PuSH - Publikationsserver des Helmholtz Zentrums München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Wagner, S. ; Matek, C. ; Shetab Boushehri, S. ; Boxberg, M.* ; Lamm, L. ; Sadafi, A. ; Winter, D. ; Marr, C. ; Peng, T.

Built to last? Reproducibility and reusability of deep learning algorithms in computational pathology.

Mod. Pathol. 37:100350 (2024)
Verlagsversion DOI PMC
Open Access Hybrid
Creative Commons Lizenzvertrag
Recent progress in computational pathology has been driven by deep learning. While code and data availability are essential to reproduce findings from preceding publications, ensuring a deep learning model's reusability is more challenging. For that, the codebase should be well-documented and easy to integrate into existing workflows and models should be robust toward noise and generalizable toward data from different sources. Strikingly, only a few computational pathology algorithms have been reused by other researchers so far, let alone employed in a clinical setting. To assess the current state of reproducibility and reusability of computational pathology algorithms, we evaluated peer-reviewed articles available in PubMed, published between January 2019 and March 2021, in 5 use cases: stain normalization; tissue type segmentation; evaluation of cell-level features; genetic alteration prediction; and inference of grading, staging, and prognostic information. We compiled criteria for data and code availability and statistical result analysis and assessed them in 160 publications. We found that only one-quarter (41 of 160 publications) made code publicly available. Among these 41 studies, three-quarters (30 of 41) analyzed their results statistically, half of them (20 of 41) released their trained model weights, and approximately a third (16 of 41) used an independent cohort for evaluation. Our review is intended for both pathologists interested in deep learning and researchers applying algorithms to computational pathology challenges. We provide a detailed overview of publications with published code in the field, list reusable data handling tools, and provide criteria for reproducibility and reusability.
Impact Factor
Scopus SNIP
Altmetric
7.100
0.000
Tags
Anmerkungen
Besondere Publikation
Auf Hompepage verbergern

Zusatzinfos bearbeiten
Eigene Tags bearbeiten
Privat
Eigene Anmerkung bearbeiten
Privat
Auf Publikationslisten für
Homepage nicht anzeigen
Als besondere Publikation
markieren
Publikationstyp Artikel: Journalartikel
Dokumenttyp Review
Schlagwörter Artificial Intelligence ; Computational Pathology ; Deep Learning ; Histology/histopathology ; Reproducibility ; Reusability; Artificial-intelligence; Histopathology Images; Cancer; Prediction; Model; Stain; Segmentation
Sprache englisch
Veröffentlichungsjahr 2024
Prepublished im Jahr 2023
HGF-Berichtsjahr 2023
ISSN (print) / ISBN 0893-3952
e-ISSN 1530-0285
Zeitschrift Modern Pathology
Quellenangaben Band: 37, Heft: 1, Seiten: , Artikelnummer: 100350 Supplement: ,
Verlag United States and Canadian Academy of Pathology ; Nature Publishing Group
Verlagsort Ste 800, 230 Park Ave, New York, Ny 10169 Usa
Begutachtungsstatus Peer reviewed
Institut(e) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Human-Centered AI (HCA)
Helmholtz Pioneer Campus (HPC)
POF Topic(s) 30205 - Bioengineering and Digital Health
30203 - Molecular Targets and Therapies
Forschungsfeld(er) Enabling and Novel Technologies
Pioneer Campus
PSP-Element(e) G-530006-001
G-540007-001
G-510008-001
Förderungen European Research Council under the European Union
Joachim Herz Foundation
Helmholtz Association
DOI 10.1016/j.modpat.2023.100350
WOS ID 001110800000001
PubMed ID 37827448
Erfassungsdatum 2023-11-28
[➜Korrektur melden]