ZC3H13-Mediated m6A Modification Ameliorates Acute Myocardial Infarction through Preventing Inflammation, Oxidative Stress and Ferroptosis by Targeting lncRNA93358.

BACKGROUND: Acute myocardial infarction (AMI) is a life-threatening event that is associated with RNA modification and programmed cell death (PCD). This study attempted to investigate the impacts of zinc finger CCCH domain-containing protein 13 (ZC3H13)-mediated N6-methyladenosine (m6A) on ferroptosis in AMI. METHODS: The infarcted areas and cardiac function were evaluated, and the expression level of ZC3H13 was measured in AMI rats that were induced by isoproterenol. Meanwhile, oxygen glucose deprivation (OGD) in vitro model was induced to investigate the alterations on inflammation, oxidative stress and ferroptosis. The m6A modification site of lncRNA93358 modified by ZC3H13 was predicted using bioinformatics, and the interaction between ZC3H13 and lncRNA93358 was verified using the dual-luciferase reporter assays. ZC3H13 was overexpressed and lncRNA93358 was silenced to study their regulatory role in cell death, inflammation, oxidative stress and ferroptosis in AMI. RESULTS: Significant decreased expression of ZC3H13 was observed in AMI rats, with impaired cardiac function, enhanced inflammation and oxidative stress. ZC3H13 targeted the modification site GGACC of lncRNA93358 and downregulated lncRNA93358. Silencing lncRNA93358 inhibited cell death, reduced the levels of inflammatory cytokines tumor necrosis factor (TNF)-α, interleukin (IL)-6 and IL-1ß, suppressed oxidative stress-related indicators (lactate dehydrogenase (LDH), reactive oxygen species (ROS), glutathione (GSH) and malondialdehyde (MDA), as well as downregulated ferroptosis-related acyl-CoA synthetase long chain family member 4 (ACSL4), prostaglandin-endoperoxide synthase 2 (PTGS2) and glutathione peroxidase 4 (GPX4). The effect of silencing lncRNA93358 was further enhanced by overexpression of ZC3H13. CONCLUSION: This study reveals the ZC3H13-mediated epigenetic RNA modification targeting lncRNA93358 and suggests that ZC3H13 overexpression may be a promising approach for AMI treatment.

Silencing lncRNA 93358 Inhibits the Apoptosis of Myocardial Cells in Myocardial Infarction Rats by Inducing the Expression of SLC8A1.

Objective: To explore the inhibitor effects and mechanism of lncRNA 93358 against the apoptosis of myocardial cells in rats with myocardial infarction. Methods: The myocardial infarction model was established in rats, which were identified by cardiac ultrasound. TTC staining was used to evaluate the degree of heart infarction, and HE staining was utilized to determine the pathological state in myocardial tissues. The apoptotic state in myocardial tissues was confirmed by TUNEL assay. lncRNA 93358 was screened out using a high-throughput sequencing which was confirmed by RT-qPCR. The interaction between miR-466c-3p and SLC8A1 was identified using the dual-luciferase reporter assay. The expression level of Bax, Bcl-2, and SLC8A1 was determined in lncRNA 93358 knockdown cells using RT-qPCR and Western blotting. Results: Massive myocardial necrosis was observed in model rats according to the results of TTC staining, HE staining, and TUNEL assay. lncRNA 93358 and Bax were found significantly upregulated, and Bcl-2 and SLC8A1 were greatly downregulated in model rats, which were dramatically reversed by the knockdown of lncRNA 93358, accompanied by the decline area of myocardial necrosis and decreased apoptotic myocardial cells. Conclusion: Silencing lncRNA 93358 inhibits the apoptosis of myocardial cells in rats with myocardial infarction by inducing the expression of SLC8A1.

Content-based image retrieval with a Convolutional Siamese Neural Network: Distinguishing lung cancer and tuberculosis in CT images.

BACKGROUND: CT findings of lung cancer and tuberculosis are sometimes similar, potentially leading to misdiagnosis. This study aims to combine deep learning and content-based image retrieval (CBIR) to distinguish lung cancer (LC) from nodular/mass atypical tuberculosis (NMTB) in CT images. METHODS: This study proposes CBIR with a convolutional Siamese neural network (CBIR-CSNN). First, the lesion patches are cropped out to compose LC and NMTB datasets and the pairs of two arbitrary patches form a patch-pair dataset. Second, this patch-pair dataset is utilized to train a CSNN. Third, a test patch is treated as a query. The distance between this query and 20 patches in both datasets is calculated using the trained CSNN. The patches closest to the query are used to give the final prediction by majority voting. One dataset of 719 patients is used to train and test the CBIR-CSNN. Another external dataset with 30 patients is employed to verify CBIR-CSNN. RESULTS: The CBIR-CSNN achieves excellent performance at the patch level with an mAP (Mean Average Precision) of 0.953, an accuracy of 0.947, and an area under the curve (AUC) of 0.970. At the patient level, the CBIR-CSNN correctly predicted all labels. In the external dataset, the CBIR-CSNN has an accuracy of 0.802 and AUC of 0.858 at the patch level, and 0.833 and 0.902 at the patient level. CONCLUSIONS: This CBIR-CSNN can accurately and automatically distinguish LC from NMTB using CT images. CBIR-CSNN has excellent representation capability, compatibility with few-shot learning, and visual explainability.

Development and Validation of a Nomogram for Preoperative Prediction of Lymph Node Metastasis in Lung Adenocarcinoma Based on Radiomics Signature and Deep Learning Signature.

BACKGROUND AND PURPOSE: The preoperative LN (lymph node) status of patients with LUAD (lung adenocarcinoma) is a key factor for determining if systemic nodal dissection is required, which is usually confirmed after surgery. This study aimed to develop and validate a nomogram for preoperative prediction of LN metastasis in LUAD based on a radiomics signature and deep learning signature. MATERIALS AND METHODS: This retrospective study included a training cohort of 200 patients, an internal validation cohort of 40 patients, and an external validation cohort of 60 patients. Radiomics features were extracted from conventional CT (computed tomography) images. T-test and Extra-trees were performed for feature selection, and the selected features were combined using logistic regression to build the radiomics signature. The features and weights of the last fully connected layer of a CNN (convolutional neural network) were combined to obtain a deep learning signature. By incorporating clinical risk factors, the prediction model was developed using a multivariable logistic regression analysis, based on which the nomogram was developed. The calibration, discrimination and clinical values of the nomogram were evaluated. RESULTS: Multivariate logistic regression analysis showed that the radiomics signature, deep learning signature, and CT-reported LN status were independent predictors. The prediction model developed by all the independent predictors showed good discrimination (C-index, 0.820; 95% CI, 0.762 to 0.879) and calibration (Hosmer-Lemeshow test, P=0.193) capabilities for the training cohort. Additionally, the model achieved satisfactory discrimination (C-index, 0.861; 95% CI, 0.769 to 0.954) and calibration (Hosmer-Lemeshow test, P=0.775) when applied to the external validation cohort. An analysis of the decision curve showed that the nomogram had potential for clinical application. CONCLUSIONS: This study presents a prediction model based on radiomics signature, deep learning signature, and CT-reported LN status that can be used to predict preoperative LN metastasis in patients with LUAD.