The early detection and accurate histopathological diagnosis of gastric cancer increase the chances of successful treatment. The worldwide shortage of pathologists offers a unique opportunity for the use of artificial intelligence assistance systems to alleviate the workload and increase diagnostic accuracy. Here, we report a clinically applicable system developed at the Chinese PLA General Hospital, China, using a deep convolutional neural network trained with 2,123 pixel-level annotated H&E-stained whole slide images. The model achieves a sensitivity near 100% and an average specificity of 80.6% on a real-world test dataset with 3,212 whole slide images digitalized by three scanners. We show that the system could aid pathologists in improving diagnostic accuracy and preventing misdiagnoses. Moreover, we demonstrate that our system performs robustly with 1,582 whole slide images from two other medical centres. Our study suggests the feasibility and benefits of using histopathological artificial intelligence assistance systems in routine practice scenarios.

BackgroundSquamous cell carcinomas (SCC) account for approximately 30% of non-small cell lung cancer. Investigation of the mechanism of invasion and metastasis of lung SCC will be of great help for the development of meaningful targeted therapeutics. This study is intended to understand whether the activation of Hedgehog (Hh) pathway is involved in lung SCC, and whether activated Hh signaling regulates metastasis through epithelial-mesenchymal transition (EMT) in lung SCC.MethodsTwo cohorts of patients with lung SCC were studied. Protein expression was examined by immunohistochemistry, Western blot, or immunofluorescence. Protein expression levels in tissue specimens were scored and correlations were analyzed. Vismodegib and a Gli inhibitor were used to inhibit Shh/Gli activity, and recombinant Shh proteins were used to stimulate the Hh pathway in lung SCC cell lines. Cell migration assay was performed in vitro.ResultsShh/Gli pathway components were aberrantly expressed in lung SCC tissue samples. Gli1 expression was reversely associated with the expression of EMT markers E-Cadherin and β-Catenin in lung SCC specimens. Inhibition of the Shh/Gli pathway suppressed migration and up-regulated E-Cadherin expression in lung SCC cells. Stimulation of the pathway increased migration and down-regulated E-Cadherin expression in lung SCC cells.ConclusionsOur results suggested that the Shh/Gli pathway may be critical for lung SCC recurrence, metastasis and resistance to chemotherapy. Inhibition of the Shh/Gli pathway activity/function is a potential therapeutic strategy for the treatment of lung SCC patients.

No abstract

No abstract