Machine Learning Model of ResNet50-Ensemble Voting for Malignant-Benign Small Pulmonary Nodule Classification on Computed Tomography Images.

BACKGROUND: The early detection of benign and malignant lung tumors enabled patients to diagnose lesions and implement appropriate health measures earlier, dramatically improving lung cancer patients' quality of living. Machine learning methods performed admirably when recognizing small benign and malignant lung nodules. However, exploration and investigation are required to fully leverage the potential of machine learning in distinguishing between benign and malignant small lung nodules. OBJECTIVE: The aim of this study was to develop and evaluate the ResNet50-Ensemble Voting model for detecting the benign and malignant nature of small pulmonary nodules (<20 mm) based on CT images. METHODS: In this study, 834 CT imaging data from 396 patients with small pulmonary nodules were gathered and randomly assigned to the training and validation sets in an 8:2 ratio. ResNet50 and VGG16 algorithms were utilized to extract CT image features, followed by XGBoost, SVM, and Ensemble Voting techniques for classification, for a total of ten different classes of machine learning combinatorial classifiers. Indicators such as accuracy, sensitivity, and specificity were used to assess the models. The collected features are also shown to investigate the contrasts between them. RESULTS: The algorithm we presented, ResNet50-Ensemble Voting, performed best in the test set, with an accuracy of 0.943 (0.938, 0.948) and sensitivity and specificity of 0.964 and 0.911, respectively. VGG16-Ensemble Voting had an accuracy of 0.887 (0.880, 0.894), with a sensitivity and specificity of 0.952 and 0.784, respectively. CONCLUSION: Machine learning models that were implemented and integrated ResNet50-Ensemble Voting performed exceptionally well in identifying benign and malignant small pulmonary nodules (<20 mm) from various sites, which might help doctors in accurately diagnosing the nature of early-stage lung nodules in clinical practice.

Astaxanthin Alleviates Ochratoxin A-Induced Cecum Injury and Inflammation in Mice by Regulating the Diversity of Cecal Microbiota and TLR4/MyD88/NF-κB Signaling Pathway.

Ochratoxin A (OTA) is a common environmental pollutant found in a variety of foods and grains, and excessive OTA consumption causes serious global health effects on animals and humans. Astaxanthin (AST) is a natural carotenoid that has anti-inflammatory, antiapoptotic, immunomodulatory, antitumor, antidiabetes, and other biological activities. The present study is aimed at investigating the effects of AST on OTA-induced cecum injury and its mechanism of action. Eighty C57 mice were randomly divided into four groups, including the control group, OTA group (5 mg/kg body weight), AST group (100 mg/kg body weight), and AST intervention group (100 mg/kg body weight AST+5 mg/kg body weight OTA). It was found that AST decreased the endotoxin content, effectively prevented the shortening of mouse cecum villi, and increased the expression levels of tight junction (TJ) proteins, consisting of occludin, claudin-1, and zonula occludens-1 (ZO-1). AST increased the number of goblet cells, the contents of mucin-2 (MUC2), and defensins (Defa5 and ß-pD2) significantly, while the expression of mucin-1 (MUC1) decreased significantly. The 16S rRNA sequencing showed that AST affected the richness and diversity of cecum flora, decreased the proportion of lactobacillus, and also decreased the contents of short-chain fatty acids (SCFAs) (acetate and butyrate). In addition, AST significantly decreased the expression of TLR4, MyD88, and p-p65, while increasing the expression of p65. Meanwhile, the expression of inflammatory factors including TNF-α and INF-γ decreased, while the expression of IL-10 increased. In conclusion, AST reduced OTA-induced cecum injury by regulating the cecum barrier function and TLR4/MyD88/NF-κB signaling pathway.

Astaxanthin Protects Ochratoxin A-Induced Oxidative Stress and Apoptosis in the Heart via the Nrf2 Pathway.

This study assessed the protective mechanism of astaxanthin (ASX) against ochratoxin A- (OTA-) induced cardiac injury in mice. Four groups of mice were established: control group (0.1 mL olive oil + 0.1 mL NaHCO2), OTA group (0.1 mL OTA 5 mg/kg body weight), ASX group (0.1 mL ASX 100 mg/kg body weight), and ASX + OTA group (0.1 mL ASX 100 mg/kg body weight, 2 h later, 0.1 mL OTA 5 mg/kg body weight). The test period lasted for 27 days (7 days of dosing, 2 days of rest). Electrocardiogram, body weight, heart weight, tissue pathology, oxidative markers (malondialdehyde (MDA), superoxide dismutase (SOD), catalase (CAT), and glutathione (GSH)), biochemical markers (creatine kinase (CK), creatine kinase isoenzyme (CK-MB), and lactate dehydrogenase (LDH)), electron microscopy, TUNEL, and Western blot tests were used to examine the effects of OTA on myocardial injury and ASX detoxification. The results showed that OTA exposure significantly decreased both body weight and heart weight. OTA induced a decrease in heart rate in mice and decreased tissue concentrations of SOD, CAT, and GSH, while increasing serum concentrations of cardiac enzymes (CK, CK-MB, and LDH) and tissue MDA. ASX improved heart rate, cardiac enzymes, and antioxidant levels in mice. The results of tissue pathology and TUNEL assay showed that ASX protects against OTA-induced myocardial injury. In addition, Western blot results showed that the OTA group upregulated Keap1, Bax, Caspase3, and Caspase9, while it downregulated Nrf2, HO-1, and Bcl-2 protein expression. ASX played a protective role by changing the expression of Keap1, Nrf2, HO-1, Bax, Bcl-2, Caspase3, and Caspase9 proteins. These results indicate that the protective mechanism of ASX on the myocardium works through the Keap1-Nrf2 signaling pathway and mitochondria-mediated apoptosis pathway. This study provides a molecular rationale for the mechanism underlying OTA-induced myocardial injury and the protective effect of ASX on the myocardium.

Protective Effect of Astaxanthin on Ochratoxin A-Induced Kidney Injury to Mice by Regulating Oxidative Stress-Related NRF2/KEAP1 Pathway.

The present study aimed to investigate the effects of astaxanthin (ASX) on ochratoxin A (OTA)-induced renal oxidative stress and its mechanism of action. Serum kidney markers, histomorphology, ultrastructural observation, and oxidative stress indicators were assessed. Meanwhile, quantitative real-time reverse transcription PCR and western blotting detection of NRF2 (encoding nuclear factor, erythroid 2 like) and members of the NRF2/KEAP1 signaling pathway (KEAP1 (encoding Kelch-like ECH-associated protein), NQO1 (encoding NAD(P)H quinone dehydrogenase), HO-1 (encoding heme oxygenase 1), γ-GCS (gamma-glutamylcysteine synthetase), and GSH-Px (glutathione peroxidase 1)) were performed. Compared with the control group, the OTA-treated group showed significantly increased levels of serum UA (uric acid) and BUN (blood urea nitrogen), tubular epithelial cells were swollen and degenerated, and the levels of antioxidant enzymes decreased significantly, and the expression of NRF2 (cytoplasm), NQO1, HO-1, γ-GCS, and GSH-Px decreased significantly. More importantly, after ASX pretreatment, compared with the OTA group, serum markers were decreased, epithelial cells appeared normal; the expression of antioxidant enzymes increased significantly, NQO1, HO-1, γ-GCS and GSH-Px levels increased significantly, and ASX promoted the transfer of NRF2 from the cytoplasm to the nucleus. These results highlight the protective ability of ASX in renal injury caused by OTA exposure, and provide theoretical support for ASX's role in other mycotoxin-induced damage.

Astaxanthin Protects OTA-Induced Lung Injury in Mice through the Nrf2/NF-κB Pathway.

The aim of this research was to evaluate the potential protective mechanism of astaxanthin (ASTA) against oxidative damage and inflammation caused by ochratoxin (OTA) in mouse lung. We divided mice into a control group (CG), an OTA group (PG), an astaxanthin group (AG), and an OTA+ASTA group (JG). Oxidative indices (malondialdehyde (MDA), total superoxide dismutase (T-SOD), and reduced glutathione (GSH)) and inflammatory markers (interleukin 1ß (IL-1ß), interleukin 6 (IL-6), and tumor necrosis factor α (TNF-α)) were assayed in the lung, and the lung-weight-to-body-weight ratio was calculated. Apoptosis was detected in pathological sections by the TdT-mediated dUTP nick-end labeling (TUNEL) assay. Oxidative damage and inflammation were detected in the lung of mice after exposure to OTA. Besides, Nrf2- and NF-κB-pathway-associated proteins were detected by Western blot. In contrast with OTA, ASTA significantly raised the expression of Nrf2, HO-1, and MnSOD, while the expression of other proteins (Keap1, TLR4, and NF-κB) was significantly decreased. These results indicate that ASTA exerted protective effects against OTA-induced oxidative damage and inflammation in the lung by regulating the Nrf2 and NF-κB pathways.