Kanran Wang

Association between ultra-processed food consumption and lung cancer risk: a population-based cohort study

Background The evidence on associations between ultra-processed foods (UPF) and lung cancer risk is limited and inconsistent. Research question Are UPF associated with an increased risk of lung cancer, non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC)？ Methods Data of participants in this study were collected from the Prostate, Lung, Colorectal and Ovarian (PLCO) Cancer Screening Trial. Dietary intakes were assessed through a validated diet history questionnaire. These foods were categorised using the NOVA classification according to the degree of processing in the PLCO Cancer Screening Cohort. All cases of incident lung cancer were pathologically verified. Multivariable Cox regression was used to assess the association between consumption of UPF and lung cancer after adjustment for various potential confounders, including key risk factors related to lung cancer and overall diet quality. Results A total of 1706 cases of lung cancer cases, including 1473 NSCLC and 233 SCLC, were identified during a mean follow-up of 12.2 years among 101 732 adults (mean age 62.5 years). After multivariable adjustments, individuals in the highest quarters for UPF consumption had a higher risk of lung cancer (HR=1.41, 95% CI 1.22 to 1.60), NSCLC (HR=1.37, 95% CI 1.20 to 1.58) and SCLC (HR=1.44, 95% CI 1.03 to 2.10) compared with those in the lowest quarter. These results remained statistically significant after a large range of subgroup and sensitivity analyses. Conclusions Higher consumption of UPF is associated with an increased risk of lung cancer, NSCLC and SCLC. Although additional research in other populations and settings is warranted, these findings suggest the healthy benefits of limiting UPF.

HiCervix: An Extensive Hierarchical Dataset and Benchmark for Cervical Cytology Classification

Cervical cytology is a critical screening strategy for early detection of pre-cancerous and cancerous cervical lesions. The challenge lies in accurately classifying various cervical cytology cell types. Existing automated cervical cytology methods are primarily trained on databases covering a narrow range of coarse-grained cell types, which fail to provide a comprehensive and detailed performance analysis that accurately represents real-world cytopathology conditions. To overcome these limitations, we introduce HiCervix, the most extensive, multi-center cervical cytology dataset currently available to the public. HiCervix includes 40,229 cervical cells from 4,496 whole slide images, categorized into 29 annotated classes. These classes are organized within a three-level hierarchical tree to capture fine-grained subtype information. To exploit the semantic correlation inherent in this hierarchical tree, we propose HierSwin, a hierarchical vision transformer-based classification network. HierSwin serves as a benchmark for detailed feature learning in both coarse-level and fine-level cervical cancer classification tasks. In our comprehensive experiments, HierSwin demonstrated remarkable performance, achieving 92.08% accuracy for coarse-level classification and 82.93% accuracy averaged across all three levels. When compared to board-certified cytopathologists, HierSwin achieved high classification performance (0.8293 versus 0.7359 averaged accuracy), highlighting its potential for clinical applications. This newly released HiCervix dataset, along with our benchmark HierSwin method, is poised to make a substantial impact on the advancement of deep learning algorithms for rapid cervical cancer screening and greatly improve cancer prevention and patient outcomes in real-world clinical settings.