Identifying immune infiltration by deep learning to assess the prognosis of patients with hepatocellular carcinoma.

BACKGROUND: The treatment situation for hepatocellular carcinoma remains critical. The use of deep learning algorithms to assess immune infiltration is a promising new diagnostic tool. METHODS: Patient data and whole slide images (WSIs) were obtained for the Xijing Hospital (XJH) cohort and TCGA cohort. We wrote programs using Visual studio 2022 with C# language to segment the WSI into tiles. Pathologists classified the tiles and later trained deep learning models using the ResNet 101V2 network via ML.NET with the TensorFlow framework. Model performance was evaluated using AccuracyMicro versus AccuracyMacro. Model performance was examined using ROC curves versus PR curves. The percentage of immune infiltration was calculated using the R package survminer to calculate the intergroup cutoff, and the Kaplan‒Meier method was used to plot the overall survival curve of patients. Cox regression was used to determine whether the percentage of immune infiltration was an independent risk factor for prognosis. A nomogram was constructed, and its accuracy was verified using time-dependent ROC curves with calibration curves. The CIBERSORT algorithm was used to assess immune infiltration between groups. Gene Ontology was used to explore the pathways of differentially expressed genes. RESULTS: There were 100 WSIs and 165,293 tiles in the training set. The final deep learning models had an AccuracyMicro of 97.46% and an AccuracyMacro of 82.28%. The AUCs of the ROC curves on both the training and validation sets exceeded 0.95. The areas under the classification PR curves exceeded 0.85, except that of the TLS on the validation set, which might have had poor results (0.713) due to too few samples. There was a significant difference in OS between the TIL classification groups (p < 0.001), while there was no significant difference in OS between the TLS groups (p = 0.294). Cox regression showed that TIL percentage was an independent risk factor for prognosis in HCC patients (p = 0.015). The AUCs according to the nomogram were 0.714, 0.690, and 0.676 for the 1-year, 2-year, and 5-year AUCs in the TCGA cohort and 0.756, 0.797, and 0.883 in the XJH cohort, respectively. There were significant differences in the levels of infiltration of seven immune cell types between the two groups of samples, and gene ontology showed that the differentially expressed genes between the groups were immune related. Their expression levels of PD-1 and CTLA4 were also significantly different. CONCLUSION: We constructed and tested a deep learning model that evaluates the immune infiltration of liver cancer tissue in HCC patients. Our findings demonstrate the value of the model in assessing patient prognosis, immune infiltration and immune checkpoint expression levels.

Machine learning was used to predict risk factors for distant metastasis of pancreatic cancer and prognosis analysis.

BACKGROUND: The mechanisms of distant metastasis in pancreatic cancer (PC) have not been elucidated, and this study aimed to explore the risk factors affecting the metastasis and prognosis of metastatic patients and to develop a predictive model. METHOD: Clinical data from patients meeting criteria from 1990 to 2019 were obtained from the Surveillance, Epidemiology, and End Results (SEER) database, and two machine learning methods, random forest and support vector machine, combined with logistic regression, were used to explore risk factors influencing distant metastasis and to create nomograms. The performance of the model was validated using calibration curves and ROC curves based on the Shaanxi Provincial People's Hospital cohort. LASSO regression and Cox regression models were used to explore the independent risk factors affecting the prognosis of patients with distant PC metastases. RESULTS: We found that independent risk factors affecting PC distant metastasis were: age, radiotherapy, chemotherapy, T and N; the independent risk factors for patient prognosis were: age, grade, bone metastasis, brain metastasis, lung metastasis, radiotherapy and chemotherapy. CONCLUSION: Together, our study provides a method for risk factors and prognostic assessment for patients with distant PC metastases. The nomogram we developed can be used as a convenient individualized tool to facilitate aid in clinical decision making.

Protective effect of tertiary lymphoid structures against hepatocellular carcinoma: New findings from a genetic perspective.

Background: Tertiary lymphoid structures (TLS) have an effect on hepatocellular carcinoma (HCC), but the underlying mechanism remains to be elucidated. Methods: Intratumoral TLS (iTLS) was classified in the Cancer Genome Atlas-Liver Hepatocellular Carcinoma (TCGA-LIHC) cohort using pathological sections from the Cancer Digital Slide Archive. Univariate and multivariate Cox regression analyses were performed to validate the effect of iTLS on overall survival (OS), relapse-free survival (RFS), and disease-free survival (DFS). The genes differentially expressed between the iTLS-negative and iTLS-positive groups were analyzed in combination with sequencing data. Gene set enrichment analysis (GSEA) was used to explore the signaling pathways affected by these differentially expressed genes. The random forest algorithm was used to identify genes with the highest correlation with the iTLS in the training set. Multivariate logistic regression was used to build a model to predict iTLS in tissue samples. Spearman's correlation was used to analyze the relationship between TLS-associated chemokines and signature genes, and CIBERSORT was used to calculate immune infiltration scores. Copy number variation and its relationship with immune cell infiltration and signature genes were assessed using the gene set cancer analysis (GSCA). The Correlation R package was used for gene ontology (GO), disease ontology (DO), and gene mutation analyses. The GSCA was used for drug sensitivity analysis. LASSO regression was used to build prognostic models, and external data were used to validate the models. Results: There were 218 positive and 146 negative samples for iTLS. iTLS was significantly associated with better RFS and DFS according to Cox regression analysis. Twenty signature genes that were highly associated with iTLS positivity were identified. GO and mutation analyses revealed that the signature genes were associated with immunity. Most signature genes were sensitive to immune checkpoint inhibitors. Risk scores calculated using a characteristic gene-based prognostic model were found to be an independent prognostic factor for OS. Conclusions: The improvement of RFS in HCC by iTLS was not limited to the early period as previously reported. iTLS improved DFS in patients. Characteristic genes are closely related to the formation of iTLS and TLS chemokines in HCC. These genes are closely related to immunity in terms of cellular infiltration, biological functions, and signaling pathways. Most are sensitive to immune checkpoint inhibitors, and their expression levels can affect prognosis.

Tertiary Lymphatic Structures in Primary Hepatic Carcinoma: Controversy Cannot Overshadow Hope.

Tertiary lymphoid structures (TLSs) are organized aggregates of immune cells found in the tumor microenvironment. TLS can influence primary hepatic carcinoma (PHC) occurrence and have an active role in cancer. TLS can promote or inhibit the growth of PHC depending on their location, and although available findings are controversial, they suggest that TLS have a protective role in PHC tissues and a non-protective role in paracancerous tissues. In addition, the cellular composition of TLS can also influence the outcome of PHC. As an immunity marker, TLS can act as a marker of immunotherapy to predict its effect and help to identify patients who will respond well to immunotherapy. Modulation of TLS formation through the use of chemokines/cytokines, immunotherapy, or induction of high endothelial vein to interfere with tumor growth has been studied extensively in PHC and other cancers. In addition, new tools such as genetic interventions, cellular crosstalk, preoperative radiotherapy, and advances in materials science have been shown to influence the prognosis of malignant tumors by modulating TLS production. These can also be used to develop PHC treatment.