Precise and automated lung cancer cell classification using deep neural network with multiscale features and model distillation.

Lung diseases globally impose a significant pathological burden and mortality rate, particularly the differential diagnosis between adenocarcinoma, squamous cell carcinoma, and small cell lung carcinoma, which is paramount in determining optimal treatment strategies and improving clinical prognoses. Faced with the challenge of improving diagnostic precision and stability, this study has developed an innovative deep learning-based model. This model employs a Feature Pyramid Network (FPN) and Squeeze-and-Excitation (SE) modules combined with a Residual Network (ResNet18), to enhance the processing capabilities for complex images and conduct multi-scale analysis of each channel's importance in classifying lung cancer. Moreover, the performance of the model is further enhanced by employing knowledge distillation from larger teacher models to more compact student models. Subjected to rigorous five-fold cross-validation, our model outperforms existing models on all performance metrics, exhibiting exceptional diagnostic accuracy. Ablation studies on various model components have verified that each addition effectively improves model performance, achieving an average accuracy of 98.84% and a Matthews Correlation Coefficient (MCC) of 98.83%. Collectively, the results indicate that our model significantly improves the accuracy of disease diagnosis, providing physicians with more precise clinical decision-making support.

Identification and validation of an epithelial-mesenchymal transition-related lncRNA pairs prognostic model for gastric cancer.

Background: Gastric cancer (GC) is a common malignancy. A mounting body of evidence has demonstrated the correlation between GC prognosis and epithelial-mesenchymal transition (EMT)-related biomarkers. This research constructed an available model using EMT-related long noncoding RNA (lncRNA) pairs to predict the survival for GC patients. Methods: The transcriptome data along with clinical information on GC samples were derived from The Cancer Genome Atlas (TCGA). Differentially expressed EMT-related lncRNAs were acquired and paired. Univariate and least absolute shrinkage and selection operator (LASSO) Cox regression analyses were applied to filter lncRNA pairs, and the risk model was built to investigate its effect on the prognosis of GC patients. Then, the areas under the receiver operating characteristic curves (AUCs) were calculated and the cutoff point for distinguishing low- or high-risk GC patients was identified. And the predictive ability of this model was tested in the GSE62254. Furthermore, the model was evaluated from the perspectives of survival time, clinicopathological parameters, infiltration of immunocytes, and functional enrichment analysis. Results: The risk model was built by using the identified twenty EMT-related lncRNA pairs, and it was not necessary to know the specific expression level of each lncRNA. Survival analysis pointed out that GC patients with high risk had poorer outcomes. Additionally, this model could be an independent prognostic variable for GC patients. The accuracy of the model was also verified in the testing set. Conclusions: The new predictive model constructed here is composed of EMT-related lncRNA pairs, with reliable prognostic values, and can be utilized to predict the survival of GC.

A novel prognostic model based on epithelial-mesenchymal transition-related genes predicts patient survival in gastric cancer.

BACKGROUND: Gastric cancer (GC) represents a major malignancy and is the third deathliest cancer globally. Several lines of evidence indicate that the epithelial-mesenchymal transition (EMT) has a critical function in the development of gastric cancer. Although plentiful molecular biomarkers have been identified, a precise risk model is still necessary to help doctors determine patient prognosis in GC. METHODS: Gene expression data and clinical information for GC were acquired from The Cancer Genome Atlas (TCGA) database and 200 EMT-related genes (ERGs) from the Molecular Signatures Database (MSigDB). Then, ERGs correlated with patient prognosis in GC were assessed by univariable and multivariable Cox regression analyses. Next, a risk score formula was established for evaluating patient outcome in GC and validated by survival and ROC curves. In addition, Kaplan-Meier curves were generated to assess the associations of the clinicopathological data with prognosis. And a cohort from the Gene Expression Omnibus (GEO) database was used for validation. RESULTS: Six EMT-related genes, including CDH6, COL5A2, ITGAV, MATN3, PLOD2, and POSTN, were identified. Based on the risk model, GC patients were assigned to the high- and low-risk groups. The results revealed that the model had good performance in predicting patient prognosis in GC. CONCLUSIONS: We constructed a prognosis risk model for GC. Then, we verified the performance of the model, which may help doctors predict patient prognosis.