Deep learning-based differentiation of ventricular septal defect from tetralogy of Fallot in fetal echocardiography images.

BACKGROUND: Congenital heart disease (CHD) seriously affects children's health and quality of life, and early detection of CHD can reduce its impact on children's health. Tetralogy of Fallot (TOF) and ventricular septal defect (VSD) are two types of CHD that have similarities in echocardiography. However, TOF has worse diagnosis and higher morality than VSD. Accurate differentiation between VSD and TOF is highly important for administrative property treatment and improving affected factors' diagnoses. OBJECTIVE: TOF and VSD were differentiated using convolutional neural network (CNN) models that classified fetal echocardiography images. METHODS: We collected 105 fetal echocardiography images of TOF and 96 images of VSD. Four CNN models, namely, VGG19, ResNet50, NTS-Net, and the weakly supervised data augmentation network (WSDAN), were used to differentiate the two congenital heart diseases. The performance of these four models was compared based on sensitivity, accuracy, specificity, and AUC. RESULTS: VGG19 and ResNet50 performed similarly, with AUCs of 0.799 and 0.802, respectively. A superior performance was observed with NTS-Net and WSDAN specific for fine-grained image categorization tasks, with AUCs of 0.823 and 0.873, respectively. WSDAN had the best performance among all models tested. CONCLUSIONS: WSDAN exhibited the best performance in differentiating between TOF and VSD and is worthy of further clinical popularization.

Peroxiredoxin 3 has a crucial role in the macrophage polarization by regulating mitochondrial homeostasis.

Acute lung injury (ALI) is one of the life-threatening complications of sepsis, and macrophage polarization plays a crucial role in the sepsis-associated ALI. However, the regulatory mechanisms of macrophage polarization in ALI and in the development of inflammation are largely unknown. In this study, we demonstrated that macrophage polarization occurs in sepsis-associated ALI and is accompanied by mitochondrial dysfunction and inflammation, and a decrease of PRDX3 promotes the initiation of macrophage polarization and mitochondrial dysfunction. Mechanistically, PRDX3 overexpression promotes M1 macrophages to differentiate into M2 macrophages, and enhances mitochondrial functional recovery after injury by reducing the level of glycolysis and increasing TCA cycle activity. In conclusion, we identified PRDX3 as a critical hub integrating oxidative stress, inflammation, and metabolic reprogramming in macrophage polarization. The findings illustrate an adaptive mechanism underlying the link between macrophage polarization and sepsis-associated ALI.

Deep learning for differentiating benign from malignant tumors on breast-specific gamma image.

BACKGROUND: Breast diseases are a significant health threat for women. With the fast-growing BSGI data, it is becoming increasingly critical for physicians to accurately diagnose benign as well as malignant breast tumors. OBJECTIVE: The purpose of this study is to diagnose benign and malignant breast tumors utilizing the deep learning model, with the input of breast-specific gamma imaging (BSGI). METHODS: A benchmark dataset including 144 patients with benign tumors and 87 patients with malignant tumors was collected and divided into a training dataset and a test dataset according to the ratio of 8:2. The convolutional neural network ResNet18 was employed to develop a new deep learning model. The model proposed was compared with neural network and autoencoder models. Accuracy, specificity, sensitivity and ROC were used to evaluate the performance of different models. RESULTS: The accuracy, specificity and sensitivity of the model proposed are 99.1%, 98.8% and 99.3% respectively, which achieves the best performance among all methods. Additionally, the Grad-CAM method is used to analyze the interpretability of the diagnostic results based on the deep learning model. CONCLUSION: This study demonstrates that the proposed deep learning method could help physicians diagnose benign and malignant breast tumors quickly as well as reliably.

Effects of neuronavigation-guided rTMS on serum BDNF, TrkB and VGF levels in depressive patients with suicidal ideation.

BACKGROUND: Neuronavigation-guided high-dose repetitive transcranial magnetic stimulation (rTMS) could rapidly treat depressive patients with suicidal ideation. But the mechanism of rTMS still needs to be elucidated. This study aims to investigate if rTMS improves suicidal ideation and depressive symptoms by influencing brain-derived neurotrophic factor (BDNF), tropomysin receptor kinase B (TrkB) and VGF levels. METHODS: In the present 1-week study, 59 treatment-naive depressive patients with suicidal ideation were randomly assigned to the active (n = 31) or sham (n = 28) rTMS group. The severity of suicidal ideation and depression were measured by the Beck Scale for Suicide Ideation, the Hamilton Depression Rating Scale and Montgomery-Asberg Depression Rating Scale. Fasting venous blood samples were collected at baseline and after treatment. Serum protein concentrations of BDNF, TrkB and VGF were measured by enzyme linked immunosorbent assay. RESULTS: We found after treatment the levels of BDNF in the active rTMS group were higher than the sham group (p = 0.011), TrkB levels were decreased in the active group (p < 0.001), VGF levels were increased in the active group (p = 0.005). Post-treatment VGF levels in the active group were higher than the sham group (p = 0.008). However, there were no significant correlation between changes in BDNF, TrkB and VGF levels and the changes in clinical variables. LIMITATIONS: Participants taking medication may affect the results. CONCLUSIONS: Our results suggest that the BDNF-TrkB pathway and VGF may be implicated in the mechanisms underlying neuronavigation-guided rTMS for treating depressive patients with suicidal ideation.

SPT20 Regulates the Hog1-MAPK Pathway and Is Involved in Candida albicans Response to Hyperosmotic Stress.

Candida albicans is the most common fungal pathogen and relies on the Hog1-MAPK pathway to resist osmotic stress posed by the environment or during host invasions. Here, we investigated the role of SPT20 in response to osmotic stress. Testing a C. albicans spt20Δ/Δ mutant, we found it was sensitive to osmotic stress. Using sequence alignment, we identified the conserved functional domains between CaSpt20 and ScSpt20. Reconstitution of the Spt20 function in a spt20Δ/CaSPT20 complemented strain found CaSPT20 can suppress the high sensitivity to hyperosmotic stressors, a cell wall stress agent, and antifungal drugs in the Saccharomyces cerevisiae spt20Δ/Δ mutant background. We measured the cellular glycerol accumulation and found it was significantly lower in the C. albicans spt20Δ/Δ mutant strain, compared to the wild type strain SC5314 (P < 0.001). This result was also supported by quantitative reverse transcription-PCR, which showed the expression levels of gene contributing to glycerol accumulation were reduced in Caspt20Δ/Δ compared to wild type (GPD2 and TGL1, P < 0.001), while ADH7 and AGP2, whose expression can lead to glycerol decrease, were induced when cells were exposed to high osmolarity (ADH7, P < 0.001; AGP2, P = 0.002). In addition, we tested the transcription levels of Hog1-dependent osmotic stress response genes, and found that they were significantly upregulated in wild type cells encountering hyperosmolarity, while the expression of HGT10, SKO1, CAT1, and SLP3 were not induced when SPT20 was deleted. Although the transcript of ORF19.3661 and ORF19.4370 in Caspt20Δ/Δ was induced in the presence of 1 M NaCl, the levels were less than what was observed in the wild type (ORF19.3661, P = 0.007; ORF19.4370, P = 0.011). Moreover, the deletion of CaSPT20 in C. albicans reduced phosphorylation levels of Hog1. These findings suggested that SPT20 is conserved between yeast and C. albicans and plays an important role in adapting to osmotic stress through regulating Hog1-MAPK pathway.

Candidemia in Adults at a Tertiary Hospital in China: Clinical Characteristics, Species Distribution, Resistance, and Outcomes.

BACKGROUND: Candidemia is one of the most common nosocomial bloodstream infections. Early diagnosis and antifungal treatment improve clinical outcomes in some studies but not all, with diverse data reported from different institutions. Similarly, antifungal resistance is more common in the USA than in Europe, but there is little data regarding the microbiology and clinical course of candidemia in adult patients in Asia. AIMS: (1) To capture species distribution and drug resistance rates among Candida bloodstream isolates, (2) to describe clinical features of candidemia, and (3) to identify factors associated with all-cause mortality, with emphasis on early initiation of antifungal treatment, at a large tertiary University Hospital in China. METHODS: In this single-center retrospective study, we identified all patients with candidemia, between 2008 and 2014. Demographic and clinical characteristics, microbiological information, details of antifungal therapy and clinical outcomes were collected. RESULTS: We studied 166 patients. 71 (42.8%) had cancer. Candida albicans was the most frequent species (37.3%), followed by C. parapsilosis (24.1%), C. tropicalis (22.8%), and C. glabrata (14.5%). Antifungal resistance was more frequent in non-albicans strains and especially C. glabrata. Twenty patients received inappropriate treatment with all-cause mortality of 35%. The remaining 146 patients had significantly lower mortality (21.9%, P = 0.045). Among patients who received antifungal treatment, mortality rate increased with time to appropriate antifungal therapy (AAT): 13.7%, for < 24 h, 21.1% for 24-48 h, 23.1% for > 48 h, and 32.4% among patients who received no AT (χ2 for trend P = 0.039). Initiating AAT more than 24 h after blood culture collection was an independent risk factor for mortality, after adjustment for other confounders (OR 7.1, 95% CI 1.3-39.4, P = 0.024). CONCLUSIONS: Candida albicans was the most frequent cause of candidemia at a large tertiary hospital in China, but antifungal resistance is a growing concern among non-albicans Candida species. The mortality rate of patients treated with ineffective antifungal agents based on in vitro susceptibilities was similar to that of patients who received no treatment at all, and delayed initiation of antifungal treatment was associated with increased risk of death.

Possible sertraline-induced extrapyramidal adverse effects in an adolescent.

Sertraline has been considered to be a relatively safe selective serotonin reuptake inhibitor for adolescents for a long time. We report herein a case of a 16-year-old Chinese boy with depression who experienced extrapyramidal-like effects, for example, facial spasm, upper limb dystonia, akathisia, and other disturbed behaviors, while being treated with sertraline 200 mg per day. His movement symptoms were significantly alleviated after the discontinuation of sertraline and the administration of scopolamine. This finding indicates that albeit infrequent, sertraline may cause severe extrapyramidal symptoms in adolescent patients, suggesting that clinicians should be alert to the neurological side effects of sertraline in young patients.