This is a repository copy of Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer.
Cancer cells induce a set of adaptive response pathways to survive in the face of stressors due to inadequate vascularization1. One such adaptive pathway is the unfolded protein (UPR) or endoplasmic reticulum (ER) stress response mediated in part by the ER-localized transmembrane sensor IRE12 and its substrate XBP13. Previous studies report UPR activation in various human tumors4-6, but XBP1's role in cancer progression in mammary epithelial cells is largely unknown. Triple negative breast cancer (TNBC), a form of breast cancer in which tumor cells do not express the genes for estrogen receptor, progesterone receptor, and Her2/neu, is a highly aggressive malignancy with limited treatment options7, 8. Here, we report that XBP1 is activated in TNBC and plays a pivotal role in the tumorigenicity and progression of this human breast cancer subtype. In breast cancer cell line models, depletion of XBP1 inhibited tumor growth and tumor relapse and reduced the CD44high/CD24low population. Hypoxia-inducing factor (HIF)1α is known to be hyperactivated in TNBCs 9, 10. Genome-wide mapping of the XBP1 transcriptional regulatory network revealed that XBP1 drives TNBC tumorigenicity by assembling a transcriptional complex with HIF1α that regulates the expression of HIF1α targets via the recruitment of RNA polymerase II. Analysis of independent cohorts of patients with TNBC revealed a specific XBP1 gene expression signature that was highly correlated with HIF1α and hypoxia-driven signatures and that strongly associated with poor prognosis. Our findings reveal a key function for the XBP1 branch of the UPR in TNBC and imply that targeting this pathway may offer alternative treatment strategies for this aggressive subtype of breast cancer.
SummaryBackgroundEndometriosis is a risk factor for epithelial ovarian cancer; however, whether this risk extends to all invasive histological subtypes or borderline tumours is not clear. We undertook an international collaborative study to assess the association between endometriosis and histological subtypes of ovarian cancer.MethodsData from 13 ovarian cancer case–control studies, which were part of the Ovarian Cancer Association Consortium, were pooled and logistic regression analyses were undertaken to assess the association between self-reported endometriosis and risk of ovarian cancer. Analyses of invasive cases were done with respect to histological subtypes, grade, and stage, and analyses of borderline tumours by histological subtype. Age, ethnic origin, study site, parity, and duration of oral contraceptive use were included in all analytical models.Findings13 226 controls and 7911 women with invasive ovarian cancer were included in this analysis. 818 and 738, respectively, reported a history of endometriosis. 1907 women with borderline ovarian cancer were also included in the analysis, and 168 of these reported a history of endometriosis. Self-reported endometriosis was associated with a significantly increased risk of clear-cell (136 [20·2%] of 674 cases vs 818 [6·2%] of 13 226 controls, odds ratio 3·05, 95% CI 2·43–3·84, p<0·0001), low-grade serous (31 [9·2%] of 336 cases, 2·11, 1·39–3·20, p<0·0001), and endometrioid invasive ovarian cancers (169 [13·9%] of 1220 cases, 2·04, 1·67–2·48, p<0·0001). No association was noted between endometriosis and risk of mucinous (31 [6·0%] of 516 cases, 1·02, 0·69–1·50, p=0·93) or high-grade serous invasive ovarian cancer (261 [7·1%] of 3659 cases, 1·13, 0·97–1·32, p=0·13), or borderline tumours of either subtype (serous 103 [9·0%] of 1140 cases, 1·20, 0·95–1·52, p=0·12, and mucinous 65 [8·5%] of 767 cases, 1·12, 0·84–1·48, p=0·45).InterpretationClinicians should be aware of the increased risk of specific subtypes of ovarian cancer in women with endometriosis. Future efforts should focus on understanding the mechanisms that might lead to malignant transformation of endometriosis so as to help identify subsets of women at increased risk of ovarian cancer.FundingOvarian Cancer Research Fund, National Institutes of Health, California Cancer Research Program, California Department of Health Services, Lon V Smith Foundation, European Community's Seventh Framework Programme, German Federal Ministry of Education and Research of Germany, Programme of Clinical Biomedical Research, German Cancer Research Centre, Eve Appeal, Oak Foundation, UK National Institute of Health Research, National Health and Medical Research Council of Australia, US Army Medical Research and Materiel Command, Cancer Council Tasmania, Cancer Foundation of Western Australia, Mermaid 1, Danish Cancer Society, and Roswell Park Alliance Foundation.
BackgroundFor virtually every patient with colorectal cancer (CRC), hematoxylin–eosin (HE)–stained tissue slides are available. These images contain quantitative information, which is not routinely used to objectively extract prognostic biomarkers. In the present study, we investigated whether deep convolutional neural networks (CNNs) can extract prognosticators directly from these widely available images.Methods and findingsWe hand-delineated single-tissue regions in 86 CRC tissue slides, yielding more than 100,000 HE image patches, and used these to train a CNN by transfer learning, reaching a nine-class accuracy of >94% in an independent data set of 7,180 images from 25 CRC patients. With this tool, we performed automated tissue decomposition of representative multitissue HE images from 862 HE slides in 500 stage I–IV CRC patients in the The Cancer Genome Atlas (TCGA) cohort, a large international multicenter collection of CRC tissue. Based on the output neuron activations in the CNN, we calculated a “deep stroma score,” which was an independent prognostic factor for overall survival (OS) in a multivariable Cox proportional hazard model (hazard ratio [HR] with 95% confidence interval [CI]: 1.99 [1.27–3.12], p = 0.0028), while in the same cohort, manual quantification of stromal areas and a gene expression signature of cancer-associated fibroblasts (CAFs) were only prognostic in specific tumor stages. We validated these findings in an independent cohort of 409 stage I–IV CRC patients from the “Darmkrebs: Chancen der Verhütung durch Screening” (DACHS) study who were recruited between 2003 and 2007 in multiple institutions in Germany. Again, the score was an independent prognostic factor for OS (HR 1.63 [1.14–2.33], p = 0.008), CRC-specific OS (HR 2.29 [1.5–3.48], p = 0.0004), and relapse-free survival (RFS; HR 1.92 [1.34–2.76], p = 0.0004). A prospective validation is required before this biomarker can be implemented in clinical workflows.ConclusionsIn our retrospective study, we show that a CNN can assess the human tumor microenvironment and predict prognosis directly from histopathological images.
Our study has identified key features of the histologic phenotypes of breast cancers in carriers of mutant BRCA1 and BRCA2 genes. This information may improve the classification of breast cancers in individuals with a family history of the disease and may ultimately aid in the clinical management of patients.
A B S T R A C T PurposeHuman papillomavirus type 16 (HPV16) infection is causing an increasing number of oropharyngeal cancers in the United States and Europe. The aim of our study was to investigate whether HPV antibodies are associated with head and neck cancer risk when measured in prediagnostic sera. MethodsWe identified 638 participants with incident head and neck cancers (patients; 180 oral cancers, 135 oropharynx cancers, and 247 hypopharynx/larynx cancers) and 300 patients with esophageal cancers as well as 1,599 comparable controls from within the European Prospective Investigation Into Cancer and Nutrition cohort. Prediagnostic plasma samples from patients (collected, on average, 6 years before diagnosis) and control participants were analyzed for antibodies against multiple proteins of HPV16 as well as HPV6, HPV11, HPV18, HPV31, HPV33, HPV45, and HPV52. Odds ratios (ORs) of cancer and 95% CIs were calculated, adjusting for potential confounders. All-cause mortality was evaluated among patients using Cox proportional hazards regression. Results HPV16E6 seropositivity was present in prediagnostic samples for 34.8% of patients with oropharyngeal cancer and 0.6% of controls (OR, 274; 95% CI, 110 to 681) but was not associated with other cancer sites. The increased risk of oropharyngeal cancer among HPV16 E6 seropositive participants was independent of time between blood collection and diagnosis and was observed more than 10 years before diagnosis. The all-cause mortality ratio among patients with oropharyngeal cancer was 0.30 (95% CI, 0.13 to 0.67), for patients who were HPV16 E6 seropositive compared with seronegative. ConclusionHPV16 E6 seropositivity was present more than 10 years before diagnosis of oropharyngeal cancers. J Clin Oncol 31:2708-2715. © 2013 by American Society of Clinical Oncology INTRODUCTIONHuman papillomavirus type 16 (HPV16) is recognized as a cause of virtually all cervical cancers and of a substantial proportion of other anogenital cancers and oropharyngeal cancers. 1 The association between HPV16 and cancers of the oral cavity and larynx is less clear but, if associated, the attributable proportion is small. 1 HPV16 has been associated with a rapid increase in the incidence of oropharynx cancer in some parts of the world, notably in the United States, Sweden, and Australia, where it is now responsible for more than 50% of cases.2-4 If current trends continue, the annual number of oropharyngeal cancers in the United States may soon surpass the number of cervical cancers. 2The only evidence for the temporal relationship between HPV exposure and development of head and neck cancers (HNC) comes from a study within the Nordic serum banks linked to tumor registries: a significant 14-fold increased risk for cancer of the oropharynx was reported for seropositivity to the L1 capsid protein of HPV16.5 Antibodies against HPV L1 represent cumulative past HPV infection from multiple possible anatomic sites (ie, genital, anal, or oral), are common in controls, and © 2013 by American Society o...
We combined data from 5 prospective studies to compare the death rates from common diseases of vegetarians with those of nonvegetarians with similar lifestyles. A summary of these results was reported previously; we report here more details of the findings. Data for 76172 men and women were available. Vegetarians were those who did not eat any meat or fish (n = 27808). Death rate ratios at ages 16-89 y were calculated by Poisson regression and all results were adjusted for age, sex, and smoking status. A random-effects model was used to calculate pooled estimates of effect for all studies combined. There were 8330 deaths after a mean of 10.6 y of follow-up. Mortality from ischemic heart disease was 24% lower in vegetarians than in nonvegetarians (death rate ratio: 0.76; 95% CI: 0.62, 0.94; P<0.01). The lower mortality from ischemic heart disease among vegetarians was greater at younger ages and was restricted to those who had followed their current diet for >5 y. Further categorization of diets showed that, in comparison with regular meat eaters, mortality from ischemic heart disease was 20% lower in occasional meat eaters, 34% lower in people who ate fish but not meat, 34% lower in lactoovovegetarians, and 26% lower in vegans. There were no significant differences between vegetarians and nonvegetarians in mortality from cerebrovascular disease, stomach cancer, colorectal cancer, lung cancer, breast cancer, prostate cancer, or all other causes combined.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.