Machine learning-based radiomics to distinguish pulmonary nodules between lung adenocarcinoma and tuberculosis.

BACKGROUND: Radiomics is increasingly utilized to distinguish pulmonary nodules between lung adenocarcinoma (LUAD) and tuberculosis (TB). However, it remains unclear whether different segmentation criteria, such as the inclusion or exclusion of the cavity region within nodules, affect the results. METHODS: A total of 525 patients from two medical centers were retrospectively enrolled. The radiomics features were extracted according to two regions of interest (ROI) segmentation criteria. Multiple logistic regression models were trained to predict the pathology: (1) The clinical model relied on clinical-radiological semantic features; (2) The radiomics models (radiomics+ and radiomics-) utilized radiomics features from different ROIs (including or excluding cavities); (3) the composite models (composite+ and composite-) incorporated both above. RESULTS: In the testing set, the radiomics+/- models and the composite+/- models still possessed efficient prediction performance (AUC ≥ 0.94), while the AUC of the clinical model was 0.881. In the validation set, the AUC of the clinical model was only 0.717, while that of the radiomics+/- models and the composite+/- models ranged from 0.801 to 0.825. The prediction performance of all the radiomics+/- and composite+/- models were significantly superior to that of the clinical model (p < 0.05). Whether the ROI segmentation included or excluded the cavity had no significant effect on these models (radiomics+ vs. radiomics-, composite+ model vs. composite-) (p > 0.05). CONCLUSIONS: The present study established a machine learning-based radiomics strategy for differentiating LUAD from TB lesions. The ROI segmentation including or excluding the cavity region may exert no significant effect on the predictive ability.

SH2D4A inhibits esophageal squamous cell carcinoma progression through FAK/PI3K/AKT signaling pathway.

Esophageal squamous cell carcinoma (ESCC), one of the most common malignant tumors, is now afflicting approximately 80% of patients diagnosed with esophageal cancers. The therapeutic effect and prognosis of ESCC remain inadequate due to the unusual early symptoms and rapid malignant progression. SH2 Domain containing 4 A (SH2D4A) is downregulated in malignancies and is closely associated with tumor progression. However, neither the biological functions nor the fundamental mechanisms of SH2D4A on ESCC are known. In this study, it was found that SH2D4A is downregulated in ESCC tissues and cell lines. Incorporating immunohistochemistry and clinicopathological findings, we determined that decreased SH2D4A expression was substantially associated with adverse clinical outcomes. Overexpression of SH2D4A inhibited cell proliferation and migration, whereas suppressing SH2D4A has the opposite effect. SH2D4A mechanistically inhibited cells from proliferating and migrating through the FAK/PI3K/AKT signaling pathway. Furthermore, the results of xenograft tumor growth confirmed the preceding findings. In conclusion, our findings reveal that SH2D4A is a gene which can serve as a cancer suppressor in ESCC and may inhibits the ESCC progression by interfering with the FAK/PI3K/AKT signaling pathway. SH2D4A could act as a target for diagnostic or therapeutic purpose in ESCC.

Immunocyte count combined with CT features for distinguishing pulmonary tuberculoma from malignancy among non-calcified solitary pulmonary solid nodules.

Background: Tuberculoma is the most common type of surgically removed benign solid solitary pulmonary nodule (SPN) and can lead to a high risk of misdiagnoses for clinicians. This study aimed to discuss the value of the immunocyte count combined with computed tomography (CT) features in distinguishing pulmonary tuberculoma from malignancy among non-calcified solid SPNs. Methods: Forty-eight patients with pulmonary tuberculoma and 52 patients with lung cancer were retrospectively included in our study. Univariate and multivariate analyses were conducted to screen the independent predictors. Receiver operating characteristic (ROC) analysis was performed to investigate the validity of the predictive model. Results: The univariate and multivariate analyses revealed that a coarse margin, vacuole, lobulation, pleural indentation, cluster of differentiation (CD)3+ T-lymphocyte count, and CD4+ T-lymphocyte count were independent predictors for distinguishing pulmonary tuberculoma from malignancy. The sensitivity, specificity, accuracy, and the area under the ROC curve of the model comprising the CD3+ T-lymphocyte count were 79.2%, 75%, 74.5%, and 0.845 [95% confidence interval (CI), 0.759-0.910], respectively, and those of the model involving the CD4+ T-lymphocyte count were 77.1%, 78.8%, 77.1%, and 0.857 (95% CI, 0.773-0.919), respectively. Conclusions: Immunocyte count combined with CT features is efficient in distinguishing pulmonary tuberculoma from malignancy among non-calcified solid SPNs and has applicable clinical value.

Identification of key biomarkers and immune infiltration in the thoracic acute aortic dissection by bioinformatics analysis.

BACKGROUND: Thoracic acute aortic dissection (TAAD), one of the most fatal cardiovascular diseases, leads to sudden death, however, its mechanism remains unclear. METHODS: Three Gene Expression Omnibus datasets were employed to detect differentially expressed genes (DEGs). A similar function and co-expression network was identified by weighted gene co-expression network analysis. The least absolute shrinkage and selection operator, random forest, and support vector machines-recursive feature elimination were utilized to filter diagnostic TAAD markers, and then screened markers were validated by quantitative real-time PCR and another independent dataset. CIBERSORT was deployed to analyze and evaluate immune cell infiltration in TAAD tissues. RESULTS: Twenty-five DEGs were identified and narrowed down to three after screening. Finally, two genes, SLC11A1 and FGL2, were verified by another dataset and qRT-PCR. Function analysis revealed that SLC11A1 and FGL2 play significant roles in immune-inflammatory responses. CONCLUSION: SLC11A1 and FGL2 are differently expressed in aortic dissection and may be involved in immune-inflammatory responses.

Development and Validation of a Nomogram for Predicting Overall Survival in Patients with Second Primary Small Cell Lung Cancer After Non-Small Cell Lung Cancer: A SEER-Based Study.

Background: Non-small cell lung cancer (NSCLC) survivors are at an increased risk of developing second primary malignancies, such as small cell lung cancer. This paper sought to establish a prognostic nomogram to assess overall survival (OS) in patients with second primary small cell lung cancer (SPSCLC) after NSCLC. Methods: 420 patients who developed SPSCLC after NSCLC were randomly split into the training and validation groups. A nomogram was established by stepwise regression. Area under the curve (AUC) and calibration plots were applied to assess the prognostic performance of the nomogram. Concordance index (C-index), integrated discrimination improvement (IDI), net reclassification index (NRI) and decision curve analysis (DCA) were performed to compare the nomogram with the American Joint Committee on Cancer (AJCC) 8th staging system. Survival risk classification was constructed based on the nomogram. Results: Five variables were chosen to construct the nomogram. The AUC showed that it had a satisfactory discrimination ability. All calibration plots displayed good concordance between nomogram and observation. The C-index, IDI, NRI and DCA showed the nomogram was superior to the AJCC 8th staging system. The Kaplan-Meier curves suggested huge differences in prognosis among the three risk groups. Conclusion: This study build a nomogram and risk stratification system for predicting probabilities of OS in patients with SPSCLC after NSCLC, which can help clinicians in individualized survival assessment and treatment decisions.

Construction and Integrated Analysis of Competitive Endogenous Long Non-Coding RNA Network in Thoracic Aortic Dissection.

BACKGROUND: Long non-coding RNAs (lncRNAs) can act as a competitive endogenous RNA (ceRNA) to regulate gene expression by sequestering the microRNA (miRNA). However, the lncRNA-miRNA-mRNA ceRNA network in thoracic aortic dissection (TAD) has been rarely documented. METHODS: Three Gene Expression Omnibus (GEO) datasets were used to detect differentially expressed mRNAs, miRNAs, and lncRNAs in TAD. Gene ontology and the Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were conducted for the differentially expressed mRNAs. A protein-protein interaction network for differentially expressed mRNAs was also constructed, and hub genes were identified. We established a ceRNA network of TAD based on the differentially expressed miRNAs, mRNAs and lncRNAs, and verified our results using an independent dataset and quantitative real-time PCR (qRT-PCR). RESULTS: In TAD, 267 lncRNAs, 81 miRNAs, and 346 mRNAs were identified as differentially expressed. The established ceRNA network consisted of seven lncRNA nodes, three mRNA nodes, and three miRNA nodes, and the expression of miRNAs in TAD was opposite to that of lncRNAs and mRNAs. Subsequently, an independent GEO dataset and qRT-PCR were used to validate the expression of three mRNAs. In addition, the expression differences in SLC7A5, associated miRNA and lncRNA were verified. According to gene set enrichment analysis of SLC7A5, the most significant KEGG pathway was considerably enriched in spliceosome and pentose phosphate pathway. CONCLUSION: We established a novel ceRNA regulatory network in TAD, which provides valuable information for further research in the molecular mechanisms of TAD.

Impact of ocean acidification on the early development and escape behavior of marine medaka (Oryzias melastigma).

Ocean acidification is predicted to affect a wide diversity of marine organisms. However, no studies have reported the effects of ocean acidification on Indian Ocean fish. We have used the Indian Ocean medaka (Oryzias melastigma) as a model species for a marine fish that lives in coastal waters. We investigated the impact of ocean acidification on the embryonic development and the stereotyped escape behavior (mediated by the Mauthner cell) in newly hatched larvae. Newly fertilized eggs of medaka were reared in seawater at three different partial pressures of carbon dioxide (pCO2): control at 450 µatm, moderate at 1160 µatm, and high at 1783 µatm. Hatch rates, embryonic duration, and larval malformation rates were compared and were not significantly different between the treatments and the control. In the high pCO2 group, however, the yolks of larvae were significantly smaller than in the control group, and the newly hatched larvae were significantly longer than the larvae in the control. In the moderate pCO2 group, the eye distance decreased significantly. No significantly negative growth effects were observed in the larvae when exposed to pCO2 levels that are predicted as a result of ocean acidification in the next 100-200 years. Larvae reared under control conditions readily produced C-start escape behavior to mechanosensory stimuli; however, in the moderate and high pCO2 experimental groups, the probabilities of C-start were significantly lower than those of the control group. Therefore, the sensory integration needed for the C-start escape behavior appears to be vulnerable to ocean acidification. Altered behavior in marine larval fish, particularly behaviors involved in escape from predation, could have potentially negative implications to fish populations, and, further, to the marine ecosystems at the levels of CO2 projected for the future.