Improving intracranial aneurysms image quality and diagnostic confidence with deep learning reconstruction in craniocervical CT angiography.

BACKGROUND: The diagnostic impact of deep learning computed tomography (CT) reconstruction on intracranial aneurysm (IA) remains unclear. PURPOSE: To quantify the image quality and diagnostic confidence on IA in craniocervical CT angiography (CTA) reconstructed with DEep Learning Trained Algorithm (DELTA) compared to the routine hybrid iterative reconstruction (HIR). MATERIAL AND METHODS: A total of 60 patients who underwent craniocervical CTA and were diagnosed with IA were retrospectively enrolled. Images were reconstructed with DELTA and HIR, where the image quality was first compared in noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). Next, two radiologists independently graded the noise appearance, arterial sharpness, small vessel visibility, conspicuity of calcifications that may present in arteries, and overall image quality, each with a 5-point Likert scale. The diagnostic confidence on IAs of various sizes was also graded. RESULTS: Significantly lower noise and higher SNR and CNR were found on DELTA than on HIR images (all P < 0.05). All five subjective metrics were scored higher by both readers on the DELTA images (all P < 0.05), with good to excellent inter-observer agreement (κ = 0.77-0.93). DELTA images were rated with higher diagnostic confidence on IAs compared to HIR (P < 0.001), particularly for those with size ≤3 mm, which were scored 4.5 ± 0.6 versus 3.4 ± 0.8 and 4.4 ± 0.7 versus 3.5 ± 0.8 by two readers, respectively. CONCLUSION: The DELTA shows potential for improving the image quality and the associated confidence in diagnosing IA that may be worth consideration for routine craniocervical CTA applications.

Automatic and efficient pneumothorax segmentation from CT images using EFA-Net with feature alignment function.

Pneumothorax is a condition involving a collapsed lung, which requires accurate segmentation of computed tomography (CT) images for effective clinical decision-making. Numerous convolutional neural network-based methods for medical image segmentation have been proposed, but they often struggle to balance model complexity with performance. To address this, we introduce the Efficient Feature Alignment Network (EFA-Net), a novel medical image segmentation network designed specifically for pneumothorax CT segmentation. EFA-Net uses EfficientNet as an encoder to extract features and a Feature Alignment (FA) module as a decoder to align features in both the spatial and channel dimensions. This design allows EFA-Net to achieve superior segmentation performance with reduced model complexity. In our dataset, our method outperforms various state-of-the-art methods in terms of accuracy and efficiency, achieving a Dice coefficient of 90.03%, an Intersection over Union (IOU) of 81.80%, and a sensitivity of 88.94%. Notably, EFA-Net has significantly lower FLOPs (1.549G) and parameters (0.432M), offering better robustness and facilitating easier deployment. Future work will explore the integration of downstream applications to enhance EFA-Net's utility for clinicians and patients in real-world diagnostic scenarios. The source code of EFA-Net is available at: https://github.com/tianjiamutangchun/EFA-Net .

DAWTran: dynamic adaptive windowing transformer network for pneumothorax segmentation with implicit feature alignment.

Objective. This study aims to address the significant challenges posed by pneumothorax segmentation in computed tomography images due to the resemblance between pneumothorax regions and gas-containing structures such as the trachea and bronchus.Approach. We introduce a novel dynamic adaptive windowing transformer (DAWTran) network incorporating implicit feature alignment for precise pneumothorax segmentation. The DAWTran network consists of an encoder module, which employs a DAWTran, and a decoder module. We have proposed a unique dynamic adaptive windowing strategy that enables multi-head self-attention to effectively capture multi-scale information. The decoder module incorporates an implicit feature alignment function to minimize information deviation. Moreover, we utilize a hybrid loss function to address the imbalance between positive and negative samples.Main results. Our experimental results demonstrate that the DAWTran network significantly improves the segmentation performance. Specifically, it achieves a higher dice similarity coefficient (DSC) of 91.35% (a larger DSC value implies better performance), showing an increase of 2.21% compared to the TransUNet method. Meanwhile, it significantly reduces the Hausdorff distance (HD) to 8.06 mm (a smaller HD value implies better performance), reflecting a reduction of 29.92% in comparison to the TransUNet method. Incorporating the dynamic adaptive windowing (DAW) mechanism has proven to enhance DAWTran's performance, leading to a 4.53% increase in DSC and a 15.85% reduction in HD as compared to SwinUnet. The application of the implicit feature alignment (IFA) further improves the segmentation accuracy, increasing the DSC by an additional 0.11% and reducing the HD by another 10.01% compared to the model only employing DAW.Significance. These results highlight the potential of the DAWTran network for accurate pneumothorax segmentation in clinical applications, suggesting that it could be an invaluable tool in improving the precision and effectiveness of diagnosis and treatment in related healthcare scenarios. The improved segmentation performance with the inclusion of DAW and IFA validates the effectiveness of our proposed model and its components.

Value of Serum SRY-Box Transcription Factor 2 Levels Combined with Magnetic Resonance Imaging in the Diagnosis of Endometrial Carcinoma.

Objective: To investigate the role of the SRY-box transcription factor 2 (SOX2) in endometrial carcinoma and the diagnostic value of serum SOX2 levels combined with magnetic resonance imaging (MRI). Methods: The present prospective observational study included 326 cases of endometrial carcinoma. All patients received measurements of serum SOX2 and MRI detection two weeks prior to surgery. Patients' demographic and clinical data including age, BMI, cancer stage, tumor differentiation, invasion, and lymph node metastasis were collected. All patients were followed for 5 years following surgery. Results: Deceased patients showed significantly higher ratios of: FIGO stage III-IV tumors; low tumor differentiation; myometrial invasion depths of >1/2 and cervical invasion. Lymph node metastases and distant metastasis were significantly lower in surviving patients than those in deceased patients. The serum levels of SOX2 were significantly higher in endometrial carcinoma patients compared with the healthy controls and were remarkably higher in deceased patients. Patients with elevated SOX2 levels also had higher rates of FIGO stage III-IV, higher rates of myometrial invasion depth >1/2 and higher rates of low tumor differentiation. Elevated SOX2 levels are correlated with higher rates of lymph node metastases, distant metastases and 5-year mortality. Serum SOX2 levels combined with MRI have the potential to improve the diagnosis of myometrial invasion and lymph node metastasis in endometrial carcinoma. Conclusion: Elevated serum SOX2 levels were associated with poor prognoses of patients with endometrial carcinoma. Serum SOX2 levels combined with MRI could be useful in the diagnosis and prognosis of endometrial carcinoma.

A yellow-emitting carbon quantum dot-based fluorescent logic gate for the continuous detection of Au3+ and biothiols.

Yellow-emitting carbon quantum dots, named Y-CQDs, were synthesized from O-phenylenediamine and ethylene glycol via a one-pot hydrothermal method. A fluorescent IMPLICATION logic gate for the continuous and "on-off-on" detection of Au3+ and biothiols in tap water at the nanoscale level was constructed based on these QDs. It showed promise in real sample detection and also as a fluorescent ink.

Cell imaging with multi-color DNA framework probes.

Utilizing the programmability of the fractal DNA frameworks, multi-color probes were constructed by arranging fluorescent molecules and nucleic acid aptamers on the structure. Multiplexed cell imaging and classification was realized through pattern recognition.

CD45: a critical regulator in immune cells to predict severe and non-severe COVID-19 patients.

The ongoing outbreak of COVID-19 has been announced by the World Health Organization as a worldwide public health emergency. The aim of this study was to distinguish between severe and non-severe patients in early diagnosis. The results showed that the mortality of COVID-19 patients increased accompanied by age. Host factors CRP, IL-1ß, hs-CRP, IL-8, and IL-6 levels in severe pneumonia patients were higher than in non-severe patients. CD3, CD8, and CD45 counts were decreased in COVID-19 patients. The results of this study suggest that the K-values of CD45 might be useful in distinguishing between severe and non-severe cases. The cut-off value for CD45 was -94.33. The K-values for CD45 in non-severe case were above the cut-off values, indicating a 100% prediction success rate for severe and non-severe cases following SARS-CoV-2 infection. The results confirmed that immune system dysfunction is a potential cause of mortality following COVID-19 infection, particularly for the elderly. CD45 deficiency dysfunction the naïve and memory T lymphocytes which may affects the long-term effectiveness of COVID-19 vaccines. K-values of CD45 might be useful in distinguishing between severe and non-severe cases in the early infection. May be CD45 could increase the diagnostic sensitivity.

Long noncoding RNA MCM3AP antisense RNA 1 is downregulated in chronic obstructive pulmonary disease and regulates human bronchial smooth muscle cell proliferation.

OBJECTIVES: This study aimed to investigate the involvement of MCM3AP antisense RNA 1 (MCM3AP-AS1) in chronic obstructive pulmonary disease (COPD). METHODS: The expression levels of plasma MCM3AP-AS1 in COPD patients and healthy controls were measured by quantitative PCR before treatment and at 3 months after the initiation of treatment (post-treatment) from COPD patients. The role of MCM3AP-AS1 in regulating the proliferation of human bronchial smooth muscle cells (HBSMCs) was explored by a cell proliferation assay. RESULTS: We found that MCM3AP-AS1 expression was downregulated in the plasma of COPD patients compared with controls. Among controls, MCM3AP-AS1 expression was lower in smokers than never-smokers. A 3-year follow-up study showed that, among smokers, patients with low MCM3AP-AS1 expression showed a higher incidence of COPD. After treatment for COPD, MCM3AP-AS1 expression significantly increased. The cell proliferation assay showed that MCM3AP-AS1 overexpression decreased the proliferation rate of HBSMCs. MCM3AP-AS1 silencing had the opposite effect. CONCLUSIONS: MCM3AP-AS1 appears to be downregulated in COPD and to predict its occurrence. MCM3AP-AS1 regulates the proliferation of HBSMCs to participate in airway remodeling.

Portable and sensitive quantitative detection of DNA based on personal glucose meters and isothermal circular strand-displacement polymerization reaction.

A portable and sensitive quantitative DNA detection method based on personal glucose meters and isothermal circular strand-displacement polymerization reaction was developed. The target DNA triggered target recycling process, which opened capture DNA. The released target then found another capture DNA to trigger another polymerization cycle, which was repeated for many rounds, resulting in the multiplication of the DNA-invertase conjugation on the surface of Streptavidin-MNBs. The DNA-invertase was used to catalyze the hydrolysis of sucrose into glucose for PGM readout. There was a liner relationship between the signal of PGM and the concentration of target DNA in the range of 5.0 to 1000 fM, which is lower than some DNA detection method. In addition, the method exhibited excellent sequence selectivity and there was almost no effect of biological complex to the detection performance, which suggested our method can be successfully applied to DNA detection in real biological samples.

[Microscopic identification and UV-Vis spectrum identification on Sapium sebiferum].

OBJECTIVE: To study the microscopic and UV-Vis spectrum characteristic of Sapium sebiferum. METHODS: The microscopic identification and UV-Vis spectrum identification were adopted. RESULTS: There were cluster crystals in cortical cells of roots and stems and parenchyma cells of the leaves. A few stone cells were found in cortex of the stem. The vascular bundles arranged in the form of a circle in the main vein of the leaves. It could be observed that many crystals and crystal fibers in the powder. Six kinds of solvent of crude drug had absorption peaks between 200 - 800 nm. CONCLUSION: These results can provide the scientific evidence for the establishment of standard for quality control and further study.