This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
Molecular profiling is central in cancer precision medicine but remains costly and is based on tumor average profiles. Morphological patterns observable in histopathology sections from tumors are determined by the underlying molecular phenotype and therefore have the potential to be exploited for prediction of molecular phenotypes. We report here the first transcriptome-wide Expression-Morphology (EMO) analysis in breast cancer, where individual deep convolutional neural networks (CNN) were optimized and validated for prediction of mRNA expression in 17,695 genes from hematoxylin and eosin-stained whole slide images. Predicted expressions in 9,334 (52.75%) genes were significantly associated with RNA-sequencing estimates. We also demonstrated successful prediction of an mRNAbased proliferation score with established clinical value. The results were validated in independent internal and external test datasets. Predicted spatial intra-tumor variabilities in expression were validated through spatial transcriptomics profiling. These results suggest that EMO provides a cost-efficient and scalable approach to predict both tumor average and intratumor spatial expression from histopathology images.
BackgroundThe relationship between recurrent major depression (MD) in women and suicidality is complex. We investigated the extent to which patients who suffered with various forms of suicidal symptomatology can be distinguished from those subjects without such symptoms.MethodWe examined the clinical features of the worst episode in 1970 Han Chinese women with recurrent DSM-IV MD between the ages of 30 and 60 years from across China. Student's t tests, and logistic and multiple logistic regression models were used to determine the association between suicidality and other clinical features of MD.ResultsSuicidal symptomatology is significantly associated with a more severe form of MD, as indexed by both the number of episodes and number of MD symptoms. Patients reporting suicidal thoughts, plans or attempts experienced a significantly greater number of stressful life events. The depressive symptom most strongly associated with lifetime suicide attempt was feelings of worthlessness (odds ratio 4.25, 95% confidence interval 2.9–6.3). Excessive guilt, diminished concentration and impaired decision-making were also significantly associated with a suicide attempt.ConclusionsThis study contributes to the existing literature on risk factors for suicidal symptomatology in depressed women. Identifying specific depressive symptoms and co-morbid psychiatric disorders may help improve the clinical assessment of suicide risk in depressed patients. These findings could be helpful in identifying those who need more intense treatment strategies in order to prevent suicide.
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.