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

and tluedde@ukaachen.de 34 35 Precision treatment of cancer relies on genetic alterations which are diagnosed by molecular 36 biology assays. 1 These tests can be a bottleneck in oncology workflows because of high turna-37 round time, tissue usage and costs. 2 Here, we show that deep learning can predict point muta-38 tions, molecular tumor subtypes and immune-related gene expression signatures 3,4 directly 39 from routine histological images of tumor tissue. We developed and systematically optimized 40 a one-stop-shop workflow and applied it to more than 4000 patients with breast 5 , colon and 41 rectal 6 , head and neck 7 , lung 8,9 , pancreatic 10 , prostate 11 cancer, melanoma 12 and gastric 13 can-42 cer. Together, our findings show that a single deep learning algorithm can predict clinically ac-43 tionable alterations from routine histology data. Our method can be implemented on mobile 44 hardware 14 , potentially enabling point-of-care diagnostics for personalized cancer treatment 45 in individual patients. 46 Clinical guidelines recommend molecular testing of tumor tissue for most patients with advanced 47 209 The results are in part based upon data generated by the TCGA Research Network: http://can-210 cergenome.nih.gov/. Our funding sources are as follows. J.N.K.: RWTH University Aachen (START 211

No abstract

Background Response to immunotherapy in gastric cancer is associated with microsatellite instability (or mismatch repair deficiency) and Epstein-Barr virus (EBV) positivity. We therefore aimed to develop and validate deep learningbased classifiers to detect microsatellite instability and EBV status from routine histology slides. MethodsIn this retrospective, multicentre study, we collected tissue samples from ten cohorts of patients with gastric cancer from seven countries (South Korea, Switzerland, Japan, Italy, Germany, the UK and the USA). We trained a deep learning-based classifier to detect microsatellite instability and EBV positivity from digitised, haematoxylin and eosin stained resection slides without annotating tumour containing regions. The performance of the classifier was assessed by within-cohort cross-validation in all ten cohorts and by external validation, for which we split the cohorts into a five-cohort training dataset and a five-cohort test dataset. We measured the area under the receiver operating curve (AUROC) for detection of microsatellite instability and EBV status. Microsatellite instability and EBV status were determined to be detectable if the lower bound of the 95% CI for the AUROC was above 0•5. FindingsAcross the ten cohorts, our analysis included 2823 patients with known microsatellite instability status and 2685 patients with known EBV status. In the within-cohort cross-validation, the deep learning-based classifier could detect microsatellite instability status in nine of ten cohorts, with AUROCs ranging from 0•597 (95% CI 0•522-0•737) to 0•836 (0•795-0•880) and EBV status in five of eight cohorts, with AUROCs ranging from 0•819 (0•752-0•841) to 0•897 (0•513-0•966). Training a classifier on the pooled training dataset and testing it on the five remaining cohorts resulted in high classification performance with AUROCs ranging from 0•723 (95% CI 0•676-0•794) to 0•863 (0•747-0•969) for detection of microsatellite instability and from 0•672 (0•403-0•989) to 0•859 (0•823-0•919) for detection of EBV status. Interpretation Classifiers became increasingly robust when trained on pooled cohorts. After prospective validation, this deep learning-based tissue classification system could be used as an inexpensive predictive biomarker for immunotherapy in gastric cancer. Funding German Cancer Aid and German Federal Ministry of Health.

No abstract