Artificial intelligence-driven radiomics study in cancer:the role of feature engineering and modeling

Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians.Moreover,some potentially useful quantitative information in medical images,especially that which is not visible to the naked eye,is often ignored during clinical practice.In contrast,radiomics performs high-throughput feature extraction from medical images,which enables quantitative analysis of medical images and prediction of various clinical endpoints.Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis,demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine.However,radiomics remains in a developmental phase as numerous technical challenges have yet to be solved,especially in feature engineering and statistical modeling.In this review,we introduce the current utility of radiomics by summarizing research on its application in the diagnosis,prognosis,and prediction of treatment responses in patients with cancer.We focus on machine learning approaches,for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling.Furthermore,we introduce the stability,reproducibility,and interpretability of features,and the generalizability and interpretability of models.Finally,we offer possible solutions to current challenges in radiomics research.

Wetting front migration model of ion-adsorption rare earth during the multi-hole unsaturated liquid injection

In the process of ion-adsorption rare earth ore leaching,the migration characteristics of the wetting front in multi-hole injection holes and the influence of wetting front intersection effect on the migration distance of wetting fronts are still unclear.Besides,wetting front migration distance and leaching time are usually required to optimize the leaching process.In this study,wetting front migration tests of ionadsorption rare earth ores during the multi-hole fluid injection(the spacing between injection holes was 10 cm,12 cm and 14 cm)and single-hole fluid injection were completed under the constant water head height.At the pre-intersection stage,the wetting front migration laws of ion-adsorption rare earth ores during the multi-hole fluid injection and single-hole fluid injection were identical.At the postintersection stage,the intersection accelerated the wetting front migration.By using the Darcy’s law,the intersection effect of wetting fronts during the multi-hole liquid injection was transformed into the water head height directly above the intersection.Finally,based on the Green-Ampt model,a wetting front migration model of ion-adsorption rare earth ores during the multi-hole unsaturated liquid injection was established.Error analysis results showed that the proposed model can accurately simulate the infiltration process under experimental conditions.The research results enrich the infiltration law and theory of ion-adsorption rare earth ores during the multi-hole liquid injection,and this study provides a scientific basis for optimizing the liquid injection well pattern parameters of ion-adsorption rare earth in situ leaching in the future.

Facet effects on bimetallic ZnSn hydroxide microcrystals for selective electrochemical CO_(2)reduction

Employing crystal facets to regulate the catalytic properties in electrocatalytic carbon dioxide reduction reaction(eCO_(2)RR)has been well demonstrated on electrocatalysts containing single metals but rarely explored for bimetallic systems.Here,we synthesize ZnSn(OH)_(6)(ZSO)microcrystals(MCs)with distinct facets and investigate the facet effects in eCO_(2)RR.Electrochemical studies and in situ Fourier Transform Infrared Spectroscopy(in situ-FTIR)reveal that ZSO MCs produce mainly C1 products of HCOOH and CO.The{111}facet of the ZSO MCS exhibits higher selectivity and faradaic efficiency(FE)than that of the{100}facet over a wide range of potentials(-0.9 V∼-1.3 V versus RHE).Density Functional Theory(DFT)calculations elucidate that the{111}facet is favorable to the adsorption/activation of CO_(2)molecules,the formation of intermediate in the rate-determining step,and the desorption of C1 products of CO and HCOOH molecules.

A Localization Method of High Energy Transients for All-sky Gamma-ray Monitor

Fast and reliable localization of high-energy transients is crucial for characterizing the burst properties and guiding the follow-up observations.Localization based on the relative counts of different detectors has been widely used for all-sky gamma-ray monitors.There are two major methods for this count distribution localization:χ^(2)minimization method and the Bayesian method.Here we propose a modified Bayesian method that could take advantage of both the accuracy of the Bayesian method and the simplicity of the χ^(2)method.With comprehensive simulations,we find that our Bayesian method with Poisson likelihood is generally more applicable for various bursts than the χ^(2)method,especially for weak bursts.We further proposed a location-spectrum iteration approach based on the Bayesian inference,which could alleviate the problems caused by the spectral difference between the burst and location templates.Our method is very suitable for scenarios with limited computation resources or timesensitive applications,such as in-flight localization software,and low-latency localization for rapidly follow-up observations.

The In-Flight Realtime Trigger and Localization Software of GECAM

Realtime trigger and localization of bursts are the key functions of GECAM,an all-sky gamma-ray monitor launched on 2020 December 10.We developed a multifunctional trigger and localization software operating in the CPU of the GECAM Electronic Box.This onboard software has the following features:high trigger efficiency for real celestial bursts with a suppression of false triggers caused by charged particle bursts and background fluctuation,dedicated localization algorithm optimized for both short and long bursts,and low time latency of the trigger information which is downlinked through the Global Short Message Communication service of the global BeiDou navigation system.This paper provides a detailed description of the design and development of the trigger and localization software system for GECAM.It covers the general design,workflow,the main functions,and the algorithms used in the system.The paper also includes on-ground trigger tests using simulated gamma-ray bursts generated by a dedicated X-ray tube,as well as an overview of the performance for real celestial bursts during its in-orbit operation.

Optimization of Channel Structure of Alkaline Water Electrolyzer by Using an Expanded Mesh as a Bipolar Plate

Alkaline water electrolysis(AWE)is the most mature technology for hydrogen production by water electrolysis.Alkaline water electrolyzer consists of multiple electrolysis cells,and a single cell consists of a diaphragm,electrodes,bipolar plates and end plates,etc.The existing industrial bipolar plate channel is concave-convex structure,which is manufactured by complicated and high-cost mold punching.This structure still results in uneven electrolyte flow and low current density in the electrolytic cell,further increasing in energy consumption and cost of AWE.Thereby,in this article,the electrochemical and flow model is firstly constructed,based on the existing industrial concave and convex flow channel structure of bipolar plate,to study the current density,electrolyte flow and bubble distribution in the electrolysis cell.The reliability of the model was verified by comparison with experimental data in literature.Among which,the electrochemical current density affects the bubble yield,on the other hand,the generated bubbles cover the electrode surface,affecting the active specific surface area and ohmic resistance,which in turn affects the electrochemical reaction.The result indicates that the flow velocity near the bottom of the concave ball approaches zero,while the flow velocity on the convex ball surface is significantly higher.Additionally,vortices are observed within the flow channel structure,leading to an uneven distribution of electrolyte.Next,modelling is used to optimize the bipolar plate structure of AWE by simulating the electrochemistry and fluid flow performances of four kinds of structures,namely,concave and convex,rhombus,wedge and expanded mesh,in the bipolar plate of alkaline water electrolyzer.The results show that the expanded mesh channel structure has the largest current density of 3330 A/m^(2)and electrolyte flow velocity of 0.507 m/s in the electrolytic cell.Under the same current density,the electrolytic cell with the expanded mesh runner structure has the smallest potential and energy consumption.This work provides a useful guide for the comprehensive understanding and optimization of channel structures,and a theoretical basis for the design of large-scale electrolyzer.

Relationship between glycemic variability and cognitive function in lacune patients with type 2 diabetes

BACKGROUND Lacunes are the manifestations of lacunar infarction which can lead many patients to the clinical outcome of disability or dementia.However,the relationship between lacune burden,cognitive function and blood glucose fluctuation in patients with type 2 diabetes mellitus(T2DM)complicated with lacunes is not very clear.AIM To explore the correlation between glucose variability,lacune burden and cognitive function in patients with lacunes complicated with T2DM.METHODS The clinical and imaging data of 144 patients with lacunes combined with T2DM were reviewed retrospectively.72 h continuous glucose monitoring was performed.The Montreal Cognitive Assessment was used to assess cognitive function.The burden of lacunes was evaluated using magnetic resonance imaging performance.Multifactorial logistic regression analysis was used to study the affecting the lacune load and cognitive impairment in patients.To predict the value of patients’cognitive impairment with lacunes complicated with T2DM,a receiver operating characteristic(ROC)curve and a nomogram prediction model were constructed.RESULTS The standard deviation(SD)of the average blood glucose concentration,percentage coefficient of variation(%CV)and time of range(TIR)were significantly different between the low and the high load groups(P<0.05).The SD,%CV and TIR of the cognitive impairment group and non-cognitive impairment group were significantly different(P<0.05).SD(odds ratio(OR):3.558,95%confidence interval(CI):1.268-9.978,P=0.006),and%CV(OR:1.192,95%CI:1.081-1.315,P<0.05)were the risk factors for an increased infarct burden in lacunes patients complicated with T2DM.TIR(OR:0.874,95%CI:0.833-0.928,P<0.05)is a protective factor.In addition,an increased SD(OR:2.506,95%CI:1.008-6.23,P=0.003),%CV(OR:1.163,95%CI:1.065-1.270,P<0.05)were the risk factors for cognitive impairment in patients with lacunes complicated with T2DM,TIR(OR:0.957,95%CI:0.922-0.994,P<0.05)is a protective factor.A nomogram prediction model of the risk of cognitive impairment was established based on SD,%CV and TIR.Decision curve analysis and the internal calibration analysis were used for internal verification and showed that the model was clinical benefit.The area under the ROC curves for predicting cognitive impairment in patients with lacunes complicated with T2DM was drawn were%CV:0.757(95%CI:0.669-0.845,P<0.05),TIR:0.711(95%CI:0.623-0.799,P<0.05).CONCLUSION Blood glucose variability is closely associated with the level of lacune burden and cognitive dysfunction in lacune patients combined with T2DM.%CV,TIR have a certain predictive effect in cognitive impairment in lacune patients.

The efficacy of full-thickness endoscopic resection of subepithelial tumors in the gastric cardia

BACKGROUND Gastric subepithelial tumors(SETs)may harbor potential malignancy.Although it is well recognized that large SETs should be resected,the precise treatment strategy remains controversial.Compared to surgical resection,endoscopic resection(ER)has many advantages;however,ER of SETs in the cardia is challenging.AIM To evaluate the safety and efficacy of endoscopic full-thickness resection(EFTR)for the treatment of gastric cardia SETs.METHODS We retrospectively reviewed data from all patients with SETs originating from the muscularis propria layer in the gastric cardia that were treated by EFTR or submucosal tunneling ER(STER)at Zhongshan Hospital Fudan University between November 2014 and May 2022.Baseline characteristics and clinical outcomes,including procedure times and complications rates,were compared between groups of patients receiving EFTR and STER.RESULTS A total of 171 tumors were successfully removed[71(41.5%)tumors in the EFTR and 100(58.5%)tumors in the STER group].Gastrointestinal stromal tumors(GISTs)were the most common SET.The en bloc resection rate was 100%in the EFTR group vs 97.0%in STER group(P>0.05).Overall,the EFTR group had a higher complete resection rate than the STER group(98.6%vs 91.0%,P<0.05).The procedure time was also shorter in the EFTR group(44.63±28.66 min vs 53.36±27.34,P<0.05).The most common major complication in both groups was electrocoagulation syndrome.There was no significant difference in total complications between the two groups(21.1%vs 22.0%,P=0.89).CONCLUSION EFTR of gastric cardia SETs is a very promising method to facilitate complete resection with similar complications and reduced operative times compared to STER.In cases of suspected GISTs or an unclear diagnosis,EFTR should be recommended to ensure complete resection.

合作问题解决视角下《义务教育信息科技课程标准》的研究

信息科技课程中,学科核心素养的培养与合作问题解决能力的培养互相支持、互相渗透。《义务教育信息科技课程标准(2022年版)》以育人目标为导向进行知识选择和内容组织,对课程建设与教学实施具有指导性作用。以课程标准为研究对象,探究合作问题解决能力在课程标准中的呈现情况和渗透力度,将有助于在信息科技课程中更好地落实合作问题解决能力的培养。基于PISA2015合作问题解决能力测评框架,构建合作问题解决视角下课程标准的评价指标体系,将合作问题解决能力的呈现分成6种情况,采用内容分析法,定量刻画、定性诠释课程标准中合作问题解决能力的呈现水平、方式及其效果。通过分析发现:课程标准有意渗透合作问题解决能力,其中合作问题解决能力以显性呈现为主,整体呈现水平处于中上,并在“课程内容”“课程目标”“附录”中的呈现效果较好;课程标准中合作问题解决能力的呈现具有适切性,符合课程内容特点和学习者认知水平;课程标准对合作问题解决能力的渗透虽较有成效,但并不彻底,仍有完善空间。据此,为保证学生能够有效发展合作问题解决能力,提出相关建议:进一步提高课程标准中合作问题解决能力的呈现效果;强化合作问题解决能力在高中课程标准中计算思维部分的呈现;强化过程性评价,提高合作问题解决能力测评的有效性;从课程资源出发,进一步优化合作问题解决能力的培养;教师从合作问题解决能力的视角解读课程标准;紧扣信息科技学科的本质开展合作问题解决活动。

Simultaneous Determination of Five Components in Operculina turpethum

[Objectives]This study was conducted to establish a method for the simultaneous determination of caffeic acid, rutin, ononin, luteolin, and apigenin in Operculina turpethum(L.) S. Manso. [Methods]With ononin from O. turpethum as the internal reference, the five components were separated by HPLC, and the contents of various components were calculated according to the relative correction factors of ononin with caffeic acid, rutin, luteolin, and apigenin. Meanwhile, the calculated results of quantitative analysis of multi-components by single marker(QAMS) were compared with the determined values of the external standard method. [Results] The linear relationship of the five components in their respective ranges was good(r=0.999 9). The average recovery was in the range of 97.48%-101.05%, and the RSD values were in the range of 1.04%-2.71%. The results obtained by QAMS were close to those obtained by the external standard method. [Conclusions] The method is accurate, stable and adaptable, and can be used for the determination of five flavonoids in O. turpethum.

Effects of Long-Term Fertilization on Different Nitrogen Forms in Paddy along Soil Depth Gradient

The combined application of organic fertilizer and chemical fertilizer is an effective measure to increase nutrient content of soil plough layer, which must have a profound impact on the deep soil nutrients, especially the contents of nitrogen forms. The purpose of this study was to explore the characteristics of soil nitrogen forms in plough layer and along depth gradient in different fertilization treatments, so as to evaluate the soil quality in spatial dimension, further providing a theoretical basis for scientific fertilization and improvement of paddy soil fertility. Here, a 34-year field experiment was conducted with three treatments: without any fertilizer (CK), pure chemical fertilizer (NPK) and chemical fertilizer combined with organic fertilizer (NPKM). We analyzed the content of nitrogen forms in 0 - 100 cm soil depth and their ratios to total nitrogen (TN), and discussed the correlation between nitrogen forms contents and pH, CEC. Results showed that, compared with CK, both NPK and NPKM significantly increased the contents of nitrogen forms in topsoil (soil layer of 0 - 20 cm), especially nitrate nitrogen (NO3--N) content increased by 70% (NPK) and 111% (NPKM), respectively. Although the contents of different nitrogen forms decreased gradually along soil depth gradient, NPKS slowed down the decline rate of TN and alkali-hydrolysable nitrogen (AN) in 0 - 60 cm soil layer, compared to CK. Compared to NPK, NPKM significantly increased the NO3--N/TN ratio in 0 - 20 cm soil layer, but also decreased the content of -N in 20 - 40 cm, which was beneficial to reduce the risk of nitrogen leaching caused by nitrate leaching into deep layer. The increase of soil pH in NPKM treatment obviously alleviated the problem of soil acidification caused by long-term application of chemical fertilizer. Correlation analysis showed that there was a significant positive correlation between soil nitrogen forms and cation exchange capacity (CEC), but no significant correlation with soil pH. In conclusion, NPKM ensured the nutrients of soil plough layer (0 - 20 cm), also reduced the risk of nitrogen infiltration and nitrogen loss, thus ensuring the fertility of soil profile.

Preoperative prediction of perineural invasion of rectal cancer based on a magnetic resonance imaging radiomics model:A dual-center study

BACKGROUND Perineural invasion(PNI)has been used as an important pathological indicator and independent prognostic factor for patients with rectal cancer(RC).Preoperative prediction of PNI status is helpful for individualized treatment of RC.Recently,several radiomics studies have been used to predict the PNI status in RC,demonstrating a good predictive effect,but the results lacked generalizability.The preoperative prediction of PNI status is still challenging and needs further study.AIM To establish and validate an optimal radiomics model for predicting PNI status preoperatively in RC patients.METHODS This retrospective study enrolled 244 postoperative patients with pathologically confirmed RC from two independent centers.The patients underwent preoperative high-resolution magnetic resonance imaging(MRI)between May 2019 and August 2022.Quantitative radiomics features were extracted and selected from oblique axial T2-weighted imaging(T2WI)and contrast-enhanced T1WI(T1CE)sequences.The radiomics signatures were constructed using logistic regression analysis and the predictive potential of various sequences was compared(T2WI,T1CE and T2WI+T1CE fusion sequences).A clinical-radiomics(CR)model was established by combining the radiomics features and clinical risk factors.The internal and external validation groups were used to validate the proposed models.The area under the receiver operating characteristic curve(AUC),DeLong test,net reclassification improvement(NRI),integrated discrimination improvement(IDI),calibration curve,and decision curve analysis(DCA)were used to evaluate the model performance.RESULTS Among the radiomics models,the T2WI+T1CE fusion sequences model showed the best predictive performance,in the training and internal validation groups,the AUCs of the fusion sequence model were 0.839[95%confidence interval(CI):0.757-0.921]and 0.787(95%CI:0.650-0.923),which were higher than those of the T2WI and T1CE sequence models.The CR model constructed by combining clinical risk factors had the best predictive performance.In the training and internal and external validation groups,the AUCs of the CR model were 0.889(95%CI:0.824-0.954),0.889(95%CI:0.803-0.976)and 0.894(95%CI:0.814-0.974).Delong test,NRI,and IDI showed that the CR model had significant differences from other models(P<0.05).Calibration curves demonstrated good agreement,and DCA revealed significant benefits of the CR model.CONCLUSION The CR model based on preoperative MRI radiomics features and clinical risk factors can preoperatively predict the PNI status of RC noninvasively,which facilitates individualized treatment of RC patients.

Asymmetric Zn-N_4 atomic sites embedded hollow fibers as stable Zn anode for high-performance Zn-ion hybrid capacitor

Zn based electrochemical energy storage systems(EES)have attracted tremendous interests owing to their low cost and high intrinsic safety.Nevertheless,the uncontrolled growth of Zn dendrites and the side reactions of Zn metal anodes(ZMAs)severely restrict their applications.To address these issues,we design the asymmetric Zn-N_(4) atomic sites embedded hollow fibers(AS-IHF)as the flexible host for stable ZMAs.Through introducing different nitrogen resources in the synthesis,two kinds of coordination,i,e.Zn-N(pyridinic)and Zn-N(pyrrolic),are introduced in the Zn-N_(4) atomic module synchronously.The asymmetric Zn-N_(4) module with regulated micro-environment facilitates the superior zincophilic features and promotes the Zn adsorption.Meanwhile,the highly porous structure of the hollow fiber effectively reduces local current density,homogenize Zn ion flux,and alleviate structure stress.All the advantages endow the high efficiency and good stability for Zn plating/stripping.Both theoretical and experimental results demonstrate the high reversibility,low nucleation overpotential,and dendritefree behavior of the AS-IHF@Zn anode,which afford the high stability in high-rate and long-term cycling.Moreover,the solid-state Zn-ion hybrid capacitor(ZIHC)based on AS-IHF@Zn anode shows the high flexibility,reliability,and superior long-term cycling capability in a wide-range of temperatures(-20-25℃).Therefore,the present work not only gives a new strategy for modulating local environments of single atomic sites,but also propels the development of flexible power sources for diverse electronics.

Progress on immuno-microenvironment and immune-related therapies in patients with pseudomyxoma peritonei

Pseudomyxoma peritonei(PMP) is an indolent malignant syndrome. The standard treatment for PMP is cytoreductive surgery combined with intraperitoneal hyperthermic chemotherapy(CRS + HIPEC). However, the high recurrence rate and latent clinical symptoms and signs are major obstacles to further improving clinical outcomes. Moreover, patients in advanced stages receive little benefit from CRS + HIPEC due to widespread intraperitoneal metastases. Another challenge in PMP treatment involves the progressive sclerosis of PMP cell-secreted mucus, which is often increased due to activating mutations in the gene coding for guanine nucleotide-binding protein alpha subunit(GNAS). Consequently, the development of other PMP therapies is urgently needed. Several immune-related therapies have shown promise, including the use of bacterium-derived non-specific immunogenic agents, radioimmunotherapeutic agents, and tumor cell-derived neoantigens, but a well-recognized immunotherapy has not been established. In this review the roles of GNAS mutations in the promotion of mucin secretion and disease development are discussed. In addition, the immunologic features of the PMP microenvironment and immune-associated treatments are discussed to summarize the current understanding of key features of the disease and to facilitate the development of immunotherapies.

Minimally invasive reconstruction of extensive mid-lower ureteral strictures using a bilateral Boari flap

Objective:To describe and evaluate the technique using bilateral Boari flap ureteroneocystostomy(BBFUNC)for bilateral mid-lower ureteral strictures.Methods:We retrospectively reviewed five patients who underwent minimally invasive BBFUNC in our institution(Union Hospital,Wuhan,China)between July 2019 and December 2021.The bilateral ureters were mobilized and transected above the stenotic segments.The bladder was isolated and incised longitudinally from the middle of the anterior wall.Then,an inverted U-shaped bladder flap was created on both sides,fixed onto the psoas tendon,and anastomosed to the ipsilateral distal normal ureter.Following double-J stenting,the Boari flaps were tubularized,and the bladder was closed with continuous sutures.The patients’perioperative data and follow-up outcomes were collected,and a descriptive statistical analysis was performed.Results:No case converted to open surgery,and no intraoperative complication occurred.The median surgical time was 230(range 203-294)min.The median length of the bladder flaps was 6.2(range 4.3-10.0)cm on the left and 5.5(range 4.7-10.5)cm on the right side.All patients had not developed recurrent ureteral stenosis during the median follow-up time of 17(range 16-45)months and had a normal maximum flow rate after surgery.The median post-void residual was 7(range 0-19)mL.The maximal bladder capacity was decreased in one(20%)patient.Conclusion:The present study demonstrates that minimally invasive BBFUNC is feasible and safe in treating is limited.

Two Stages Segmentation Algorithm of Breast Tumor in DCE-MRI Based on Multi-Scale Feature and Boundary Attention Mechanism

Nuclearmagnetic resonance imaging of breasts often presents complex backgrounds.Breast tumors exhibit varying sizes,uneven intensity,and indistinct boundaries.These characteristics can lead to challenges such as low accuracy and incorrect segmentation during tumor segmentation.Thus,we propose a two-stage breast tumor segmentation method leveraging multi-scale features and boundary attention mechanisms.Initially,the breast region of interest is extracted to isolate the breast area from surrounding tissues and organs.Subsequently,we devise a fusion network incorporatingmulti-scale features and boundary attentionmechanisms for breast tumor segmentation.We incorporate multi-scale parallel dilated convolution modules into the network,enhancing its capability to segment tumors of various sizes through multi-scale convolution and novel fusion techniques.Additionally,attention and boundary detection modules are included to augment the network’s capacity to locate tumors by capturing nonlocal dependencies in both spatial and channel domains.Furthermore,a hybrid loss function with boundary weight is employed to address sample class imbalance issues and enhance the network’s boundary maintenance capability through additional loss.Themethod was evaluated using breast data from 207 patients at RuijinHospital,resulting in a 6.64%increase in Dice similarity coefficient compared to the benchmarkU-Net.Experimental results demonstrate the superiority of the method over other segmentation techniques,with fewer model parameters.

Transfer force perception skills to robot‐assisted laminectomy via imitation learning from human demonstrations

A comparative study of two force perception skill learning approaches for robot‐assisted spinal surgery,the impedance model method and the imitation learning(IL)method,is presented.The impedance model method develops separate models for the surgeon and patient,incorporating spring‐damper and bone‐grinding models.Expert surgeons'feature parameters are collected and mapped using support vector regression and image navi-gation techniques.The imitation learning approach utilises long short‐term memory networks(LSTM)and addresses accurate data labelling challenges with custom models.Experimental results demonstrate skill recognition rates of 63.61%-74.62%for the impedance model approach,relying on manual feature extraction.Conversely,the imitation learning approach achieves a force perception recognition rate of 91.06%,outperforming the impedance model on curved bone surfaces.The findings demonstrate the potential of imitation learning to enhance skill acquisition in robot‐assisted spinal surgery by eliminating the laborious process of manual feature extraction.

The Design of GECAM Scientific Ground Segment

The Gravitational wave burst high-energy Electromagnetic Counterpart All-sky Monitor(GECAM)is a dedicated mission for monitoring high-energy transients.Here we report the design of the GECAM Scientific Ground Segment(GSGS)in terms of the scientific requirements,including the architecture,the external interfaces,the main function,and workflow.Judging from the analysis and verification results during the commissioning phase,the GSGS functions well and is able to monitor the status of the payloads,adjust the parameters,develop the scientific observation plans,generate the scientific data products,analyze the data,etc.Thus,the on-orbit operation and scientific researches of GECAM are guaranteed.

DeepGCN based on variable multi‐graph and multimodal data for ASD diagnosis

Diagnosing individuals with autism spectrum disorder(ASD)accurately faces great chal-lenges in clinical practice,primarily due to the data's high heterogeneity and limited sample size.To tackle this issue,the authors constructed a deep graph convolutional network(GCN)based on variable multi‐graph and multimodal data(VMM‐DGCN)for ASD diagnosis.Firstly,the functional connectivity matrix was constructed to extract primary features.Then,the authors constructed a variable multi‐graph construction strategy to capture the multi‐scale feature representations of each subject by utilising convolutional filters with varying kernel sizes.Furthermore,the authors brought the non‐imaging in-formation into the feature representation at each scale and constructed multiple population graphs based on multimodal data by fully considering the correlation between subjects.After extracting the deeper features of population graphs using the deep GCN(DeepGCN),the authors fused the node features of multiple subgraphs to perform node classification tasks for typical control and ASD patients.The proposed algorithm was evaluated on the Autism Brain Imaging Data Exchange I(ABIDE I)dataset,achieving an accuracy of 91.62%and an area under the curve value of 95.74%.These results demon-strated its outstanding performance compared to other ASD diagnostic algorithms.

基于OBE理念的大学生创新实践能力的培养——以合肥工业大学应用化学专业为例

基于成果导向教育(OBE)理念,遵循成果导向教育思路,围绕学生创新实践能力的培养,制定特色鲜明的合肥工业大学应用化学专业人才培养方案,即加强“双师型”师资队伍、搭建创新实践能力的培养与专业教育相结合的“科教、赛教、企教”创新实践平台、建立强化过程考核为导向的教学评价模式。应用化学专业的实践探索对培养具有创新意识和实践能力的复合型人才具有很好的参考价值。