Direct prediction of genetic aberrations from pathology images in gastric cancer with swarm learning.
Artificial intelligence
Biomarker
Blockchain
Gastric cancer
Pathology
Swarm learning
Journal
Gastric cancer : official journal of the International Gastric Cancer Association and the Japanese Gastric Cancer Association
ISSN: 1436-3305
Titre abrégé: Gastric Cancer
Pays: Japan
ID NLM: 100886238
Informations de publication
Date de publication:
03 2023
03 2023
Historique:
received:
04
08
2022
accepted:
12
10
2022
pubmed:
21
10
2022
medline:
3
3
2023
entrez:
20
10
2022
Statut:
ppublish
Résumé
Computational pathology uses deep learning (DL) to extract biomarkers from routine pathology slides. Large multicentric datasets improve performance, but such datasets are scarce for gastric cancer. This limitation could be overcome by Swarm Learning (SL). Here, we report the results of a multicentric retrospective study of SL for prediction of molecular biomarkers in gastric cancer. We collected tissue samples with known microsatellite instability (MSI) and Epstein-Barr Virus (EBV) status from four patient cohorts from Switzerland, Germany, the UK and the USA, storing each dataset on a physically separate computer. On an external validation cohort, the SL-based classifier reached an area under the receiver operating curve (AUROC) of 0.8092 (± 0.0132) for MSI prediction and 0.8372 (± 0.0179) for EBV prediction. The centralized model, which was trained on all datasets on a single computer, reached a similar performance. Our findings demonstrate the feasibility of SL-based molecular biomarkers in gastric cancer. In the future, SL could be used for collaborative training and, thus, improve the performance of these biomarkers. This may ultimately result in clinical-grade performance and generalizability.
Sections du résumé
BACKGROUND
Computational pathology uses deep learning (DL) to extract biomarkers from routine pathology slides. Large multicentric datasets improve performance, but such datasets are scarce for gastric cancer. This limitation could be overcome by Swarm Learning (SL).
METHODS
Here, we report the results of a multicentric retrospective study of SL for prediction of molecular biomarkers in gastric cancer. We collected tissue samples with known microsatellite instability (MSI) and Epstein-Barr Virus (EBV) status from four patient cohorts from Switzerland, Germany, the UK and the USA, storing each dataset on a physically separate computer.
RESULTS
On an external validation cohort, the SL-based classifier reached an area under the receiver operating curve (AUROC) of 0.8092 (± 0.0132) for MSI prediction and 0.8372 (± 0.0179) for EBV prediction. The centralized model, which was trained on all datasets on a single computer, reached a similar performance.
CONCLUSIONS
Our findings demonstrate the feasibility of SL-based molecular biomarkers in gastric cancer. In the future, SL could be used for collaborative training and, thus, improve the performance of these biomarkers. This may ultimately result in clinical-grade performance and generalizability.
Identifiants
pubmed: 36264524
doi: 10.1007/s10120-022-01347-0
pii: 10.1007/s10120-022-01347-0
pmc: PMC9950158
doi:
Substances chimiques
Biomarkers, Tumor
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
264-274Informations de copyright
© 2022. The Author(s).
Références
Laleh NG, Muti HS, Loeffler CML, Echle A, Saldanha OL, Mahmood F, et al. Benchmarking weakly-supervised deep learning pipelines for whole slide classification in computational pathology. Med Image Anal. 2022;79:102474.
doi: 10.1016/j.media.2022.102474
Heinz CN, Echle A, Foersch S, Bychkov A, Kather JN. The future of artificial intelligence in digital pathology - results of a survey across stakeholder groups. Histopathology. 2022;80(7):1121–7. https://doi.org/10.1111/his.14659 .
doi: 10.1111/his.14659
pubmed: 35373378
Shmatko A, GhaffariLaleh N, Gerstung M, Kather JN. Artificial intelligence in histopathology: enhancing cancer research and clinical oncology. Nat Cancer. 2022;3:1026–38.
doi: 10.1038/s43018-022-00436-4
pubmed: 36138135
Bera K, Schalper KA, Rimm DL, Velcheti V, Madabhushi A. Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology. Nat Rev Clin Oncol. 2019;16:703–15.
doi: 10.1038/s41571-019-0252-y
pubmed: 31399699
pmcid: 6880861
Muti HS, Heij LR, Keller G, Kohlruss M, Langer R, Dislich B, et al. Deep Learning for diagnosis of microsatellite instable and Epstein–Barr-Virus-associated gastric cancer. Lancet Digital Health. 2021 [cited 21 Jun 2022]. Available: https://eprints.whiterose.ac.uk/174309/
Kather JN, Pearson AT, Halama N, Jäger D, Krause J, Loosen SH, et al. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat Med. 2019;25:1054–6.
doi: 10.1038/s41591-019-0462-y
pubmed: 31160815
pmcid: 7423299
Echle A, Laleh NG, Schrammen PL, West NP, Trautwein C, Brinker TJ, et al. Deep learning for the detection of microsatellite instability from histology images in colorectal cancer: a systematic literature review. ImmunoInformatics. 2021;3–4: 100008.
doi: 10.1016/j.immuno.2021.100008
Kather JN, Schulte J, Grabsch HI, Loeffler C, Muti H, Dolezal J, et al. Deep learning detects virus presence in cancer histology. bioRxiv. 2019. https://doi.org/10.1101/690206 .
doi: 10.1101/690206
Bilal M, Raza SEA, Azam A, Graham S, Ilyas M, Cree IA, et al. Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study. Lancet Digit Health. 2021;3:e763–72.
doi: 10.1016/S2589-7500(21)00180-1
pubmed: 34686474
pmcid: 8609154
GhaffariLaleh N, Ligero M, Perez-Lopez R, Kather JN. Facts and hopes on the use of artificial intelligence for predictive immunotherapy biomarkers in cancer. Clin Cancer Res. 2022. https://doi.org/10.1158/1078-0432.CCR-22-0390 .
doi: 10.1158/1078-0432.CCR-22-0390
Kacew AJ, Strohbehn GW, Saulsberry L, Laiteerapong N, Cipriani NA, Kather JN, et al. Artificial intelligence can cut costs while maintaining accuracy in colorectal cancer genotyping. Front Oncol. 2021. https://doi.org/10.3389/fonc.2021.630953 .
doi: 10.3389/fonc.2021.630953
pubmed: 34168975
pmcid: 8217761
Echle A, GhaffariLaleh N, Quirke P, Grabsch HI, Muti HS, Saldanha OL, et al. Artificial intelligence for detection of microsatellite instability in colorectal cancer—a multicentric analysis of a pre-screening tool for clinical application. ESMO Open. 2022;7: 100400.
doi: 10.1016/j.esmoop.2022.100400
pubmed: 35247870
pmcid: 9058894
Muti HS, Heij LR, Keller G, Kohlruss M, Langer R, Dislich B, et al. Development and validation of deep learning classifiers to detect Epstein-Barr virus and microsatellite instability status in gastric cancer: a retrospective multicentre cohort study. Lancet Digital Health. 2021. https://doi.org/10.1016/S2589-7500(21)00133-3 .
doi: 10.1016/S2589-7500(21)00133-3
pubmed: 34417147
Cifci D, Foersch S, Kather JN. Artificial intelligence to identify genetic alterations in conventional histopathology. J Pathol. 2022. https://doi.org/10.1002/path.5898 .
doi: 10.1002/path.5898
pubmed: 35342954
Lu MY, Chen RJ, Kong D, Lipkova J, Singh R, Williamson DFK, et al. Federated learning for computational pathology on gigapixel whole slide images. Med Image Anal. 2022;76: 102298.
doi: 10.1016/j.media.2021.102298
pubmed: 34911013
Warnat-Herresthal S, Schultze H, Shastry KL, Manamohan S, Mukherjee S, Garg V, et al. Swarm learning for decentralized and confidential clinical machine learning. Nature. 2021;594:265–70.
doi: 10.1038/s41586-021-03583-3
pubmed: 34040261
pmcid: 8189907
Saldanha OL, Quirke P, West NP, James JA, Loughrey MB, Grabsch HI, et al. Swarm learning for decentralized artificial intelligence in cancer histopathology. Nat Med. 2022. https://doi.org/10.1038/s41591-022-01768-5 .
doi: 10.1038/s41591-022-01768-5
pubmed: 35469069
pmcid: 9205774
Dislich B, Blaser N, Berger MD, Gloor B, Langer R. Preservation of Epstein-Barr virus status and mismatch repair protein status along the metastatic course of gastric cancer. Histopathology. 2020;76:740–7.
doi: 10.1111/his.14059
pubmed: 31898331
Hayashi T, Yoshikawa T, Bonam K, SueLing HM, Taguri M, Morita S, et al. The superiority of the seventh edition of the TNM classification depends on the overall survival of the patient cohort: comparative analysis of the sixth and seventh TNM editions in patients with gastric cancer from Japan and the United Kingdom. Cancer. 2013;119:1330–7.
doi: 10.1002/cncr.27928
pubmed: 23280435
Kohlruss M, Grosser B, Krenauer M, Slotta-Huspenina J, Jesinghaus M, Blank S, et al. Prognostic implication of molecular subtypes and response to neoadjuvant chemotherapy in 760 gastric carcinomas: role of Epstein–Barr virus infection and high- and low-microsatellite instability. Hip Int. 2019;5:227–39.
The Cancer Genome Atlas Research Network. The cancer genome atlas research network. Comprehensive molecular characterization of gastric adenocarcinoma. Nature. 2014;513:202–9. https://doi.org/10.1038/nature13480 .
doi: 10.1038/nature13480
GhaffariLaleh N, Truhn D, Veldhuizen GP, Han T, van Treeck M, Buelow RD, et al. Adversarial attacks and adversarial robustness in computational pathology. Nat Commun. 2022;13:1–10.
Muti HS, Loeffler C, Echle A, Heij LR, Buelow RD, Krause J, et al. The Aachen protocol for deep learning histopathology: a hands-on guide for data preprocessing. 2020. Zenodo. https://doi.org/10.5281/ZENODO.3694994 .
Macenko M, Niethammer M, Marron JS, Borland D, Woosley JT, Xiaojun Guan, et al. A method for normalizing histology slides for quantitative analysis. In: 2009 IEEE international symposium on biomedical imaging: from nano to macro. IEEE: Piscataway; 2009. p. 1107–1110.
Wang X, Du Y, Yang S, Zhang J, Wang M, Zhang J, et al. RetCCL: clustering-guided contrastive learning for whole-slide image retrieval. Med Image Anal. 2022. https://doi.org/10.1016/j.media.2022.102645 .
doi: 10.1016/j.media.2022.102645
pubmed: 36623381
pmcid: 9792121
Saldanha OL, Loeffler CML, Niehues JM, van Treeck M, Seraphin TP, Hewitt KJ, et al. Self-supervised deep learning for pan-cancer mutation prediction from histopathology. bioRxiv. 2022. https://doi.org/10.1101/2022.09.15.507455 .
doi: 10.1101/2022.09.15.507455
Thorsson V, Gibbs DL, Brown SD, Wolf D, Bortone DS, Ou Yang T-H, et al. The immune landscape of cancer. Immunity. 2018;48:812-830.e14.
doi: 10.1016/j.immuni.2018.03.023
pubmed: 29628290
pmcid: 5982584
Mathiak M, Warneke VS, Behrens H-M, Haag J, Böger C, Krüger S, et al. Clinicopathologic characteristics of microsatellite instable gastric carcinomas revisited: urgent need for standardization. Appl Immunohistochem Mol Morphol. 2017;25:12–24.
doi: 10.1097/PAI.0000000000000264
pubmed: 26371427
Martinez-Ciarpaglini C, Fleitas-Kanonnikoff T, Gambardella V, Llorca M, Mongort C, Mengual R, et al. Assessing molecular subtypes of gastric cancer: microsatellite unstable and Epstein-Barr virus subtypes. Methods for detection and clinical and pathological implications. ESMO Open. 2019;4:e000470.
doi: 10.1136/esmoopen-2018-000470
pubmed: 31231566
pmcid: 6555614
Schirris Y, Gavves E, Nederlof I, Horlings HM, Teuwen J. DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancer. Med Image Anal. 2022;79:102464.
doi: 10.1016/j.media.2022.102464
pubmed: 35596966
Chen RJ, Lu MY, Williamson DFK, Chen TY, Lipkova J, Noor Z, et al. Pan-cancer integrative histology-genomic analysis via multimodal deep learning. Cancer Cell. 2022;40:865-878.e6.
doi: 10.1016/j.ccell.2022.07.004
pubmed: 35944502