RESUMO
BACKGROUND: Tumor-infiltrating lymphocytes (TILs) are clinically significant in triple-negative breast cancer (TNBC). Although a standardized methodology for visual TILs assessment (VTA) exists, it has several inherent limitations. We established a deep learning-based computational TIL assessment (CTA) method broadly following VTA guideline and compared it with VTA for TNBC to determine the prognostic value of the CTA and a reasonable CTA workflow for clinical practice. METHODS: We trained three deep neural networks for nuclei segmentation, nuclei classification and necrosis classification to establish a CTA workflow. The automatic TIL (aTIL) score generated was compared with manual TIL (mTIL) scores provided by three pathologists in an Asian (n = 184) and a Caucasian (n = 117) TNBC cohort to evaluate scoring concordance and prognostic value. FINDINGS: The intraclass correlations (ICCs) between aTILs and mTILs varied from 0.40 to 0.70 in two cohorts. Multivariate Cox proportional hazards analysis revealed that the aTIL score was associated with disease free survival (DFS) in both cohorts, as either a continuous [hazard ratio (HR)=0.96, 95% CI 0.94-0.99] or dichotomous variable (HR=0.29, 95% CI 0.12-0.72). A higher C-index was observed in a composite mTIL/aTIL three-tier stratification model than in the dichotomous model, using either mTILs or aTILs alone. INTERPRETATION: The current study provides a useful tool for stromal TIL assessment and prognosis evaluation for patients with TNBC. A workflow integrating both VTA and CTA may aid pathologists in performing risk management and decision-making tasks. FUNDING: National Natural Science Foundation of China, Guangdong Medical Research Foundation, Guangdong Natural Science Foundation.
Assuntos
Diagnóstico por Computador/métodos , Linfócitos do Interstício Tumoral/patologia , Guias de Prática Clínica como Assunto , Neoplasias de Mama Triplo Negativas/diagnóstico , Aprendizado Profundo , Diagnóstico por Computador/normas , Feminino , Humanos , Variações Dependentes do Observador , Patologistas/normas , Patologistas/estatística & dados numéricosRESUMO
OBJECTS: Nasopharyngeal carcinoma (NPC) incidence exhibits a remarkable sex disparity, with higher risk among males. Whether this pattern can be partly explained by female reproductive history is unclear. METHODS: A population-based case-control study of NPC was conducted in southern China between 2010 and 2014, including 674 histopathologically verified female NPC cases and 690 female controls randomly selected from population-based registries. Odds ratios (ORs) and 95% confidence intervals (CIs) were estimated using logistic regression after adjusting for potential confounders. RESULTS: Women who had 3, 4, or ≥5 pregnancies compared with 2 pregnancies were at significantly increased risk for NPC (ORs 1.56, 1.45 and 1.88, respectively). History of deliveries was similarly associated with a greater risk of NPC. These positive associations were more prominent in women who were younger than 50â¯years, had less than 10â¯years of education, or were white-collar workers. Increasing time since menopause was associated with a diminished NPC risk (Ptrendâ¯=â¯0.010). Women more than 15â¯years after menopause had a 0.35-fold (95% CI: 0.16-0.75) NPC risk compared with those 0-3â¯years after menopause. CONCLUSION: Contrary to our hypothesis, a history of pregnancy or delivery increased the risk of NPC and the risk decreased with increasing time since menopause. However, the non-linear relationship and no consistent risk patterns across strata indicate that the observed associations are unlikely to be causal, and may at least partially be ascribed to residual confounding by socioeconomic factors.