Abstract Objective: To explore of ultrasound combined with renal pathology score, and compare the application value of elastography, two-dimensional (2D) ultrasound, three-dimensional（3D） ultrasound and other ultrasound imaging methods in early chronic kidney diagnosis. Methods: Combined ultrasound and pathological scores. A retrospective analysis of 118 patients with chronic kidney disease examined in the department of nephrology of the author's hospital. 36 healthy who were normal in the same period were selected as the control group. Combined with the left kidney pathology score and multi-factor logistic regression analysis to evaluate independent predictors of early pathological injured in CKD, ROC curve analysis to evaluate the diagnostic efficacy of each ultrasound index. Statistical evaluation: The difference was statistically significant (P <0.05). Results : In patients with severely injured CKD, renal length, three-dimensional kidney volume, Renal interlobar artery RI, and AT all appear to be effective predictors. Among patients with moderate injured, only AT and RI were effective predictors. Among patients with mildly impaired CKD, AT has the highest diagnostic efficacy, but SWV has the highest sensitivity (83.8%) for detecting mild renal injured. The results confirm that the Renal interlobar artery AT is the strongest independent predictor of CKD injured. Conclusion: The results confirm that the Renal interlobar artery AT is the strongest independent predictor of CKD injured.
To address the challenges of similarity between lesions and surrounding tissues, overlapping appearances of partially benign and malignant nodules, and difficulty in classification, a deep learning network that integrates CNN and Transformer is proposed for the classification of benign and malignant breast lesions in ultrasound images. This network adopts a dual-branch architecture for local-global feature extraction, making full use of the advantages of CNN in extracting local features and the ability of ViT to extract global features to enhance the network's feature extraction capabilities for breast nodules. The local feature extraction branch employs a residual network with multiple attention-guided modules, which can effectively capture the local details and texture features of breast nodules, enhance sensitivity to subtle changes within the nodules, and thus can aid in accurate classification of their benign and malignancy. The global feature extraction branch utilizes the multi-head self-attention ViT network, which can capture the overall shape, boundary, and relationship with surrounding tissues, and thereby enhancing the understanding and modeling of both nodule and global image features. Experimental results on a public ultrasound breast nodule data set show that the proposed method is better than other comparison networks, This indicates that the fusion of CNN and Transformer networks can effectively improve the performance of the classification model and provide a powerful solution for the benign-malignant classification of ultrasound breast.
Abstract Background: Deep brain stimulation (DBS) has proved effective for Parkinsons disease (PD), but the identification of stimulation parameters relies on doctors’ subjective judgment on patient behavior. Methods: Five PD patients performed 10-meter walking tasks under different brain stimulation frequencies. During walking tests, a wearable functional near-infrared spectroscopy (fNIRS) system was used to measure the concentration change of oxygenated hemoglobin (Δ HbO 2 ) in prefrontal cortex, parietal lobe and occipital lobe. Brain functional connectivity and global efficiency were calculated to quantify the brain activities. Results: We discovered that both the global and regional brain efficiency of all patients varied with stimulation parameters, and the DBS pattern enabling the highest brain efficiency was optimal for each patient, in accordance with the clinical assessments and DBS treatment decision made by the doctors. Conclusions: Task fNIRS assessments and brain functional connectivity analysis promise a quantified and objective solution for patient-specific optimization of DBS treatment. Trial registration: The study was approved by the Ethical Committee of Tianjin Huanhu Hospital (2019-35), and has been registered in Chinese Clinical Trial Registry (ChiCTR1900022715).
A novel classification model that integrates shallow and deep features is proposed. Firstly, traditional image processing methods, such as LBP and Canny operator, are utilized to extract shape, texture, and edge features from the region of interest. Then, a novel FCST model composed of a residual convolution branch and a Swin Transformer branch is designed for extraction deep features of ultrasound nodule images. The residual convolution branch extracts local features and passes them layer by layer to the Swin Transformer, which compensates for the missing information of local details and enables the model to capture both local details and global dependencies. Finally, the shallow and deep features are fused for classification to obtain the identification results of benign and malignant nodules. Experimental results demonstrate that the fusion of deep and shallow features can effectively enhance the network's capability of identifying nodules, significantly improving the accuracy of identifying benign and malignant nodules.
Objective To investigate the value of haemodynamic parameters (S/D, RI, PI) of the lateral thoracic artery (LTA) in the diagnosis of breast cancer. Methods Seventy breast tumor patients and thirty healthy women were examined by Color Doppler sonography in one week before operation. Size of the mass, tumor position, the classification of flow signals, and LTA haemodynamic parameters were assessed. Results S/D ratio, PI, RI of LTA were significantly lower in the tumor affected breasts than the contralateral healthy breasts in breast cancer group (P0.05). However, there were no significant differences in benign breast tumor group (P0.05). When the S/D H-C≥1.5 of LTA served as diagnostic criteria of breast cancer, sensitivity, specificity were 83.8%, 76.7%, respectively; When the PI H-C≥0.3 of LTA served as diagnostic criteria of breast cancer, sensitivity, specificity were 83.7%, 83.3%, respectively; when the RI H-C≥0.06 of LTA served as diagnostic criteria of breast cancer, sensitivity, specificity reached 86.4%, 90%. Correlation analysis showed that S/D ratio, PI, RI of LTA were negatively correlated with tumor size and the classification of flow signals, while were not significantly correlated with tumor position. Conclusion Detecting the S/D ratio, PI, RI of LTA by color Doppler sonography can be used as one of diagnostic indicators of breast cancer and S/D ratios, PI, RI of LTA were correlated with tumor size, the classification of flow signals.
This study aims to examine brain activity during different swallowing actions in patients with dysphagia caused by medullary infarction (MI) before and after treatment using blood oxygen level-dependent (BOLD) functional magnetic resonance imaging.
Macrolides are a significant family of natural products with diverse structures and bioactivities. Considerable effort has been made in recent decades to isolate additional macrolides and characterize their chemical and bioactive properties. The majority of macrolides are obtained from marine organisms, including sponges, marine microorganisms and zooplankton, cnidarians, mollusks, red algae, bryozoans, and tunicates. Sponges, fungi and dinoflagellates are the main producers of macrolides. Marine macrolides possess a wide range of bioactive properties including cytotoxic, antibacterial, antifungal, antimitotic, antiviral, and other activities. Cytotoxicity is their most significant property, highlighting that marine macrolides still encompass many potential antitumor drug leads. This extensive review details the chemical and biological diversity of 505 macrolides derived from marine organisms which have been reported from 1990 to 2020.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)