiling through explainable machine learning
Standard
Morphological and molecular breast cancer profiling through explainable machine learning. / Binder, Alexander; Bockmayr, Michael; Hägele, Miriam; Wienert, Stephan; Heim, Daniel; Hellweg, Katharina; Ishii, Masaru; Stenzinger, Albrecht; Hocke, Andreas; Denkert, Carsten; Müller, Klaus Robert; Klauschen, Frederick.
In: NAT MACH INTELL, Vol. 3, No. 4, 04.2021, p. 355-366.Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Morphological and molecular breast cancer profiling through explainable machine learning
AU - Binder, Alexander
AU - Bockmayr, Michael
AU - Hägele, Miriam
AU - Wienert, Stephan
AU - Heim, Daniel
AU - Hellweg, Katharina
AU - Ishii, Masaru
AU - Stenzinger, Albrecht
AU - Hocke, Andreas
AU - Denkert, Carsten
AU - Müller, Klaus Robert
AU - Klauschen, Frederick
N1 - Publisher Copyright: © 2021, The Author(s), under exclusive licence to Springer Nature Limited. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2021/4
Y1 - 2021/4
N2 - Recent advances in cancer research and diagnostics largely rely on new developments in microscopic or molecular profiling techniques, offering high levels of detail with respect to either spatial or molecular features, but usually not both. Here, we present an explainable machine-learning approach for the integrated profiling of morphological, molecular and clinical features from breast cancer histology. First, our approach allows for the robust detection of cancer cells and tumour-infiltrating lymphocytes in histological images, providing precise heatmap visualizations explaining the classifier decisions. Second, molecular features, including DNA methylation, gene expression, copy number variations, somatic mutations and proteins are predicted from histology. Molecular predictions reach balanced accuracies up to 78%, whereas accuracies of over 95% can be achieved for subgroups of patients. Finally, our explainable AI approach allows assessment of the link between morphological and molecular cancer properties. The resulting computational multiplex-histology analysis can help promote basic cancer research and precision medicine through an integrated diagnostic scoring of histological, clinical and molecular features.
AB - Recent advances in cancer research and diagnostics largely rely on new developments in microscopic or molecular profiling techniques, offering high levels of detail with respect to either spatial or molecular features, but usually not both. Here, we present an explainable machine-learning approach for the integrated profiling of morphological, molecular and clinical features from breast cancer histology. First, our approach allows for the robust detection of cancer cells and tumour-infiltrating lymphocytes in histological images, providing precise heatmap visualizations explaining the classifier decisions. Second, molecular features, including DNA methylation, gene expression, copy number variations, somatic mutations and proteins are predicted from histology. Molecular predictions reach balanced accuracies up to 78%, whereas accuracies of over 95% can be achieved for subgroups of patients. Finally, our explainable AI approach allows assessment of the link between morphological and molecular cancer properties. The resulting computational multiplex-histology analysis can help promote basic cancer research and precision medicine through an integrated diagnostic scoring of histological, clinical and molecular features.
UR - http://www.scopus.com/inward/record.url?scp=85102257467&partnerID=8YFLogxK
U2 - 10.1038/s42256-021-00303-4
DO - 10.1038/s42256-021-00303-4
M3 - SCORING: Journal article
AN - SCOPUS:85102257467
VL - 3
SP - 355
EP - 366
JO - NAT MACH INTELL
JF - NAT MACH INTELL
SN - 2522-5839
IS - 4
ER -