BACKGROUND:The extent to which infection versus vaccination has conferred similarly durable severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) immunity during the Omicron era remains unclear. METHODS:In a cohort of 4496 adults under continued serological surveillance throughout the first year of Omicron-predominant SARS-CoV-2 transmission, we examined incidence of new infection among individuals whose last known antigenic exposure was either recent (<90 days) or remote (≥90 days) infection or vaccination. RESULTS:We adjudicated 2053 new-onset infections occurring between 15 December 2021 through 22 December 2022. In multivariable-adjusted analyses, compared to individuals whose last known exposure was remote vaccination, those with recent vaccination (odds ratio [OR], 0.82 [95% confidence interval {CI}, .73-.93]; P = .002) or recent infection (OR, 0.14 [95% CI, .05-.45]; P = .001) had lower risk for new infection within the subsequent 90-day period. Given a significant age interaction (P = .004), we found that remote infection compared to remote vaccination was associated with significantly greater new infection risk in persons aged ≥60 years (OR, 1.88 [95% CI, 1.13-3.14]; P = .015) with no difference seen in those <60 years (1.03 [95% CI, .69-1.53]; P = .88). CONCLUSIONS:During the initial year of Omicron, prior infection and vaccination both offered protection against new infection. However, remote prior infection was less protective than remote vaccination for individuals aged ≥60 years. In older adults, immunity gained from vaccination appeared more durable than immunity gained from infection.

Given the importance of steatotic liver disease (SLD) in relation to cardiovascular disease (CVD) risks, we have followed with great interest the recent advances in the field including SLD nomenclature modifications to replace non-alcoholic fatty liver disease (NAFLD) with metabolic dysfunction-associated steatotic liver disease (MASLD). 1 Rinella M.E. Lazarus J.V. Ratziu V. et al. A multisociety Delphi consensus statement on new fatty liver disease nomenclature. Journal of Hepatology. 2023; 79: 1542-1556 Abstract Full Text Full Text PDF PubMed Scopus (450) Google Scholar In particular, we appreciate the inclusion of "metabolic" in the terminology and addition of cardiometabolic diagnoses within definitional criteria given the need to improve our understanding of the disease and its sequelae. Awareness of NAFLD as a highly prevalent and potent cardiometabolic risk factor was only beginning to emerge within the cardiovascular field prior to publication of nomenclature changes by the Journal of Hepatology. 2 Duell P.B. Welty F.K. Miller M. et al. Nonalcoholic fatty liver disease and cardiovascular risk: a scientific statement from the American Heart Association. Arteriosclerosis, thrombosis, and vascular biology. 2022; 42: e168-e185 Crossref PubMed Scopus (164) Google Scholar We anticipate this recognition will continue to grow for several reasons. First, a subsequent report in the Journal has demonstrated strong consistency between MASLD and NAFLD clinical profiles and outcomes. 3 Younossi Z.M. Paik J.M. Stepanova M. et al. Clinical profiles and mortality rates are similar for metabolic dysfunction-associated steatotic liver disease and non-alcoholic fatty liver disease. Journal of Hepatology. 2024; 80: 694-701 Abstract Full Text Full Text PDF Scopus (8) Google Scholar Second, the FDA recently approved Resmetirom for metabolic dysfunction associated steatohepatitis (MASH), 4 U.S. Food and Drug Administration. FDA Approves First Treatment for Patients with Liver Scarring Due to Fatty Liver Disease [Press Release]. https://www.fda.gov/news-events/press-announcements/fda-approves-first-treatment-patients-liver-scarring-due-fatty-liver-disease; March 14, 2024. Google Scholar and this agent appears to confer significant positive effects on atherogenic lipid profiles in addition to MASH. 5 Harrison S.A. Bedossa P. Guy C.D. et al. A Phase 3, Randomized, Controlled Trial of Resmetirom in NASH with Liver Fibrosis. New England Journal of Medicine. 2024; 390: 497-509 Crossref PubMed Scopus (36) Google Scholar Third, obesity-related medications including GLP-1 agonists have been shown to improve both hepatic and cardiovascular risk resulting in a broadening CVD prevention framework within therapies for traditionally "metabolic-related" conditions. 6 U.S. Food and Drug Administration. FDA Approves First Treatment to Reduce Risk of Serious Heart Problems Specifically in Adults with Obesity or Overweight. March 8, 2024. Google Scholar Given these rapid advances in the field, we expect an increasing need for collaboration between hepatologists and cardiologists to address SLD and its epidemiological sequelae. In this context, we wish to raise considerations related to the cardiovascular impact of SLD that may be less immediately apparent. Our observations arise from having examined the effects of standardized diagnostic thresholds for SLD and hepatic fibrosis on vascular health in males and females. A multisociety Delphi consensus statement on new fatty liver disease nomenclatureJournal of HepatologyVol. 79Issue 6PreviewThe principal limitations of the terms NAFLD and NASH are the reliance on exclusionary confounder terms and the use of potentially stigmatising language. This study set out to determine if content experts and patient advocates were in favour of a change in nomenclature and/or definition. A modified Delphi process was led by three large pan-national liver associations. The consensus was defined a priori as a supermajority (67%) vote. An independent committee of experts external to the nomenclature process made the final recommendation on the acronym and its diagnostic criteria. Full-Text PDF Open Access

Introduction:Women experience excess cardiovascular risk compared to men in the setting of similar metabolic disease burden. This consistent finding could be related to sex differences in the vascular response to various forms of metabolic stress. In this study we examine the association of both systemic and organ-specific metabolic stress with vascular health in women and men. Methods:We conducted an observational study of 4,299 adult participants (52% women, aged 59±13 years) of the National Health and Nutrition Examination Survey (NHANES) 2017-2018 cohort and 110,225 adult outpatients (55% women, aged 64±16 years) of the Cedars-Sinai Medical Center (CSMC) 2019 cohort. We used natural splines to examine the association of systemic and organ-specific measures of metabolic stress including body mass index (BMI), hemoglobin A1c (HbA1c), hepatic FIB-4 score, and CKD-EPI estimated glomerular filtration rate (eGFR) on systolic blood pressure (SBP). Piecewise linear models were generated using normal value thresholds (BMI <25 kg/m 2 , HbA1c <5.7%, FIB-4 <1.3, and eGFR ≥90 ml/min), which approximated observed spline breakpoints. The primary outcome was increase in SBP (relative to a sex-specific physiologic baseline SBP) in association with increase in level of each metabolic measure. Results:Women compared to men demonstrated larger magnitudes and an earlier onset of increase in SBP per increment increase across all metabolic stress measures. The slope of SBP increase per increment of each metabolic measure was greater for women than men particularly for metabolic measures within the normal range, with slope differences of 1.71 mmHg per kg/m2 of BMI, 9.61 mmHg per %HbA1c, 6.45 mmHg per FIB-4 unit, and 0.37 mmHg per ml/min decrement of eGFR in the NHANES cohort (P difference <0.05 for all). Overall results were consistent in the CSMC cohort. Conclusions:Women exhibited greater vascular sensitivity in the setting of multiple types of metabolic stress, particularly in periods representing the transition from metabolic health to disease. These findings underscore the importance of involving early metabolic health interventions as part of efforts to mitigate vascular risks in both women and men.

Blood pressure variability (BPV) and heart rate variability (HRV) have been associated with Alzheimer’s Disease and Related Dementias (ADRD) in rigorously controlled studies. However, the extent to which BPV and HRV may offer predictive information in real-world, routine clinical care is unclear. In a retrospective cohort study of 48,204 adults (age 54.9 ± 17.5 years, 60% female) receiving continuous care at a single center, we derived BPV and HRV from routinely collected clinical data. We use multivariable Cox models to evaluate the association of BPV and HRV, separately and in combination, with incident ADRD. Over a median 3 [2.4, 3.0] years, there were 443 cases of new-onset ADRD. We found that clinically derived measures of BPV, but not HRV, were consistently associated with incident ADRD. In combined analyses, only patients in both the highest quartile of BPV and lowest quartile of HRV had increased ADRD risk (HR 2.34, 95% CI 1.44–3.81). These results indicate that clinically derived BPV, rather than HRV, offers a consistent and readily available metric for ADRD risk assessment in a real-world patient care setting. Thus, implementation of BPV as a widely accessible tool could allow clinical providers to efficiently identify patients most likely to benefit from comprehensive ADRD screening.

Accurately predicting ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) properties early in drug development is essential for selecting compounds with optimal pharmacokinetics and minimal toxicity. Existing ADMET-related benchmark sets are limited in utility due to their small dataset sizes and the lack of representation of compounds used in drug discovery projects. These shortcomings hinder their application in model building for drug discovery. To address this issue, we propose a multi-agent data mining system based on Large Language Models that effectively identifies experimental conditions within 14,401 bioassays. This approach facilitates merging entries from different sources, culminating in the creation of PharmaBench. Additionally, we have developed a data processing workflow to integrate data from various sources, resulting in 156,618 raw entries. Through this workflow, we constructed PharmaBench, a comprehensive benchmark set for ADMET properties, which comprises eleven ADMET datasets and 52,482 entries. This benchmark set is designed to serve as an open-source dataset for the development of AI models relevant to drug discovery projects.

Background and objectivesRecognized as a potential risk factor for Alzheimer's disease and related dementias (ADRD), blood pressure variability (BPV) could be leveraged to facilitate identification of at-risk individuals at a population level. Granular BPV data are available during acute care hospitalization periods for potentially high-risk patients, but the incident ADRD risk association with BPV measured in this setting is unknown. Our objective was to evaluate the relation of BPV, measured during acute care hospitalization, and incidence of ADRD.MethodsWe retrospectively studied adults, without a prior ADRD diagnosis, who were admitted to a large quaternary care medical center in Southern California between January 1, 2013 and December 31, 2019. For all patients, determined BPV, calculated as variability independent of the mean (VIM), using blood pressure readings obtained as part of routine clinical care. We used multivariable Cox proportional hazards regression to examine the association between BP VIM during hospitalization and the development of incident dementia, determined by new ICD-9/10 coding or the new prescription of dementia medication, occurring at least 2 years after the index hospitalization.ResultsOf 81,892 adults hospitalized without a prior ADRD diagnosis, 2,442 (2.98%) went on to develop ADRD (2.6 to 5.2 years after hospitalization). In multivariable-adjusted Cox models, both systolic (HR 1.05, 95% CI 1.00–1.09) and diastolic (1.06, 1.02–1.10) VIM were associated with incident ADRD. In pre-specified stratified analyses, the VIM associations with incident ADRD were most pronounced in individuals over age 60 years and among those with renal disease or hypertension. Results were similar when repeated to include incident ADRD diagnoses made at least 1 or 3 years after index hospitalization.DiscussionWe found that measurements of BPV from acute care hospitalizations can be used to identify individuals at risk for developing a diagnosis of ADRD within approximately 5 years. Use of the readily accessible BPV measure may allow healthcare systems to risk stratify patients during periods of intense patient-provider interaction and, in turn, facilitate engagement in ADRD screening programs.

Herein, we review established clinical use cases for SARS-CoV-2 antibody measures, which include diagnosis of recent prior infection, isolating high titer convalescent plasma, diagnosing multisystem inflammatory syndrome in children (MIS-C), and booster dosing in the immunosuppressed and other populations. We then address whether an antibody correlate of protection (CoP) for SARS-CoV-2 has been successfully defined with the following considerations: Antibody responses in the immunocompetent, vaccine type, variants, use of binding antibody tests vs. neutralization tests, and endpoint measures. In the transition from the COVID-19 pandemic to endemic, there has been much interest in defining an antibody CoP. Due to the high mutability of respiratory viruses and our current knowledge of SARS-CoV-2 variants defining a CoP for prevention of infection is unrealistic. However, a CoP may be defined for prevention of severe disease requiring hospitalization and/or death. Most SARS-CoV-2 CoP research has focused on neutralization measurements. However, there can be significant differences in neutralization test methods, and disparate responses to new variants depending on format. Furthermore, neutralization assays are often impractical for high throughput applications (e.g., assessing humoral immune response in populations or large cohorts). Nevertheless, CoP studies using neutralization measures are reviewed to determine where there is consensus. Alternatively, binding antibody tests could be used to define a CoP. Binding antibody assays tend to be highly automatable, high throughput, and therefore practical for large population applications. Again, we review studies for consensus on binding antibody responses to vaccines, focusing on standardized results. Binding antibodies directed against the S1 receptor binding domain (S1-RBD) of the viral spike protein can provide a practical, indirect measure of neutralization. Initially, a response for S1-RBD antibodies may be selected that reflects the peak response in immunocompetent populations and may serve as a target for booster dosing in the immunocompromised. From existing studies reporting peak S1-RBD responses in standardized units, an approximate range of 1372–2744 BAU/mL for mRNA and recombinant protein vaccines was extracted that could serve as an initial CoP target. This target would need to be confirmed and potentially adjusted for updated vaccines, and almost certainly for other vaccine formats (i.e., viral vector). Alternatively, a threshold or response could be defined based on outcomes over time (i.e., prevention of severe disease). We also discuss the precedent for clinical measurement of antibodies for vaccine-preventable diseases (e.g., hepatitis B). Lastly, cellular immunity is briefly addressed for its importance in the nature and durability of protection.

An updated understanding of how immunity may wane or be sustained following SARS-CoV-2 vaccination is needed to guide efforts aimed at mitigating the ongoing risks from COVID. Prior studies found that greater magnitude and duration of antibody response after initial vaccination are associated with prior infection, female sex, and younger age. However, most of these earlier reports were limited to analyses conducted within a year of vaccine availability, among predominantly female healthcare workers, and without data on the effects of comorbidities [1–4].

BACKGROUND:Tixagevimab-cilgavimab (Tix-Cil) was authorized for prophylaxis against COVID-19 in immunocompromised patients from December 2021 through January 2023. Real-world effectiveness for solid organ transplant (SOT) recipients has been unclear. METHODS:We enrolled 911 SOT recipients into a longitudinal COVID-19 serology study, of whom 381 (42%) received ≥1 dose of Tix-Cil. We collected and analyzed data on incident SARS-CoV-2 infections and antibody kinetics for all patients from January 2022 to March 2023, including periods dominated by Omicron BA and BQ subvariants. RESULTS:Over 253 ± 131 days of follow-up, there were 324 new-onset SARS-CoV-2 infections: 117 (31%) in Tix-Cil treated and 207 (39%) in Tix-Cil untreated patients (p = .012). In analyses adjusting for demographic, clinical, and COVID-19 exposure factors, any Tix-Cil treatment was associated with lower infection risk (OR 0.52, 95% CI 0.27-0.96, p = .039) throughout the surveillance period including when more resistant BQ.1 and BQ.1.1 subvariants had emerged (12/1/2022 onwards). Among treated patients, receiving a Tix-Cil dose was associated with substantial and sustained increase in anti-spike IgG antibody and angiotensin-converting enzyme 2 binding inhibition levels (Abbott Architect assay) that together also demonstrated association with lower infection risk (p = .042). During the full surveillance period, the frequency of infections requiring hospitalization was low overall (N = 26, 2.9% of the total cohort) and not significantly different between Tix-Cil recipients (N = 12, 3.2% of treated patients) and non-Tix-Cil recipients (N = 14, 2.6% of untreated patients) with unadjusted p = .31 for between-group difference. CONCLUSION:In a large cohort of SOT recipients, we found that Tix-Cil reduced infection risk even amidst emergent Omicron subvariants. Additionally, the extent of measurable humoral response to Tix-Cil may indicate relative effectiveness. Pre-exposure monoclonal antibody therapy may represent a strategy that will continue to offer clinical benefit for immunocompromised persons who are known to derive limited protection from vaccinations.

Rapid and accurate prediction of molecular properties is a fundamental task in drug discovery. In recent years, deep learning-based molecular property prediction methods have received much attention and recent successes have shown that learning the representations of molecular structures by applying graph neural networks (GNNs) can achieve better prediction results. However, most previous approaches typically focus on learning atomic embedding, while in this paper, we propose a novel attention method based on atom pair embedding, and it was applied to two types of prediction task. Firstly, learning of atom pair embedding was done on 2D molecular graphs for predicting a series of ligand properties and secondly, the atom pair embedding was learned on ligand/protein 3D complex structures together with axial attention network to predict protein-ligand interaction. In MolecularNet benchmark datasets, our method achieved better performance than previous state-of-the-art models in ten property prediction tasks and in the task for protein-ligand interaction prediction, our method also obtained superior results on the PDB2016 dataset than a collection of reference models. Our source code will be publicly available upon the acceptance of the manuscript.

目的 在骨龄智能评估研究中,如何准确地提取手腕参照骨的兴趣区域(region of interest,ROI)是保证骨龄精确评估的关键.基于传统深度学习的方法用于手腕骨ROI提取,存在个别参照骨漏判、误判等情况,导致平均提取准确率较低.本文结合目标检测强大的定位和识别能力,以准确提取所有手腕骨ROI为目的,提出了一种参照骨自动匹配与修正方法.方法 针对不同参照骨形状、位置等特征表现出的规律性和关联性,本文采集了大量不同性别、不同年龄段的人手腕图谱作为参照骨样本匹配,然后分多个阶段提取参照骨ROI:1)基于目标检测算法初步提取出所有参照骨候选ROI,并根据一定的阈值剔除置信度较低的区域;2)结合参照骨的大数据样本构建位置点匹配模型,对剔除区域进行自动匹配与填补,保证ROI提取的完整性;3)通过多尺度滑动窗口以及ROI分类模型,对填补得到的ROI位置进行滑动修正,进一步保证提取准确率.结果 实验结果表明,本文结合目标检测与匹配修正的方法优于现有绝大多数方法.其中,匹配修正方法在目标检测算法的提取结果基础上,提升了约1.42％的平均准确率,当结合Faster R-CNN(region-convolutional neural network)算法时能达到最高98.45％的交并比(intersec-tion-over-union,IoU)准确率.结论 本文方法利用手腕骨的位置特征,对个别提取困难的参照骨类型进行重新匹配与修正,有效地弥补了传统方法泛化能力不足的缺点.本文方法能够同时面向人手腕中所有参照骨ROI提取,具备良好的扩展性和易操作性.

Judging the maturity level of each hand-wrist reference bone is the core issue in bone age assessment. Relying on the superiority of convolutional neural networks in feature representation, deep learning is widely studied for the automatic bone age assessment. However, an efficient but complex deep learning network requests a large dataset with bone-maturity-level labels for training, restricting its large-scale application in bone maturity classification. For this reason, we transform the bone-maturity-level classification problem into the similarity matching problem. Also, we propose a general structure based on Siamese network by merging two inputs into a two-channel input and introducing a dual attention mechanism, to create an Attentional Two-Channel Network (ATC-Net). This paper takes the intermediate phalanges III as an example to assess the performance of the similarity matching method and the ATC-Net. Experiments show that our method can perform better on small datasets, which effectively makes up for the data shortage problem. The ATC-Net used for classification significantly reduces the evaluation time compared with other classical networks. It reduces the time of assessing one sample by about 49% as compared to VGG-16. And more importantly, it achieves the highest classification accuracy of 92.74% among all investigated networks.

The rapid spread of coronavirus 2019 disease (COVID-19) has manifested a global public health crisis, and chest CT has been proven to be a powerful tool for screening, triage, evaluation and prognosis in COVID-19 patients. However, CT is not only costly but also associated with an increased incidence of cancer, in particular for children. This study will question whether clinical symptoms and laboratory results can predict the CT outcomes for the pediatric patients with positive RT-PCR testing results in order to determine the necessity of CT for such a vulnerable group. Clinical data were collected from 244 consecutive pediatric patients (16 years of age and under) treated at Wuhan Children's Hospital with positive RT-PCR testing, and the chest CT were performed within 3 days of clinical data collection, from January 21 to March 8, 2020. This study was approved by the local ethics committee of Wuhan Children's Hospital. Advanced decision tree based machine learning models were developed for the prediction of CT outcomes. Results have shown that age, lymphocyte, neutrophils, ferritin and C-reactive protein are the most related clinical indicators for predicting CT outcomes for pediatric patients with positive RT-PCR testing. Our decision support system has managed to achieve an AUC of 0.84 with 0.82 accuracy and 0.84 sensitivity for predicting CT outcomes. Our model can effectively predict CT outcomes, and our findings have indicated that the use of CT should be reconsidered for pediatric patients, as it may not be indispensable.

The world is currently experiencing an ongoing pandemic of an infectious disease named coronavirus disease 2019 (i.e., COVID-19), which is caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Computed Tomography (CT) plays an important role in assessing the severity of the infection and can also be used to identify those symptomatic and asymptomatic COVID-19 carriers. With a surge of the cumulative number of COVID-19 patients, radiologists are increasingly stressed to examine the CT scans manually. Therefore, an automated 3D CT scan recognition tool is highly in demand since the manual analysis is time-consuming for radiologists and their fatigue can cause possible misjudgment. However, due to various technical specifications of CT scanners located in different hospitals, the appearance of CT images can be significantly different leading to the failure of many automated image recognition approaches. The multi-domain shift problem for the multi-center and multi-scanner studies is therefore nontrivial that is also crucial for a dependable recognition and critical for reproducible and objective diagnosis and prognosis. In this paper, we proposed a COVID-19 CT scan recognition model namely coronavirus information fusion and diagnosis network (CIFD-Net) that can efficiently handle the multi-domain shift problem via a new robust weakly supervised learning paradigm. Our model can resolve the problem of different appearance in CT scan images reliably and efficiently while attaining higher accuracy compared to other state-of-the-art methods.

An outbreak of a novel coronavirus disease (i.e., COVID-19) has been recorded in Wuhan, China since late December 2019, which subsequently became pandemic around the world. Although COVID-19 is an acutely treated disease, it can also be fatal with a risk of fatality of 4.03% in China and the highest of 13.04% in Algeria and 12.67% Italy (as of 8th April 2020). The onset of serious illness may result in death as a consequence of substantial alveolar damage and progressive respiratory failure. Although laboratory testing, e.g., using reverse transcription polymerase chain reaction (RT-PCR), is the golden standard for clinical diagnosis, the tests may produce false negatives. Moreover, under the pandemic situation, shortage of RT-PCR testing resources may also delay the following clinical decision and treatment. Under such circumstances, chest CT imaging has become a valuable tool for both diagnosis and prognosis of COVID-19 patients. In this study, we propose a weakly supervised deep learning strategy for detecting and classifying COVID-19 infection from CT images. The proposed method can minimise the requirements of manual labelling of CT images but still be able to obtain accurate infection detection and distinguish COVID-19 from non-COVID-19 cases. Based on the promising results obtained qualitatively and quantitatively, we can envisage a wide deployment of our developed technique in large-scale clinical studies.

Background and Objective: Ventricle volume is closely related to hydrocephalus, brain atrophy, Alzheimer's, Parkinson's syndrome, and other diseases. To accurately measure the volume of the ventricles for elderly patients, we use deep learning to establish a systematic and comprehensive automated ventricle segmentation framework. Methods: The study participation included 20 normal elderly people, 20 patients with cerebral atrophy, 64 patients with normal pressure hydrocephalus, and 51 patients with acquired hydrocephalus. Second, get their imaging data through the picture archiving and communication systems (PACS) system. Then use ITK software to manually label participants' ventricular structures. Finally, extract imaging features through machine learning. Results: This automated ventricle segmentation method can be applied not only to CT and MRI images but also to images with different scan slice thicknesses. More importantly, it produces excellent segmentation results (Dice > 0.9). Conclusion: This automated ventricle segmentation method has wide applicability and clinical practicability. It can help clinicians find early disease, diagnose disease, understand the patient's disease progression, and evaluate the patient's treatment effect.

Due to the influence of the irregular shapes and the adjacent positions of the wrist reference bones, it is difficult for the expert to accurately estimate the mature indication of the wrist reference bones of the minor. How to precisely segment the reference bones of the minor is a challenge. For this problem, the ARU-Net for wrist reference bone segmentation is proposed. First, we extract the reference bone ROI by Faster R-CNN. Then, the pre-processed ROI is fed into ARU-Net for segmentation. On the basis of traditional U-Net, ARU-Net adds residual mapping and attention mechanism, which improves the utilization rate of features and the accuracy of reference bone segmentation. Finally, a post-processing method including the flood fill algorithm and the morphological operation is used to eliminate jagged edges and holes in the segmented result. The hamate is one of the most difficult reference bones to segment in the wrist. This paper takes it as an example to assess the performance of ARU-Net. Experiments show that compared with FCN, U-Net and ResUnet, the accuracy and F1 scores of ARU-Net are higher. The accuracy rate is 96.4%, and the F1 score is 0.953. The post-processing method can further improve the result. Finally, the accuracy rate reaches 96.5%, and the F1 score reaches 0.954. In order to verify the segmentation stability of ARU-Net, it is also applied to the segmentation of the radius and the capitate. RU-Net can precisely segment the reference bone, which facilitates the expert to assess its mature indication, so as to accurately evaluate the bone age.