Deep learning framework for comprehensive molecular and prognostic stratifications of triple-negative breast cancer.

Triple-negative breast cancer (TNBC) is the most challenging breast cancer subtype. Molecular stratification and target therapy bring clinical benefit for TNBC patients, but it is difficult to implement comprehensive molecular testing in clinical practice. Here, using our multi-omics TNBC cohort (N = 425), a deep learning-based framework was devised and validated for comprehensive predictions of molecular features, subtypes and prognosis from pathological whole slide images. The framework first incorporated a neural network to decompose the tissue on WSIs, followed by a second one which was trained based on certain tissue types for predicting different targets. Multi-omics molecular features were analyzed including somatic mutations, copy number alterations, germline mutations, biological pathway activities, metabolomics features and immunotherapy biomarkers. It was shown that the molecular features with therapeutic implications can be predicted including the somatic PIK3CA mutation, germline BRCA2 mutation and PD-L1 protein expression (area under the curve [AUC]: 0.78, 0.79 and 0.74 respectively). The molecular subtypes of TNBC can be identified (AUC: 0.84, 0.85, 0.93 and 0.73 for the basal-like immune-suppressed, immunomodulatory, luminal androgen receptor, and mesenchymal-like subtypes respectively) and their distinctive morphological patterns were revealed, which provided novel insights into the heterogeneity of TNBC. A neural network integrating image features and clinical covariates stratified patients into groups with different survival outcomes (log-rank P < 0.001). Our prediction framework and neural network models were externally validated on the TNBC cases from TCGA (N = 143) and appeared robust to the changes in patient population. For potential clinical translation, we built a novel online platform, where we modularized and deployed our framework along with the validated models. It can realize real-time one-stop prediction for new cases. In summary, using only pathological WSIs, our proposed framework can enable comprehensive stratifications of TNBC patients and provide valuable information for therapeutic decision-making. It had the potential to be clinically implemented and promote the personalized management of TNBC.

[Study on the health status and affecting factors among people living in the surveillance sites of three Gorges Reservoir Areas, in 2007].

OBJECTIVE: To understand the health status and potential impact resulted in the second stage of Three Gorges Reservoir Areas sluicing. METHODS: Data were collected on deaths, prevalence rates of infectious and endemic diseases, as well as on vector surveillance through the project entitled 'Three Gorges Population Health Survey System'. RESULTS: The main causes of death in the population living in the Three Gorges Reservoir Areas would include: circulatory system diseases, tumors, respiratory system diseases, injuries/poison and digestive system diseases. The number of deaths caused by the above said five kind of diseases accounted for 90.94% of the total number of deaths. The prevalence rates on Water-born diseases related to the sluicing of reservoir and zoonosis-borne diseases related to the changes of vectors were still low. The indoor and outdoor densities of rodents were 3.11% and 3.16%, both were higher than that in 2006 but lower than the average numbers in the five years prior to the sluicing. The constituent ratio of Apodemus agrarius had constantly risen since 2006. The density of mosquitoes found in livestock barns and human households was higher than that in 2006 but lower than the average number of the five-year studies prior to the sluicing. CONCLUSION: Environment change after the sluicing of the Three Gorges Reservoir Areas did not seem to have obvious impact on the health status of the people living in the areas. However, to strengthen the surveillance on the biological features of the vectors which might have related to the transmission of diseases would be highly recommended.

[Estimation on the level of birth and death rates of population in the three gorges area by means of capture-mark-recapture method].

OBJECTIVE: To evaluate quality of surveillance and emendate rates of birth and death of population of the Three Gorges area. METHODS: Data on the two samples collected were designed based on principle of capture-recapture method. An investigation of missing report of birth and death was conducted in 7061 families selected through stratified random sampling method. We collected and registered the data of birth and death in every family investigated and checked with correlative records reported in disease surveillance system of the Three Gorges area. The missing report rates and the 95% confidence intervals of birth rate and death rate were calculated. RESULTS: The underreporting rates of birth and death were 13.91% and 15.60% and death of infant was 33.33%. The emended birth rate was 8.92 per thousandth and the 95% confidence interval of birth rate was 8.38 per thousandth-9.45 per thousandth. The emended report rate of death was 6.88 per thousandth and the collectivity 95% confidence interval was 6.37%-7.38 per thousandth. CONCLUSION: Results showed that the quality of birth and death in the disease surveillance reporting system of Three Gorges area was competent to the quality level of the standard set for national disease surveillance system. The birth and death rates of population in the Three Gorges area were under 10.00 per thousandth.