Visual Interpretation of Radiomics Features in Filtered Computed Tomography Images during the Portal Phase of Acute Pancreatitis.

BACKGROUND: Current research on radiomics for diagnosing and prognosing acute pancreatitis predominantly revolves around model development and testing. However, there is a notable absence of ongoing interpretation and analysis regarding the physical significance of these models and features. Additionally, there is a lack of extensive exploration of visual information within the images. This limitation hinders the broad applicability of radiomics findings. This study aims to address this gap by specifically analyzing filtered Computed Tomography (CT) image features of acute pancreatitis to identify meaningful visual markers in the pancreas and peripancreatic area. METHODS: Numerous filtered CT images were obtained through pyradiomics. The window width and window level were fine-tuned to emphasize the pancreas and peripancreatic regions. Subsequently, the LightGBM algorithm was employed to conduct an embedded feature screening, followed by statistical analysis to identify features with statistical significance (p-value < 0.01). Within the purview of the study, for each filtering method, features of high importance to the preceding prediction model were incorporated into the analysis. The image visual markers were then systematically sought in reverse, and their medical interpretation was undertaken to a certain extent. RESULTS: In Laplacian of Gaussian filtered images within the pancreatic region, severe acute pancreatitis (SAP) exhibited fewer small areas with repetitive greyscale patterns. Conversely, in the peripancreatic region, SAP displayed greater irregularity in both area size and the distribution of greyscale levels. In logarithmic images, SAP demonstrated reduced low greyscale connectivity in the pancreatic region, while showcasing a higher average variation in greyscale between two adjacent pixels in the peripancreatic region. Moreover, in gradient images, SAP presented with decreased repetition of two adjacent pixel greyscales within the pancreatic region, juxtaposed with an increased inhomogeneity in the size of the same greyscale region within the δ range in the peripancreatic region. CONCLUSIONS: Various filtered images convey distinct physical significance and properties. The selection of the appropriate filtered image, contingent upon the characteristics of the Region of Interest (ROI), enables a more comprehensive capture of the heterogeneity of the disease.

Biodiversity drives ecosystem multifunctionality in sandy grasslands?

Plant communities and soil microbiomes play a crucial role in regulating ecosystem multifunctionality (EMF). However, whether and how aboveground plant diversity, belowground soil microbial diversity and interactions with environmental factors affect EMF in sandy grasslands under climate change conditions is unclear. Here, we selected 15 typical grassland communities from the Horqin sandy grassland along temperature and precipitation gradients, using the mean annual temperature (AMT), mean annual precipitation (AP), soil temperature (ST), soil water content (SW) and pH as abiotic factors, and plant diversity (PD) and soil microbial diversity (SD) as biodiversity indicators. The effects of biodiversity and abiotic factors on individual ecosystem functions and EMF were studied. We found that PD and its components, plant species richness (SR), species diversity (PR) and genetic diversity (GD), had significant effects on aboveground biomass (AGB) and major factors involved in ecosystem nitrogen cycling (plant leaf nitrogen content (PLN) and soil total nitrogen content (STN)) (P < 0.05). Soil fungal diversity (FR) has a greater impact on ecosystem function than soil bacteria (BR) and archaea (ABR) in sandy grasslands and mainly promotes the accumulation of soil microbial carbon and nitrogen (MBC, MBN) (P < 0.05), STC and STN (P < 0.01). PD and two types of SD (FR and ABR) significantly regulated EMF (P < 0.01). Among the abiotic factors, soil pH and SW regulated EMF (P < 0.05), and SW and ST directly drove EMF (P < 0.05). PD drove EMF significantly and indirectly (positively) through soil pH and ST (P < 0.001), while SD drove EMF weakly and indirectly (negatively) through AP and PD (P > 0.05). PD was a stronger driving force on EMF than SD. These results improve our understanding of the drivers of multifunctionality in sandy grassland ecosystems.

Recognition of eye diseases based on deep neural networks for transfer learning and improved D-S evidence theory.

BACKGROUND: Human vision has inspired significant advancements in computer vision, yet the human eye is prone to various silent eye diseases. With the advent of deep learning, computer vision for detecting human eye diseases has gained prominence, but most studies have focused only on a limited number of eye diseases. RESULTS: Our model demonstrated a reduction in inherent bias and enhanced robustness. The fused network achieved an Accuracy of 0.9237, Kappa of 0.878, F1 Score of 0.914 (95% CI [0.875-0.954]), Precision of 0.945 (95% CI [0.928-0.963]), Recall of 0.89 (95% CI [0.821-0.958]), and an AUC value of ROC at 0.987. These metrics are notably higher than those of comparable studies. CONCLUSIONS: Our deep neural network-based model exhibited improvements in eye disease recognition metrics over models from peer research, highlighting its potential application in this field. METHODS: In deep learning-based eye recognition, to improve the learning efficiency of the model, we train and fine-tune the network by transfer learning. In order to eliminate the decision bias of the models and improve the credibility of the decisions, we propose a model decision fusion method based on the D-S theory. However, D-S theory is an incomplete and conflicting theory, we improve and eliminate the existed paradoxes, propose the improved D-S evidence theory(ID-SET), and apply it to the decision fusion of eye disease recognition models.

Early prediction of acute pancreatitis severity based on changes in pancreatic and peripancreatic computed tomography radiomics nomogram.

Background: Early identification of severe acute pancreatitis (SAP) is key to reducing mortality and improving prognosis. We aimed to establish a radiomics model and nomogram for early prediction of acute pancreatitis (AP) severity based on contrast-enhanced computed tomography (CT) images. Methods: We retrospectively analyzed 215 patients with first-episode AP, including 141 in the training cohort (87 men and 54 women, mean age 51.37±16.09 years) and 74 in the test cohort (40 men and 34 women, mean age 55.49±17.83 years). Radiomics features were extracted from portal venous phase images based on pancreatic and peripancreatic regions. The light gradient boosting machine (LightGBM) algorithm was used for feature selection, a logistic regression (LR) model was established and trained by 10-fold cross-validation, and a nomogram was established based on the best features. The model's predictive performance was evaluated according to the area under the curve (AUC) of the receiver operating characteristic (ROC) curve, sensitivity, specificity, and accuracy. Results: A total of 13 optimal radiomics features were selected by LightGBM for LR model building. The AUC of the radiomics (LR) model was 0.992 [95% confidence interval (CI): 0.963-0.996] in the training cohort, 0.965 (95% CI: 0.924-0.981) in the validation cohort, and 0.894 (95% CI: 0.789-0.966) in the test cohort. The sensitivity was 0.862 (95% CI: 0.674-0.954), the specificity was 0.800 (95% CI: 0.649-0.899), and the accuracy was 0.824 (95% CI: 0.720-0.919). The nomogram based on the 13 radiomics features showed that SAP would be predicted when the total score was greater than 124. Conclusions: The radiomics model based on enhanced-CT images of pancreatic and peripancreatic regions performed well in the early prediction of AP severity. The nomogram based on selected radiomics features could provide a reference for AP clinical assessment.

Automatic Liver Segmentation in CT Images with Enhanced GAN and Mask Region-Based CNN Architectures.

Liver image segmentation has been increasingly employed for key medical purposes, including liver functional assessment, disease diagnosis, and treatment. In this work, we introduce a liver image segmentation method based on generative adversarial networks (GANs) and mask region-based convolutional neural networks (Mask R-CNN). Firstly, since most resulting images have noisy features, we further explored the combination of Mask R-CNN and GANs in order to enhance the pixel-wise classification. Secondly, k-means clustering was used to lock the image aspect ratio, in order to get more essential anchors which can help boost the segmentation performance. Finally, we proposed a GAN Mask R-CNN algorithm which achieved superior performance in comparison with the conventional Mask R-CNN, Mask-CNN, and k-means algorithms in terms of the Dice similarity coefficient (DSC) and the MICCAI metrics. The proposed algorithm also achieved superior performance in comparison with ten state-of-the-art algorithms in terms of six Boolean indicators. We hope that our work can be effectively used to optimize the segmentation and classification of liver anomalies.

Leaf Physiological Responses of Three Psammophytes to Combined Effects of Warming and Precipitation Reduction in Horqin Sandy Land, Northeast China.

The decreasing precipitation with global climate warming is the main climatic condition in some sandy grassland ecosystems. The understanding of physiological responses of psammophytes in relation to warming and precipitation is a possible way to estimate the response of plant community stability to climate change. We selected Lespedeza davurica, Artemisia scoparia, and Cleistogenes squarrosa in sandy grassland to examine the effect of a combination of climate warming and decreasing precipitation on relative water content (RWC), chlorophyll, proline, and antioxidant enzyme activities. We found that all experimental treatments have influenced RWC, chlorophyll, proline, and antioxidant enzyme activities of three psammophytes. L. davurica has the highest leaf RWC among the three psammophytes. With the intensification of precipitation reduction, the decreasing amplitude of chlorophyll from three psammophytes was L. davurica > C. squarrosa > A. scoparia. At the natural temperature, the malondialdehyde (MDA) content of the three psammophytes under severe drought treatment was much higher than other treatments, and their increasing degree was as follows: A. scoparia > C. squarrosa > L. davurica. At the same precipitation gradient, the proline of three psammophytes under warming was higher than the natural temperature. The differences in superoxide dismutase (SOD) among the three psammophytes were A. scoparia > L. davurica > C. squarrosa. Moreover, at natural temperature, more than 40% of precipitation reduction was most significant. Regardless of warming or not, the catalase (CAT) activity of A. scoparia under reduced precipitation treatments was higher than natural temperature, while the response of L. davurica was opposite. Correlation analyses evidenced that warming (T) was significant in L. davurica and precipitation (W) was significant in A. scoparia and C. squarrosa according to the Monte-Carlo permutation test (p = 0.002, 0.004, and 0.004). The study is important in predicting how local plants will respond to future climate change and assessing the possible effects of climate change on sandy grassland ecosystems.

Liver segmentation in CT imaging with enhanced mask region-based convolutional neural networks.

BACKGROUND: Liver segmentation in computed tomography (CT) imaging has been widely investigated as a crucial step for analyzing liver characteristics and diagnosing liver diseases. However, obtaining satisfactory liver segmentation performance is highly challenging because of the poor contrast between the liver and its surrounding organs and tissues, the high levels of CT image noise, and the wide variability in liver shapes among patients. METHODS: To overcome these challenges, we propose a novel method for liver segmentation in CT image sequences. This method uses an enhanced mask region-based convolutional neural network (Mask R-CNN) with graph-cut segmentation. Specifically, the k-nearest neighbor (k-NN) algorithm is employed to cluster the target liver pixels in order to get an appropriate aspect ratio. Then, anchors are adapted to the liver size using the ratio information. Thus, high-accuracy liver localization can be achieved using the anchors and rotation-invariant object recognition. Next, a fully convolutional network (FCN) is used to segment the foreground objects, and local fine-grained liver detection is realized by pixel prediction. Finally, a whole liver mask is obtained by Mask R-CNN proposed in this paper. RESULTS: We proposed a Mask R-CNN algorithm which achieved superior performance in comparison with the conventional Mask R-CNN algorithms in term of the dice similarity coefficient (DSC), and the Medical Image Computing and Computer-Assisted Intervention (MICCAI) metrics. CONCLUSIONS: Our experimental results demonstrate that the improved Mask R-CNN architecture has good performance, accuracy, and robustness for liver segmentation in CT image sequences.

[Quantitative experiment and analysis of gradient-induced eddy currents on magnetic resonance imaging].

Pulsed magnetic field gradients generated by gradient coils are widely used in signal location in magnetic resonance imaging (MRI). However, gradient coils can also induce eddy currents in final magnetic field in the nearby conducting structures which lead to distortion and artifact in images, misguiding clinical diagnosis. We tried in our laboratory to measure the magnetic field of gradient-induced eddy current in 1.5 T superconducting magnetic resonance imaging device; and extracted key parameters including amplitude and time constant of exponential terms according to inductance-resistance series mathematical module. These parameters of both self-induced component and crossing component are useful to design digital filters to implement pulse pre-emphasize to reshape the waveform. A measure device that is a basement equipped with phantoms and receiving coils was designed and placed in the isocenter of the magnetic field. By applying testing sequence, contrast experiments were carried out in a superconducting magnet before and after eddy current compensation. Sets of one dimension signal were obtained as raw data to calculate gradient-induced eddy currents. Curve fitting by least squares method was also done to match inductance-resistance series module. The results also illustrated that pulse pre-emphasize measurement with digital filter was correct and effective in reducing eddy current effect. Pre-emphasize waveform was developed based on system function. The usefulness of pre-emphasize measurement in reducing eddy current was confirmed and the improvement was also presented. All these are valuable for reducing artifact in magnetic resonance imaging device.

[Modeling and simulation of responses from ultrasonic linear phased array].

Phased array transducers are very attractive because the beam generated by the arrays can be electronically focused and steered. The present work characterizes far-field 2D properties of phased array system by functions that are deduced from rectangle source, rectangle line array and phased array based on point source. Results are presented for the distribution of ultrasound intensity on plane xoz and on x-axis by simulation using numerical calculation. It is shown that the shape of response of rectangle line array is modulated by the single array element. It is also demonstrated that the delay time of phased array is the key to steer the beam, sacrificing the value of main lobe and increasing the number of side lobes.

Alternative splicing and expression profile analysis of expressed sequence tags in domestic pig.

Domestic pig (Sus scrofa domestica) is one of the most important mammals to humans. Alternative splicing is a cellular mechanism in eukaryotes that greatly increases the diversity of gene products. Expression sequence tags (ESTs) have been widely used for gene discovery, expression profile analysis, and alternative splicing detection. In this study, a total of 712,905 ESTs extracted from 101 different non-normalized EST libraries of the domestic pig were analyzed. These EST libraries cover the nervous system, digestive system, immune system, and meat production related tissues from embryo, newborn, and adult pigs, making contributions to the analysis of alternative splicing variants as well as expression profiles in various stages of tissues. A modified approach was designed to cluster and assemble large EST datasets, aiming to detect alternative splicing together with EST abundance of each splicing variant. Much efforts were made to classify alternative splicing into different types and apply different filters to each type to get more reliable results. Finally, a total of 1,223 genes with average 2.8 splicing variants were detected among 16,540 unique genes. The overview of expression profiles would change when we take alternative splicing into account.

[A practicable model of a secure electronic medical record system].

In this article, a new application model has been given for digital signing technology used in the Electronic Medical Record system, which uses digital signature to implement authentication mechanism and doctor signing, and uses a notarial digital signature server to implement the third party's digital signature for notarial mechanism. It can prevent the others from modifying the doctor's record and prevent the doctor himself from modifying the record as well. Case history database preserves signed data to ensure the authenticity and validity, in law, of the Electronic Medical Record.

EST pipeline system: detailed and automated EST data processing and mining.

Expressed sequence tags (ESTs) are widely used in gene survey research these years. The EST Pipeline System, software developed by Hangzhou Genomics Institute (HGI), can automatically analyze different scalar EST sequences by suitable methods. All the analysis reports, including those of vector masking, sequence assembly, gene annotation, Gene Ontology classification, and some other analyses, can be browsed and searched as well as downloaded in the Excel format from the web interface, saving research efforts from routine data processing for biological rules embedded in the data.