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

No abstract

Previous research has suggested that the expression of proteins related to the Warburg effect may have prognostic value in colorectal cancer (CRC), but results remain inconsistent. Our objective was to investigate the relationship between Warburg-subtypes and patient survival in a large population-based series of CRC patients. In the present study, we investigated the expression of six proteins related to the Warburg effect (LDHA, GLUT1, MCT4, PKM2, p53, PTEN) by immunohistochemistry on tissue microarrays (TMAs) from 2,399 incident CRC patients from the prospective Netherlands Cohort Study. Expression levels of the six proteins were combined into a pathway-based sum-score and patients were categorised into three Warburg-subtypes (low/moderate/high). The associations between Warburgsubtypes and CRC-specific and overall survival were investigated using Kaplan-Meier curves and Cox regression models. CRC patients were classified as Warburg-low (n = 695, 29.0%), Warburg-moderate (n = 858, 35.8%) or Warburg-high (n = 841, 35.1%). Patients with Warburg-high CRC had the poorest CRC-specific [hazard ratio (HR) 1.17; 95% CI 1.00-1.38] and overall survival (HR 1.19; 95% CI 1.05-1.35), independent of known prognostic factors. In stratified analyses, this was particularly true for patients with tumour-node-metastasis (TNM) stage III CRC (HR CRC-specific 1.45; 95% CI 1.10-1.92 and HR overall 1.47; 95% CI 1.15-1.87), and cancers located in the rectum (HR overall 1.56; 95% CI 1.15-2.13). To our knowledge, this is the first study to identify the prognostic value of immunohistochemistry-based Warburg-subtypes in CRC. Our data suggest that Warburg-subtypes are related to potentially important differences in CRC survival. Further research is required to validate our findings and to investigate the potential clinical utility of these Warburg-subtypes in CRC.

Deep learning can detect microsatellite instability (MSI) from routine histology images in colorectal cancer (CRC). However, ethical and legal barriers impede sharing of images and genetic data, hampering development of new algorithms for detection of MSI and other biomarkers. We hypothesized that histology images synthesized by conditional generative adversarial networks (CGANs) retain information about genetic alterations. To test this, we developed a ‘histology CGAN’ which was trained on 256 patients (training cohort 1) and 1457 patients (training cohort 2). The CGAN synthesized 10 000 synthetic MSI and non‐MSI images which contained a range of tissue types and were deemed realistic by trained observers in a blinded study. Subsequently, we trained a deep learning detector of MSI on real or synthetic images and evaluated the performance of MSI detection in a held‐out set of 142 patients. When trained on real images from training cohort 1, this system achieved an area under the receiver operating curve (AUROC) of 0.742 [0.681, 0.854]. Training on the larger cohort 2 only marginally improved the AUROC to 0.757 [0.707, 0.869]. Training on purely synthetic data resulted in an AUROC of 0.743 [0.658, 0.801]. Training on both real and synthetic data further increased AUROC to 0.777 [0.715, 0.821]. We conclude that synthetic histology images retain information reflecting underlying genetic alterations in colorectal cancer. Using synthetic instead of real images to train deep learning systems yields non‐inferior classifiers. This approach can be used to create large shareable data sets or to augment small data sets with rare molecular features. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons, Ltd. on behalf of The Pathological Society of Great Britain and Ireland.

Early-life (childhood to adolescence) energy balance-related factors (height, energy restriction, BMI) have been associated with adult colorectal cancer (CRC) risk.Warburg-effect activation via PI3K/Akt-signaling might explain this link. We investigated whether early-life energy balance-related factors were associated with risk of Warburg-subtypes in CRC. We used immunohistochemistry for six proteins involved in the Warburg-effect (LDHA, GLUT1, MCT4, PKM2, P53, and PTEN) on tissue microarrays of 2399 incident CRC cases from the prospective Netherlands Cohort Study (NLCS). Expression levels of all proteins were combined into a pathway-based sum score and categorized into three Warburg-subtypes (Warburg-low/-moderate/high). Multivariable Cox-regression analyses were used to estimate associations of height, energy restriction proxies (exposure to Dutch Hunger Winter; Second World War [WWII]; Economic Depression) and adolescent BMI with Warburg-subtypes in CRC. Height was positively associated with colon cancer in men, regardless of Warburg-subtypes, and with Warburg-low colon and Warburg-moderate rectal cancer in women. Energy restriction during the Dutch Hunger Winter was inversely associated with colon cancer in men, regardless of Warburg-subtypes. In women, energy restriction during the Hunger Winter and WWII was inversely associated with Warburg-low colon cancer, whereas energy restriction during the Economic Depression was positively associated with Warburg-high colon cancer. Adolescent BMI was positively associated with Warburg-high colon cancer in men, and Warburgmoderate rectal cancer in women. In conclusion, the Warburg-effect seems to be involved in associations of adolescent BMI with colon cancer in men, and of energy restriction during the Economic Depression with colon cancer in women. Further research is needed to validate these results.