Pan-cancer image-based detection of clinically actionable genetic alterations

Kather, Jakob Nikolas; Heij, Lara; Grabsch, Heike; Loeffler, Chiara Maria Lavinia; Echle, Amelie; Muti, Hannah Sophie; Krause, Jeremias; Niehues, Jan Moritz; Sommer, Kai; Bankhead, Peter; Kooreman, Loes; Schulte, Jefree J.; Cipriani, Nicole A.; Buelow, Roman D.; Boor, Peter; Ortiz-Brüchle, Nadina; Hanby, Andrew M.; Speirs, Valerie; Kochanny, Sara; Patnaik, Akash; Srisuwananukorn, Andrew; Brenner, Hermann; Hoffmeister, Michael; Brandt, Piet A. van den; Jäger, Dirk; Trautwein, Christian; Pearson, Alexander T.; Luedde, Tom

doi:10.1038/s43018-020-0087-6

Cited by 441 publications

(417 citation statements)

References 54 publications

Supporting

Mentioning

397

Contrasting

Order By: Relevance

“…We included patients from the following 4 previous studies with the intent of retraining a previously described deep learning system. 16,17 First, we used the publicly available Cancer Genome Atlas (TCGA) (n ¼ 616 patients) ( Supplementary Figure 1), a multicenter study with patients with stage I-IV disease, mainly from the United States. 20 All images and data from the TCGA study are publicly available at https://portal.gdc.cancer.gov.…”

Section: Ethics Statement and Patient Cohortsmentioning

confidence: 99%

“…30 A modified shufflenet deep learning system with a 512 Â 512 input layer was trained on these image tiles in MATLAB R2019a (Math-Works, Natick, MA) with the hyperparameters listed in Supplementary Table 3, as described before. 17 Tile-level predictions were averaged on the patient level, with the proportion of predicted MSI or dMMR tiles (positive threshold) being the free parameter for the receiver operating characteristic analysis. All confidence intervals were obtained by 10-fold bootstrapping.…”

Section: Image Preprocessing and Deep Learningmentioning

confidence: 99%

“…Smaller proof-of-concept studies have shown that deep learning can detect a range of molecular biomarkers directly from routine histology, including multiple clinically relevant oncogenes. [17][18][19] However, these classifiers were not validated in large multicenter cohorts and cannot be readily generalized beyond the training set. To our knowledge, the present study is the first international collaborative effort to validate such a deep learning-based molecular biomarker.…”

Section: Context: Multicenter Validation Of Deep Learning Biomarkersmentioning

confidence: 99%

See 2 more Smart Citations

Clinical-Grade Detection of Microsatellite Instability in Colorectal Tumors by Deep Learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

BACKGROUND & AIMS: Microsatellite instability (MSI) and mismatch-repair deficiency (dMMR) in colorectal tumors are used to select treatment for patients. Deep learning can detect MSI and dMMR in tumor samples on routine histology slides faster and less expensively than molecular assays. However, clinical application of this technology requires high performance and multisite validation, which have not yet been performed. METHODS: We collected H&E-stained slides and findings from molecular analyses for MSI and dMMR from 8836 colorectal tumors (of all stages) included in the MSI-DETECT consortium study, from Germany, the Netherlands, the United Kingdom, and the United States. Specimens with dMMR were identified by immunohistochemistry analyses of tissue microarrays for loss of MLH1, MSH2, MSH6, and/or PMS2. Specimens with MSI were identified by genetic analyses. We trained a deep-learning detector to identify samples with MSI from these slides; performance was assessed by cross-validation (N ¼ 6406 specimens) and validated in an external cohort (n ¼ 771 specimens). Prespecified endpoints were area under the receiver operating characteristic (AUROC) curve and area under the precision-recall curve

show abstract

Section: Ethics Statement and Patient Cohortsmentioning

confidence: 99%

Section: Image Preprocessing and Deep Learningmentioning

confidence: 99%

Section: Context: Multicenter Validation Of Deep Learning Biomarkersmentioning

confidence: 99%

See 1 more Smart Citation

Clinical-Grade Detection of Microsatellite Instability in Colorectal Tumors by Deep Learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Studies published over the past 1-2 years have pursued a "pan-cancer pan-mutation" approach to try to predict any genetic alteration in any type of solid tumour directly from H&E histology. [38][39][40] However, these studies have been largely based on one particular dataset, "The Cancer Genome Atlas (TCGA)", provided by the National Cancer Institute (NCI), and so large-scale validation in genomically characterised cohorts beyond TCGA is needed to gauge the robustness of these methods in pancancer applications.…”

Section: Prediction Of Genotype and Gene Expressionmentioning

confidence: 99%

Deep learning in cancer pathology: a new generation of clinical biomarkers

et al. 2020

Self Cite

View full text Add to dashboard Cite

Clinical workflows in oncology rely on predictive and prognostic molecular biomarkers. However, the growing number of these complex biomarkers tends to increase the cost and time for decision-making in routine daily oncology practice; furthermore, biomarkers often require tumour tissue on top of routine diagnostic material. Nevertheless, routinely available tumour tissue contains an abundance of clinically relevant information that is currently not fully exploited. Advances in deep learning (DL), an artificial intelligence (AI) technology, have enabled the extraction of previously hidden information directly from routine histology images of cancer, providing potentially clinically useful information. Here, we outline emerging concepts of how DL can extract biomarkers directly from histology images and summarise studies of basic and advanced image analysis for cancer histology. Basic image analysis tasks include detection, grading and subtyping of tumour tissue in histology images; they are aimed at automating pathology workflows and consequently do not immediately translate into clinical decisions. Exceeding such basic approaches, DL has also been used for advanced image analysis tasks, which have the potential of directly affecting clinical decision-making processes. These advanced approaches include inference of molecular features, prediction of survival and end-to-end prediction of therapy response. Predictions made by such DL systems could simplify and enrich clinical decision-making, but require rigorous external validation in clinical settings.

show abstract

“…A recent pan-cancer study confirmed this finding by analyzing the histopathological images of more than 5,000 patients across 14 solid tumor types using deep learning. This study demonstrated the feasibility of identifying genetic variants, gene expression signatures, and clinical biomarkers from images 16 . There are also a small number of recent studies showing that collectively analyzing molecular and imaging data can improve prediction.…”

mentioning

confidence: 84%

Histopathological imaging features- versus molecular measurements-based cancer prognosis modeling

Zhang

Fan

Zhong

et al. 2020

Sci Rep

View full text Add to dashboard Cite

For lung and many other cancers, prognosis is essentially important, and extensive modeling has been carried out. Cancer is a genetic disease. In the past 2 decades, diverse molecular data (such as gene expressions and DNA mutations) have been analyzed in prognosis modeling. More recently, histopathological imaging data, which is a “byproduct” of biopsy, has been suggested as informative for prognosis. In this article, with the TCGA LUAD and LUSC data, we examine and directly compare modeling lung cancer overall survival using gene expressions versus histopathological imaging features. High-dimensional penalization methods are adopted for estimation and variable selection. Our findings include that gene expressions have slightly better prognostic performance, and that most of the gene expressions are weakly correlated imaging features. This study may provide additional insight into utilizing the two types of important data in cancer prognosis modeling and into lung cancer overall survival.

show abstract

Pan-cancer image-based detection of clinically actionable genetic alterations

Abstract: This is a repository copy of Pan-cancer image-based detection of clinically actionable genetic alterations.

Cited by 441 publications

References 54 publications

Clinical-Grade Detection of Microsatellite Instability in Colorectal Tumors by Deep Learning

Clinical-Grade Detection of Microsatellite Instability in Colorectal Tumors by Deep Learning

Deep learning in cancer pathology: a new generation of clinical biomarkers

Histopathological imaging features- versus molecular measurements-based cancer prognosis modeling

Contact Info

Product

Resources

About