BACKGROUND: An artificial intelligence system of Faster Region-based Convolutional Neural Network (Faster R-CNN) is newly developed for the diagnosis of metastatic lymph node (LN) in rectal cancer patients. The primary objective of this study was to comprehensively verify its accuracy in clinical use. METHODS: Four hundred fourteen patients with rectal cancer discharged between January 2013 and March 2015 were collected from 6 clinical centers, and the magnetic resonance imaging data for pelvic metastatic LNs of each patient was identified by Faster R-CNN. Faster R-CNN based diagnoses were compared with radiologist based diagnoses and pathologist based diagnoses for methodological verification, using correlation analyses and consistency check. For clinical verification, the patients were retrospectively followed up by telephone for 36 months, with post-operative recurrence of rectal cancer as a clinical outcome; recurrence-free survivals of the patients were compared among different diagnostic groups, by methods of Kaplan-Meier and Cox hazards regression model. RESULTS: Significant correlations were observed between any 2 factors among the numbers of metastatic LNs separately diagnosed by radiologists, Faster R-CNN and pathologists, as evidenced by rradiologist-Faster R-CNN of 0.912, rPathologist-radiologist of 0.134, and rPathologist-Faster R-CNN of 0.448 respectively. The value of kappa coefficient in N staging between Faster R-CNN and pathologists was 0.573, and this value between radiologists and pathologists was 0.473. The 3 groups of Faster R-CNN, radiologists and pathologists showed no significant differences in the recurrence-free survival time for stage N0 and N1 patients, but significant differences were found for stage N2 patients. CONCLUSION: Faster R-CNN surpasses radiologists in the evaluation of pelvic metastatic LNs of rectal cancer, but is not on par with pathologists. TRIAL REGISTRATION www.chictr.org.cn (No. ChiCTR-DDD-17013842).
Adult ; Aged ; Aged, 80 and over ; Artificial Intelligence ; Female ; Humans ; Lymphatic Metastasis ; Male ; Middle Aged ; Neoplasm Recurrence, Local ; Neoplasm Staging ; Neural Networks (Computer) ; Pathologists ; Radiologists ; Rectal Neoplasms ; diagnostic imaging ; mortality ; pathology

Objective: To analyze and compare the distribution of the high-risk population of upper gastrointestinal (UGI) cancer and the factors influencing the compliance rate of endoscopic screening in urban China and rural China. Methods: From 2015 to 2017, an epidemiological survey was conducted on residents aged 40-69 in two rural areas (Luoshan county of Henan province, Sheyang county of Jiangsu province) and two urban areas (Changsha city of Hunan province, Harbin city of Heilongjiang province). As a result, high-risk individuals were recommended for endoscopic screening. Chi-square χ(2) test was used to compare the high-risk rate of UGI cancer between urban and rural residents. In addition, the multivariate logistic regression model was used to analyze the factors influencing the compliance rate of endoscopic screening. Results: A total of 48, 310 residents aged 40-69 were enrolled in this study, including 22 870 (47.34%) residents from rural areas and 25 440 (52.66%) residents from urban areas. A total of 23 532 individuals were assessed with a high risk of UGI cancer, with an overall risk rate of 48.71%. A higher proportion of participants with high risk was observed in rural China (56.17%, 12 845/22 870) than in urban China (42.01%, 10 687/25 440). A total of 10 971 high-risk individuals with UGI cancer participated in endoscopic screening, with an overall compliance rate of 46.62% (10 971/23 532), 45.15% (5 799/12 845) in rural China, and 48.40% (5 172/10 687) in urban China. In rural population, the compliance rate of endoscopic screening was higher in those of females, aged 50-69 years, primary school education or above, high income, a family history of UGI cancer, history of gastric and duodenal ulcer, history of reflux esophagitis, and history of superficial gastritis, but lower in smokers (P<0.05). Among the urban population, the compliance rate of endoscopic screening was higher in those aged 40-49 years, uneducated, low income, family history of UGI cancer, history of reflux esophagitis, history of superficial gastritis, but lower in smokers (P<0.05). Conclusions: The proportion of participants with high risk of UGI cancer in rural areas is higher than that of urban areas. The compliance rates of endoscopic screening in urban and rural areas are low, and influencing factors of endoscopic screening exhibit some differences in rural China and urban China.
China/epidemiology* ; Early Detection of Cancer ; Esophagitis, Peptic ; Female ; Gastritis ; Gastrointestinal Neoplasms/epidemiology* ; Humans ; Rural Population ; Urban Population

Objective: To depict gastric cancer burden trends globally and analyze geographical and socioeconomic disparities among different countries and territories. Methods: We extracted the data from Global Burden of Disease 2019 Database. We conducted the Joinpoint regression and calculated the average annual percent change (AAPC) and corresponding 95% confidence interval (CI) for age-standardized gastric cancer incidence and mortality from 1990 to 2019. Linear regression was performed to measure the association of sociodemographic index (SDI) with each country's gastric cancer incidence and mortality AAPC. We applied the age-period-cohort analysis to assess the cohort effect on gastric cancer incidence and mortality. Results: The AAPCs for gastric cancer age-standardized incidence and mortality rates from 1990 to 2019 were -1.27% (95% CI: -1.43%, -1.11%) and -1.87% (95% CI: -2.01%, -1.72%), respectively. SDI levels were negatively associated with AAPCs, which means that countries with higher SDI had higher AAPC (P<0.001). The decrease of gastric cancer burden in countries with low or medium SDI levels was slower than that globally. The age-period-cohort analysis indicated that countries with higher SDI levels had more apparent decline in birth cohort effects from 1900 to 1999. Conclusions: Countries with different socioeconomic levels have various decreasing rates for gastric cancer incidence and deaths. Countries with higher SDI levels have higher declining rates for gastric cancer burden.
Global Burden of Disease ; Global Health ; Humans ; Incidence ; Quality-Adjusted Life Years ; Stomach Neoplasms/epidemiology*