Search

In recent years, UNet and its derivative networks have gained widespread recognition as major methods of medical image segmentation. However, networks like UNet often struggle with Point-of-Care (POC) healthcare applications due to their high number of parameters and computational complexity. To tackle these challenges, this paper introduces an efficient network designed for medical image segmentation called MCU-Net, which leverages ConvNeXt to enhance UNet. 1) Based on ConvNeXt, MCU-Net proposes the MCU Block, which employs techniques such as large kernel convolution, depth-wise separable convolution, and an inverted bottleneck design. To ensure stable segmentation performance, it also integrates global response normalization (GRN) layers and Gaussian Error Linear Unit (GELU) activation functions. 2) Additionally, MCU-Net introduces an enhanced Multi-Scale Convolution Attention (MSCA) module after the original UNet's skip connections, emphasizing medical image features and capturing semantic insights across multiple scales. 3)The downsampling process replaces pooling layers with convolutions, and both upsampling and downsampling stages incorporate batch normalization (BN) layers to enhance model stability during training. The experimental results demonstrate that MCU-Net, with a parameter count of 2.19 million and computational complexity of 19.73 FLOPs, outperforms other segmentation models. The overall performance of MCU-Net in medical image segmentation surpasses that of other models, achieving a Dice score of 91.8% and mIoU of 84.7% on the GlaS dataset. When compared to UNet on the BUSI dataset, MCU-Net shows an improvement of 2% in Dice and 2.9% in mIoU. [ABSTRACT FROM AUTHOR]

This study is aimed at examining the impact of ChatGPT on pediatric endocrine and metabolic conditions, particularly in the areas of screening and diagnosis, in both Chinese and English modes. A 40-question questionnaire covering the four most common pediatric endocrine and metabolic conditions was posed to ChatGPT in both Chinese and English three times each. Six pediatric endocrinologists evaluated the responses. ChatGPT performed better when responding to questions in English, with an unreliable rate of 7.5% compared to 27.5% for Chinese questions, indicating a more consistent response pattern in English. Among the reliable questions, the answers were more comprehensive and satisfactory in the English mode. We also found disparities in ChatGPT's performance when interacting with different target groups and diseases, with improved performance for questions posed by clinicians in English and better performance for questions related to diabetes and overweight/obesity in Chinese for both clinicians and patients. Language comprehension, providing incomprehensive answers, and errors in key data were the main contributors to the low scores, according to reviewer feedback. Conclusion: Despite these limitations, as ChatGPT continues to evolve and expand its network, it has significant potential as a practical and effective tool for clinical diagnosis and treatment. What is Known: • The deep learning-based large-language model ChatGPT holds great promise for improving clinical practice for both physicians and patients and has the potential to increase the speed and accuracy of disease screening and diagnosis, as well as enhance the overall efficiency of the medical process. However, the reliability and appropriateness of AI model responses in specific field remains unclear. • This study focused on the reliability and appropriateness of AI model responses to straightforward and fundamental questions related to the four most prevalent pediatric endocrine and metabolic disorders, for both healthcare providers and patients, in different language scenarios. What is New: • The AI model performed better when responding to questions in English, with more consistent, as well as more comprehensive and satisfactory responses. In addition, we also found disparities in ChatGPT's performance when interacting with different target groups and different diseases. • Despite these limitations, as ChatGPT continues to evolve and expand its network, it has significant potential as a practical and effective tool for clinical diagnosis and treatment. [ABSTRACT FROM AUTHOR]

Automatic and precise segmentation of lung images can assist doctors in locating and diagnosing lung lesions. However, current traditional lung CT image lesion segmentation algorithms suffer from the problem of low segmentation accuracy, while deep learning-based segmentation algorithms struggle to strike a better balance between lightweight and high accuracy. In response to this issue, a multi-scale and lightweight U-Net lung image segmentation algorithm with an attention mechanism is proposed. This algorithm introduces CA convolution after the convolution in the encoding stage to extract channel relationships and positional information from the feature maps. Furthermore, the RFB module is employed to extract features from different perspectives. Lastly, upward residual connections are introduced between the RFB modules in the encoder and decoder to enhance inter-network information interaction. Experiments conducted on the LUNA (lung nodule analysis) dataset and the COVID-QU-Ex dataset for COVID-19 pneumonia demonstrate that the proposed MSA-UNet algorithm achieves the best results in terms of Precision and Dice metrics. It outperforms mainstream models such as U-Net++ and DeeplabV3+ in terms of segmentation effectiveness and segmentation generality. The model has a floating-point operation count (FLOPs) of 18.15 G, a network parameter counts of 8.83×106, and achieves a Precision of 99.37%. The algorithm achieves a good balance between computational efficiency, model size, and segmentation accuracy. [ABSTRACT FROM AUTHOR]

Background: ABCC8 variants can cause hyperinsulinemia by activating or deactivating gene expression. This study used targeted exon sequencing to investigate genetic variants of ABCC8 and the associated phenotypic features in Chinese patients with hyperinsulinemic hypoglycemia (HH). Methods: We enrolled eight Chinese children with HH and analyzed their clinical characteristics, laboratory results, and genetic variations. Results: The age at presentation among the patients ranged from neonates to 0.6 years old, and the age at diagnosis ranged from 1 month to 5 years, with an average of 1.3 ± 0.7 years. Among these patients, three presented with seizures, and five with hypoglycemia. One patient (Patient 7) also had microcephaly. All eight patients exhibited ABCC8 abnormalities, including six missense mutations (c. 2521 C > G, c. 3784G > A, c. 4478G > A, c. 4532T > C, c. 2669T > C, and c. 331G > A), two deletion-insertion mutations (c. 3126_3129delinsTC and c. 3124_3126delins13), and one splicing mutation (c. 1332 + 2T > C). Two of these mutations (c. 3126_3129delinsTC and c. 4532T > C) are novel. Six variations were paternal, two were maternal, and one was de novo. Three patients responded to diazoxide and one patient responded to octreotide treatment. All there patients had diazoxide withdrawal with age. Two patients (patients 3 and 7) were unresponsive to both diazoxide and octreotide and had mental retardation. Conclusions: Gene analysis can aid in the classification, treatment, and prognosis of children with HH. In this study, the identification of seven known and two novel variants in the ABCC8 gene further enriched the variation spectrum of the gene. [ABSTRACT FROM AUTHOR]

Fumonisins (FBs), particularly fumonisin B1 (FB1) and fumonisin B2 (FB2) produced mainly by Fusarium verticillioide and Fusarium proliferatum, are common contaminants in animal feed and pose a serious threat to both animal and human health. The use of microbial enzymes to efficiently and specifically convert fumonisins into non-toxic or low-toxic metabolites has emerged as the most promising approach. However, most of the available enzymes have only been evaluated in vitro and lack systematic evaluation in vivo. In this study, the detoxification efficacy of two carboxylesterases, FumD (FUMzyme®) and FumDSB, was evaluated comparatively in piglets. The results show that feeding piglets 4.4 mg/kg FBs-contaminated diets for 32 days did not significantly affect the average daily gain, organ indices, and immunoglobulins of the piglets. However, a significant reduction (21.2%) in anti-inflammatory cytokine interleukin-4 was observed in the FBs group, and supplementation with FUMzyme® and FumDSB significantly increased interleukin-4 by 62.1% and 28.0%, respectively. In addition, FBs-contaminated diets resulted in a 3-fold increase in the serum sphinganine/sphingosine (Sa/So) ratio, which is a specific biomarker that has been used to accurately reflect fumonisin levels. The serum Sa/So ratio was significantly reduced by 48.8% after the addition of FUMzyme®, and was insignificantly reduced by 8.2% in the FumDSB group. These results suggested that FUMzyme was more effective than FumDSB in mitigating FBs toxicity in piglets by down-regulating the Sa/So ratio. [ABSTRACT FROM AUTHOR]

Generalized arterial calcification of infancy (GACI) is a rare autosomal-recessive disease characterized by extensive arterial calcification in infancy, with clinical manifestations such as arterial stenoses and heart failure. The ENPP1 inactivation mutation has been identified as a potential defect in most of the cases of GACI, while mutations in ABCC6 are demonstrated in patients who are genotyped as pseudoxanthoma elasticum and only limited cases of GACI are reported. Whole-exome sequencing was applied for the detection of pathogenic variants. Copy-number variants of pathogenic genes were also evaluated through a bioinformatic process and were further validated by real-time quantitative PCR. In this report, we described the clinical information and treatment of a patient with extensive arterial calcification. We have identified the underlying cause as biallelic mutations in ABCC6 (NM_00117: exon30, c.4223_4227dupAGCTC p.(Leu1410Serfs*56)) and a unique exonic deletion that spans from the first to the fourth exons of ABCC6 (chr16:16313388-16330869)). This discovery was made by utilizing a combined genetic testing approach. With the review of previously reported GACI patients with ABCC6 mutation, our work contributed to enriching the mutation spectrum of GACI and providing further information on this rare form of inherited disorder. [ABSTRACT FROM AUTHOR]

With the increasing demand for resources from cloud computing users, enhancing the energy efficiency of data centers and ensuring the Quality of Service have become noteworthy research topics. Most Previous studies on Virtual Machine (VM) consolidation often neglect the delay and energy consumption associated with Power Mode Transitions (PMTs), leading to potential deviations in experimental results from real-world scenarios. In this paper, we propose a Two-Level Heuristics Virtual Machine Consolidation (TLHVMC) method that takes into account the overheads of PMTs. This method employs a Greedy Strategy-based hybrid heuristic Placement (GSP) algorithm for resource allocation. After incorporating underloaded host detection for host classification, GSP applies distinct greedy strategies on various host lists, which balances data center workload and minimizes active hosts. Moreover, Time Window-based Centralized power mode Control policies are implemented to centrally manage host power modes. These policies improve energy-saving by suspending idle hosts and reduce the Service Level Agreement violations by adaptively resuming hosts based on the data center’s state within a time window. Experimental results on real workload traces show that TLHVMC significantly improves the energy efficiency of the data center and maintains the required cloud system performance compared to some other VM consolidation algorithms. [ABSTRACT FROM AUTHOR]