Dose prediction for cervical cancer in radiotherapy based on the beam channel generative adversarial network.

Background: Existing deep learning methods, such as generative adversarial network (GAN) technology, face challenges when dealing with mixed datasets, which involve a combination of Intensity Modulated Radiotherapy (IMRT) and Volumetric Modulated Arc Therapy (VMAT). This issue significantly complicates the application of dose prediction in the field of radiotherapy. In this study, we propose a novel approach called beam channel GAN (Bc-GAN) to address the task of radiation dose prediction for mixed datasets. Bc-GAN introduces a dose prediction calculation method that requires less precision. By defining an approximate range for dose prediction, Bc-GAN limits the physical range of GAN prediction, resulting in more reasonable dose distribution predictions. Methods: We adopt a beam angle weighting method to determine the beam angle in the dose calculation. The dose of the beam with the highest weight is calculated using medical images and is then inputted into the artificial intelligence dose prediction model as the input channel. Additionally, we collect data from a total of 346 patients with Cervical Cancer (CC) for dataset. After cleaning the data, we exclude 51 cases with incomplete organ delineation, leaving us with 295 cases (IMRT: VMAT = 137:158) randomly divided into three sets: the training set, the validation set, and the test set, with proportions of 205:60:30, respectively. The assessment of model predictions was conducted via an analysis of dose distributions on the tomographic plane, dose volume histogram (DVH), and dosimetric parameters within the target zones and organs at risk (OAR). Results: After DVH analysis, minimal discrepancy was found between predicted and actual dose distributions in PTV and OAR. The predicted distribution aligned with clinical standards. Dosimetric parameters for PTV were generally lower in the predicted model, except for homogeneity index (HI) (0.238 ± 0.024, P = 0.017) and Dmax (53.599 ± 0.710 Gy, P = 1.8e-05). The prediction model varied in estimating doses for six organs. Specifically, small intestine showed higher V20 (67.92 ± 51.64 %, P = 0.019) and V30 (57.171 ± 1.213 %, P = 0.024) than manual planning. A similar trend was seen in colon's V30 (37.13 ± 61.14 %, P = 0.016). However, predicted bladder V30 (87.51 ± 41.44 %, P = 2.03e-16) was lower, indicating significant dosimetric differences. Conclusion: Overall, this study presents an innovative prediction method for CC in radiotherapy using the Bc-GAN model, addressing the challenges posed by different radiotherapy techniques. The proposed approach allows IMRT and VMAT in radiotherapy to be used as training sets, enabling the potential for large-scale engineering and commercialization applications of artificial intelligence (AI). The Bc-GAN-based prediction method for CC in radiotherapy not only reduces the amount of data needed for the training set but also expedites the model generation process. This approach can be applied to guide the development of clinical radiation therapy plans. Furthermore, future studies should consider extending the dose prediction method to encompass other types of tumors.

Developmental characteristics and control effects of myopia and eye diseases in children and adolescents: a school-based retrospective cohort study in Southwest China.

OBJECTIVES: To characterise the prevalence of myopia and eye diseases among school adolescents and children in Southwest China, and to evaluate the effectiveness of myopia control tools. DESIGN: Retrospective cohort study. SETTING: Across 95 basic education institutions in Southwest China. PARTICIPANTS: 96 146 children aged 3-17 years from a school-based survey conducted between 2019 and 2021. PRIMARY OUTCOME MEASURES: The data of vision assessment and eye disease examination of school students were analysed, including a total of four surveys once per semester. The prevalence of myopia categorised as low (-0.5D to -3.0D), moderate (-3.0D to -6.0D) and high (≥-6.0D), along with the prevalence of significant ocular diseases, was assessed. Stratified analyses were conducted to investigate the impact of correction time on visual acuity (VA) and biological parameters. Subsequently, the subjects across the groups were matched using the nearest neighbour method, followed by multidimensional statistical analysis. RESULTS: The prevalence of myopia among the surveyed students was 38.39%. After controlling for confounding variables, the statistical analysis revealed a 0.1 increase in mean VA within the orthokeratology group and a 0.1 decrease in VA within the spectacle group (p<0.001), with statistically significant differences in corneal radius, corneal curvature and equivalent spherical lens (p<0.05). Multivariate analysis indicated a statistically significant reduction in VA in the ophthalmopathy group compared with the control group (p=0.031). Furthermore, it was demonstrated that the risk of eye disease during vision correction was greater among older students than their younger counterparts (OR>1), and that female students exhibited a higher risk than male students (OR=1.5). CONCLUSIONS: The current high prevalence of myopia and eye diseases among Southwest China's school youths demands public health attention. Minors wearing orthokeratology lenses at night, especially in primary school, exhibit significantly improved naked-eye vision. However, vigilant eye healthcare during the correction period is crucial, especially for girls.

LUCMT: Learnable under-sampling and reconstructed network with cross multi-head attention transformer for accelerating MR image reconstruction.

BACKGROUND AND OBJECTIVE: As a widely used technique for Magnetic Resonance Image (MRI) acceleration, compressed sensing MRI involves two main issues: designing an effective sampling strategy and reconstructing the image from significantly under-sampled K-space data. In this paper, an innovative approach is proposed to address these two challenges simultaneously. METHODS: A novel MRI reconstruction method, termed as LUCMT, is implemented by integrating a learnable under-sampling strategy with a reconstruction network based on the Cross Multi-head Attention Transformer. In contrast to conventional static sampling methods, the proposed adaptive sampling scheme is processed optimally by learning the optimal sampling technique, which involves binarizing the sampling pattern by a sigmoid function and computing gradients by backpropagation. And the reconstruction network is designed by using CS-MRI depth unfolding network that incorporates a Cross Multi-head Attention (CMA) module with inertial and gradient descent terms. RESULTS: T1 brain MR images from the FastMRI dataset are used to validate the performance of the proposed method. A series of experiments are conducted to validate the superior performance of our proposed network in terms of quantitative metrics and visual quality. Compared with other state-of-the-art reconstruction methods, LUCMT achieves better reconstruction performances with more accurate details. Specifically, LUCMT achieves PSNR and SSIM results of 41.87/0.9749, 46.64/0.9868, 50.41/0.9924, and 53.51/0.9955 at sampling rates of 10 %, 20 %, 30 %, and 40 %, respectively. CONCLUSIONS: The proposed LUCMT method can provide a promising way for generating optimal under-sampling mask and accelerating MRI reconstruction accurately.

3MT-Net: A Multi-modal Multi-task Model for Breast Cancer and Pathological Subtype Classification Based on a Multicenter Study.

Breast cancer significantly impacts women's health, with ultrasound being crucial for lesion assessment. To enhance diagnostic accuracy, computer-aided detection (CAD) systems have attracted considerable interest. This study introduces a prospective deep learning architecture called "Multi-modal Multi-task Network" (3MT-Net). 3MT-Net utilizes a combination of clinical data, B-mode, and color Doppler ultrasound. We have designed the AM-CapsNet network, specifically tailored to extract crucial tumor features from ultrasound. To combine clinical data in 3MT-Net, we have employed a cascaded cross-attention to fuse information from three distinct sources. To ensure the preservation of pertinent information during the fusion of high-dimensional and low-dimensional data, we adopt the idea of ensemble learning and design an optimization algorithm to assign weights to different modalities. Eventually, 3MT-Net performs binary classification of benign and malignant lesions as well as pathological subtype classification. In addition, we retrospectively collected data from nine medical centers. To ensure the broad applicability of the 3MT-Net, we created two separate testsets and conducted extensive experiments. Furthermore, a comparative analysis was conducted between 3MT-Net and the industrial-grade CAD product S-detect. The AUC of 3MT-Net surpasses S-Detect by 1.4% to 3.8%.

Feasibility of a novel unassisted single-channel transcolonic endoscopic appendectomy for the treatment of appendiceal lesions (with video).

BACKGROUND: Transcolonic endoscopic appendectomy (TEA) is rapidly evolving and has been reported as a minimally invasive alternative to appendectomy. We aimed to characterize the feasibility and safety of a novel unassisted single-channel TEA. METHOD: We retrospectively investigated 23 patients with appendicitis or appendiceal lesions who underwent TEA from February 2016 to December 2022. We collected clinicopathological characteristics, procedure­related parameters, and follow­up data and analyzed the impact of previous abdominal surgery and traction technique. RESULTS: The mean age was 56.0 years. Of the 23 patients with appendiceal lesions, fourteen patients underwent TEA and nine underwent traction-assisted TEA (T-TEA). Eight patients (34.8%) had previous abdominal surgery. The En bloc resection rate was 95.7%. The mean procedure duration was 91.1 ± 45.5 min, and the mean wound closure time was 29.4 ± 18.6 min. The wounds after endoscopic appendectomy were closed with clips (21.7%) or a combination of clip closure and endoloop reinforcement (78.3%), and the median number of clips was 7 (range, 3-15). Three patients (13.0%) experienced major adverse events, including two delayed perforations (laparoscopic surgery) and one infection (salvage endoscopic suture). During a median follow-up of 23 months, no residual or recurrent lesions were observed, and no recurrence of abdominal pain occurred. There were no significant differences between TEA and T-TEA groups and between patients with and without abdominal surgery groups in each factor. CONCLUSION: Unassisted single-channel TEA for patients with appendiceal lesions has favorable short- and long-term outcomes. TEA can safely and effectively treat appendiceal disease in appropriately selected cases.

Investigating cortical complexity and connectivity in rats with schizophrenia.

Background: The above studies indicate that the SCZ animal model has abnormal gamma oscillations and abnormal functional coupling ability of brain regions at the cortical level. However, few researchers have focused on the correlation between brain complexity and connectivity at the cortical level. In order to provide a more accurate representation of brain activity, we studied the complexity of electrocorticogram (ECoG) signals and the information interaction between brain regions in schizophrenic rats, and explored the correlation between brain complexity and connectivity. Methods: We collected ECoG signal from SCZ rats. The frequency domain and time domain functional connectivity of SCZ rats were evaluated by magnitude square coherence and mutual information (MI). Permutation entropy (PE) and permutation Lempel-Ziv complexity (PLZC) were used to analyze the complexity of ECoG, and the relationship between them was evaluated. In addition, in order to further understand the causal structure of directional information flow among brain regions, we used phase transfer entropy (PTE) to analyze the effective connectivity of the brain. Results: Firstly, in the high gamma band, the complexity of brain regions in SCZ rats is higher than that in normal rats, and the neuronal activity is irregularity. Secondly, the information integration ability of SCZ rats decreased and the communication of brain network information was hindered at the cortical level. Finally, compared with normal rats, the causal relationship between brain regions of SCZ rats was closer, but the information interaction center was not clear. Conclusion: The above findings suggest that at the cortical level, complexity and connectivity are valid biomarkers for identifying SCZ. This bridges the gap between peak potentials and EEG. This may help to understand the pathophysiological mechanisms at the cortical level in schizophrenics.

Correction: Ran et al. Nomogram for Predicting Recurrence-Free Survival of Primary Localized Gastrointestinal Stromal Tumor. J. Pers. Med. 2023, 13, 498.

In the original publication [...].

Fast detection of moisture content and freshness for loquats using optical fiber spectroscopy.

Detection of the moisture content (MC) and freshness for loquats is crucial for achieving optimal taste and economic efficiency. Traditional methods for evaluating the MC and freshness of loquats have disadvantages such as destructive sampling and time-consuming. To investigate the feasibility of rapid and non-destructive detection of the MC and freshness for loquats, optical fiber spectroscopy in the range of 200-1000 nm was used in this study. The full spectra were pre-processed using standard normal variate method, and then, the effective wavelengths were selected using competitive adaptive weighting sampling (CARS) and random frog algorithms. Based on the selected effective wavelengths, prediction models for MC were developed using partial least squares regression (PLSR), multiple linear regression, extreme learning machine, and back-propagation neural network. Furthermore, freshness level discrimination models were established using simplified k nearest neighbor, support vector machine (SVM), and partial least squares discriminant analysis. Regarding the prediction models, the CARS-PLSR model performed relatively better than the other models for predicting the MC, with R 2 P and RPD values of 0.84 and 2.51, respectively. Additionally, the CARS-SVM model obtained superior discrimination performance, with 100% accuracy for both calibration and prediction sets. The results demonstrated that optical fiber spectroscopy technology is an effective tool to fast detect the MC and freshness for loquats.

Validating the performance of organ dysfunction scores in children with infection: A cohort study.

PURPOSE: We aimed to validate the performance of six available scoring models for predicting hospital mortality in children with suspected or confirmed infections. METHODS: This single-center retrospective cohort study included pediatric patients admitted to the PICU for infection. The primary outcome was hospital mortality. The six scores included the age-adapted pSOFA score, SIRS score, PELOD2 score, Sepsis-2 score, qSOFA score, and PMODS. RESULTS: Of the 5,356 children admitted to the PICU, 9.1% (488) died, and 25.1% (1,342) had basic disease with a mortality rate of 12.7% (171); 65.3% (3,499) of the patients were younger than 2 years, and 59.4% (3,183) were male. The discrimination abilities of the pSOFA and PELOD2 scores were superior to those of the other models. The calibration curves of the pSOFA and PELOD2 scores were consistent between the predictions and observations. Elevated lactate levels were a risk factor for mortality. CONCLUSION: The pSOFA and PELOD2 scores had superior predictive performance for mortality. Given the relative unavailability of items and clinical operability, the pSOFA score should be recommended as an optimal tool for acute organ dysfunction in pediatric sepsis patients. Elevated lactate levels are related to a greater risk of death from infection in children in the PICU.

Combining blood pressure variability and heart rate variability to analyze the autonomic nervous function of rotenone induced Parkinson's rat model.

BACKGROUND: Parkinson's patients have significant autonomic dysfunction, early detect the disorder is a major challenge. To assess the autonomic function in the rat model of rotenone induced Parkinson's disease (PD), Blood pressure and ECG signal acquisition are very important. NEW METHOD: We used telemetry to record the electrocardiogram and blood pressure signals from awake rats, with linear and nonlinear analysis techniques calculate the heart rate variability (HRV) and blood pressure variability (BPV). we applied nonlinear analysis methods like sample entropy and detrended fluctuation analysis to analyze blood pressure signals. Particularly, this is the first attempt to apply nonlinear analysis to the blood pressure evaluate in rotenone induced PD model rat. RESULTS: HRV in the time and frequency domains indicated sympathetic-parasympathetic imbalance in PD model rats. Linear BPV analysis didn't reflect changes in vascular function and blood pressure regulation in PD model rats. Nonlinear analysis revealed differences in BPV, with lower sample entropy results and increased detrended fluctuation analysis results in the PD group rats. COMPARISON WITH EXISTING METHODS AND CONCLUSIONS: our experiments demonstrate the ability to evaluate autonomic dysfunction in models of Parkinson's disease by combining the analysis of BPV with HRV, consistent with autonomic impairment in PD patients. Nonlinear analysis by blood pressure signal may help in early detection of the PD. It indicates that the fluctuation of blood pressure in the rats in the rotenone model group tends to be regular and predictable, contributes to understand the PD pathophysiological mechanisms and to find strategies for early diagnosis.

The relationship between Glasgow Prognostic Score and hospital duration in patients with inflammatory bowel diseases.

BACKGROUND AND OBJECTIVES: Both hypoalbuminemia and inflammation were common in patients with inflammatory bowel diseases (IBD), however, the combination of the two parameters on hospital duration re-mained unknown. METHODS AND STUDY DESIGN: This is a retrospective two-centre study performed in two tertiary hospitals in Shanghai, China. Serum levels of C-Reactive Protein (CRP) and albumin (ALB) were measured within 2 days of admission. Glasgow prognostic score (GPS), based on CRP and ALB, was calculated as follows: point "0" as CRP <10 mg/L and ALB ≥35 g/L; point "1" as either CRP ≥10 mg/L or ALB <35 g/L; point "2" as CRP ≥10 mg/L and ALB <35 g/L. Patients with point "0" were classified as low-risk while point "2" as high-risk. Length of hospital stay (LOS) was defined as the interval between admission and discharge. RESULTS: The proportion of low-risk and high-risk was 69.3% and 10.5% respectively among 3,009 patients (65% men). GPS was associated with LOS [ß=6.2 d; 95% CI (confidence interval): 4.0 d, 8.4 d] after adjustment of potential co-variates. Each point of GPS was associated with 2.9 days (95% CI: 1.9 d, 3.9 d; ptrend<0.001) longer in fully adjusted model. The association was stronger in patients with low prealbumin levels, hypocalcaemia, and hypokalaemia relative to their counterparts. CONCLUSIONS: GPS was associated with LOS in IBD patients. Our results highlighted that GPS could serve as a convenient prognostic tool associated with nutritional status and clinical outcome.

Multi-risk factors joint prediction model for risk prediction of retinopathy of prematurity.

Purpose: Retinopathy of prematurity (ROP) is a retinal vascular proliferative disease common in low birth weight and premature infants and is one of the main causes of blindness in children.In the context of predictive, preventive and personalized medicine (PPPM/3PM), early screening, identification and treatment of ROP will directly contribute to improve patients' long-term visual prognosis and reduce the risk of blindness. Thus, our objective is to establish an artificial intelligence (AI) algorithm combined with clinical demographics to create a risk model for ROP including treatment-requiring retinopathy of prematurity (TR-ROP) infants. Methods: A total of 22,569 infants who underwent routine ROP screening in Shenzhen Eye Hospital from March 2003 to September 2023 were collected, including 3335 infants with ROP and 1234 infants with TR-ROP among ROP infants. Two machine learning methods of logistic regression and decision tree and a deep learning method of multi-layer perceptron were trained by using the relevant combination of risk factors such as birth weight (BW), gestational age (GA), gender, whether multiple births (MB) and mode of delivery (MD) to achieve the risk prediction of ROP and TR-ROP. We used five evaluation metrics to evaluate the performance of the risk prediction model. The area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUCPR) were the main measurement metrics. Results: In the risk prediction for ROP, the BW + GA demonstrated the optimal performance (mean ± SD, AUCPR: 0.4849 ± 0.0175, AUC: 0.8124 ± 0.0033). In the risk prediction of TR-ROP, reasonable performance can be achieved by using GA + BW + Gender + MD + MB (AUCPR: 0.2713 ± 0.0214, AUC: 0.8328 ± 0.0088). Conclusions: Combining risk factors with AI in screening programs for ROP could achieve risk prediction of ROP and TR-ROP, detect TR-ROP earlier and reduce the number of ROP examinations and unnecessary physiological stress in low-risk infants. Therefore, combining ROP-related biometric information with AI is a cost-effective strategy for predictive diagnostic, targeted prevention, and personalization of medical services in early screening and treatment of ROP.

Developmental and stem cell biology's bright future.

The next 50 years of developmental biology will illuminate exciting new discoveries but are also poised to provide solutions to important problems society faces. Ten scientists whose work intersects with developmental biology in various capacities tell us about their vision for the future.

Associations between metabolic dysfunction-associated fatty liver disease and atherosclerotic cardiovascular disease.

Non-alcoholic fatty liver disease (NAFLD) is closely related to metabolic syndrome and remains a major global health burden. The increased prevalence of obesity and type 2 diabetes mellitus (T2DM) worldwide has contributed to the rising incidence of NAFLD. It is widely believed that atherosclerotic cardiovascular disease (ASCVD) is associated with NAFLD. In the past decade, the clinical implications of NAFLD have gone beyond liver-related morbidity and mortality, with a majority of patient deaths attributed to malignancy, coronary heart disease (CHD), and other cardiovascular (CVD) complications. To better define fatty liver disease associated with metabolic disorders, experts proposed a new term in 2020 - metabolic dysfunction associated with fatty liver disease (MAFLD). Along with this new designation, updated diagnostic criteria were introduced, resulting in some differentiation between NAFLD and MAFLD patient populations, although there is overlap. The aim of this review is to explore the relationship between MAFLD and ASCVD based on the new definitions and diagnostic criteria, while briefly discussing potential mechanisms underlying cardiovascular disease in patients with MAFLD.

Revolutionizing breast cancer Ki-67 diagnosis: ultrasound radiomics and fully connected neural networks (FCNN) combination method.

PURPOSE: This study aims to assess the diagnostic value of ultrasound habitat sub-region radiomics feature parameters using a fully connected neural networks (FCNN) combination method L2,1-norm in relation to breast cancer Ki-67 status. METHODS: Ultrasound images from 528 cases of female breast cancer at the Affiliated Hospital of Xiangnan University and 232 cases of female breast cancer at the Affiliated Rehabilitation Hospital of Xiangnan University were selected for this study. We utilized deep learning methods to automatically outline the gross tumor volume and perform habitat clustering. Subsequently, habitat sub-regions were extracted to identify radiomics features and underwent feature engineering using the L1,2-norm. A prediction model for the Ki-67 status of breast cancer patients was then developed using a FCNN. The model's performance was evaluated using accuracy, area under the curve (AUC), specificity (Spe), positive predictive value (PPV), negative predictive value (NPV), Recall, and F1. In addition, calibration curves and clinical decision curves were plotted for the test set to visually assess the predictive accuracy and clinical benefit of the models. RESULT: Based on the feature engineering using the L1,2-norm, a total of 9 core features were identified. The predictive model, constructed by the FCNN model based on these 9 features, achieved the following scores: ACC 0.856, AUC 0.915, Spe 0.843, PPV 0.920, NPV 0.747, Recall 0.974, and F1 0.890. Furthermore, calibration curves and clinical decision curves of the validation set demonstrated a high level of confidence in the model's performance and its clinical benefit. CONCLUSION: Habitat clustering of ultrasound images of breast cancer is effectively supported by the combined implementation of the L1,2-norm and FCNN algorithms, allowing for the accurate classification of the Ki-67 status in breast cancer patients.

Hyperglycemia Inhibits Hepatic SHBG Synthesis Through the NGBR-AMPK-HNF4 Pathway in Rats with Polycystic Ovary Syndrome Induced by Letrozole in Combination with a High-Fat Diet.

SCOPE: Polycystic ovary syndrome (PCOS) is closely related to non-alcoholic fatty liver disease (NAFLD), and sex hormone-binding globulin (SHBG) is a glycoprotein produced by the liver. Hepatic lipogenesis inhibits hepatic SHBG synthesis, which leads to hyperandrogenemia and ovarian dysfunction in PCOS. Therefore, this study aims to characterize the mechanism whereby liver lipogenesis inhibits SHBG synthesis. METHODS AND RESULTS: This study establishes a rat model of PCOS complicated by NAFLD using a high-fat diet in combination with letrozole and performs transcriptomic analysis of the liver. Transcriptomic analysis of the liver shows that the expression of neurite growth inhibitor-B receptor (NgBR), hepatocyte nuclear factor 4α (HNF4α), and SHBG is low. Meantime, HepG2 cells are treated with palmitic acid (PA) to model NAFLD in vitro, which causes decreases in the expression of NgBR, HNF4α, and SHBG. However, the expression of HNF4α and SHBG is restored by treatment with the AMP-activated protein kinase (AMPK) agonist AICAR. CONCLUSIONS: NgBR regulates the expression of HNF4α by activating the AMPK signaling pathway, thereby affecting the synthesis of SHBG in the liver. Further mechanistic studies regarding the effect of liver fat on NGBR expression are warranted.

Diosmetin ameliorates osteoarthritic inflammation in vivo and ECM macromolecules degradation in interleukin-1ß-stimulated murine chondrocytes through the Nrf2/NF-κB pathway.

INTRODUCTION: Osteoarthritis (OA) is a prevailing degenerative disease in elderly population and can lead to severe joint dysfunction. Studies have revealed various pharmacological activities of diosmetin, including the anti-OA efficacy. The present study further investigated its effect on interleukin (IL)-1ß-induced OA in chondrocytes. MATERIAL AND METHODS: Primary chondrocytes were isolated from young mice, stimulated with IL-1ß (10 ng/mL), and pretreated with diosmetin (10 and 20 µM) to conduct the in vitro assays. CCK-8 assay assessed the cytotoxicity of diosmetin whereas the levels of inflammatory factors (PGE2, nitrite, TNF-α, and IL-6) in homogenized cells were evaluated by ELISA. The levels of inflammatory cytokines, content of extracellular matrix (ECM), and signaling-related proteins (Nrf2, HO-1, and NF-κB p65) were assessed by western blotting. Expression of collagen II, p65, and Nrf2 in the chondrocytes was confirmed by immunofluorescence staining. The chondrocytes treated with IL-1ß and diosmetin were transfected with Nrf2 knockdown plasmid (si-Nrf2) to investigate the role of Nrf2. In vivo OA mouse model was induced by surgically destabilizing the medial meniscus (DMM). Safranin O staining was conducted to assess the OA severity in the knee-joint tissue. RESULTS: Diosmetin suppressed the expression of iNOS, COX-2, PGE2, nitrite, TNF-α, IL-6, MMP-13, and ADAMTS-5 induced by IL-1ß in chondrocytes. The expression of p-p65, p-IκBα, and nuclear p65 was decreased whereas that of Nrf2 and HO-1 increased by diosmetin treatment in IL-1ß-treated chondrocytes. Nrf2 knockdown by siRNA reversed the inhibitory effect of diosmetin on IL-1ß-induced degradation of ECM proteins and inflammatory factors in cultured chondrocytes. In the DMM-induced model of OA, diosmetin alleviated cartilage degeneration and decreased the Osteoarthritis Research Society International score. CONCLUSIONS: Diosmetin ameliorates expression of inflammation biomarkers and ECM macromolecules degradation in cultured murine chondrocytes via inactivation of NF-κB signaling by activating Nrf2/HO-1 signaling pathway.

Precision dose prediction for breast cancer patients undergoing IMRT: The Swin-UMamba-Channel Model.

BACKGROUND: Radiation therapy is one of the crucial treatment modalities for cancer. An excellent radiation therapy plan relies heavily on an outstanding dose distribution map, which is traditionally generated through repeated trials and adjustments by experienced physicists. However, this process is both time-consuming and labor-intensive, and it comes with a degree of subjectivity. Now, with the powerful capabilities of deep learning, we are able to predict dose distribution maps more accurately, effectively overcoming these challenges. METHODS: In this study, we propose a novel Swin-UMamba-Channel prediction model specifically designed for predicting the dose distribution of patients with left breast cancer undergoing radiotherapy after total mastectomy. This model integrates anatomical position information of organs and ray angle information, significantly enhancing prediction accuracy. Through iterative training of the generator (Swin-UMamba) and discriminator, the model can generate images that closely match the actual dose, assisting physicists in quickly creating DVH curves and shortening the treatment planning cycle. Our model exhibits excellent performance in terms of prediction accuracy, computational efficiency, and practicality, and its effectiveness has been further verified through comparative experiments with similar networks. RESULTS: The results of the study indicate that our model can accurately predict the clinical dose of breast cancer patients undergoing intensity-modulated radiation therapy (IMRT). The predicted dose range is from 0 to 50 Gy, and compared with actual data, it shows a high accuracy with an average Dice similarity coefficient of 0.86. Specifically, the average dose change rate for the planning target volume ranges from 0.28 % to 1.515 %, while the average dose change rates for the right and left lungs are 2.113 % and 0.508 %, respectively. Notably, due to their small sizes, the heart and spinal cord exhibit relatively higher average dose change rates, reaching 3.208 % and 1.490 %, respectively. In comparison with similar dose studies, our model demonstrates superior performance. Additionally, our model possesses fewer parameters, lower computational complexity, and shorter processing time, further enhancing its practicality and efficiency. These findings provide strong evidence for the accuracy and reliability of our model in predicting doses, offering significant technical support for IMRT in breast cancer patients. CONCLUSION: This study presents a novel Swin-UMamba-Channel dose prediction model, and its results demonstrate its precise prediction of clinical doses for the target area of left breast cancer patients undergoing total mastectomy and IMRT. These remarkable achievements provide valuable reference data for subsequent plan optimization and quality control, paving a new path for the application of deep learning in the field of radiation therapy.

A fundus image dataset for intelligent retinopathy of prematurity system.

Image-based artificial intelligence (AI) systems stand as the major modality for evaluating ophthalmic conditions. However, most of the currently available AI systems are designed for experimental research using single-central datasets. Most of them fell short of application in real-world clinical settings. In this study, we collected a dataset of 1,099 fundus images in both normal and pathologic eyes from 483 premature infants for intelligent retinopathy of prematurity (ROP) system development and validation. Dataset diversity was visualized with a spatial scatter plot. Image classification was conducted by three annotators. To the best of our knowledge, this is one of the largest fundus datasets on ROP, and we believe it is conducive to the real-world application of AI systems.