[Objective] This study aimed to analyze the temporal-spatial variation of Inner Mongolian grassland degradation during past three decades. [Method] The dis- tribution characteristics of grassland were described by lan...[Objective] This study aimed to analyze the temporal-spatial variation of Inner Mongolian grassland degradation during past three decades. [Method] The dis- tribution characteristics of grassland were described by land use types supervised classification with TM/ETM. Then, temporal-spatial changes of grassland coverage were quantified by the mean of maximum vegetation coverage in last 30 years. Lastly, the grassland degradation reasons were explored through statistic analysis between the grassland coverage and precipitation, temperature and grazing intensity. [Result] The grassland degradation index of Inner Mongolia was increased from 1.38 to 1.68, and the smallest was 1.28 in 2005s. Grassland degradation and improve- ment were concurrent after 1980s, but grassland degradation was the major change trend for Inner Mongolia grassland. The area of grassland degradation was enlarged from 18.08×10^4 km2 in 1980s to 22.47×10^4 km2 in 2010s on the whole and distribu- tion range was shifted from central-eastern to west in Inner Mongolia that mainly distributed on Hulun Buir and Xilin Gol grassland in 1980s and Ordos and Alax grassland in 2010s. The grassland area of degradation had a rising trend form 1980s to 1995s, then reduced to 10.8x104 km2 in 2005s, and decreased in 2010s, which mainly speared in the west of Xilin Gol grassland. [Conclusion] Inner Mongo-lian grassland degradation were become more seriously in last 30 years because that temperature, precipitation and graze intensities change, which not performance on decreasing coverage but grassland areas.展开更多
[ Objective] The research aimed to study temporal-spatial change characteristics of the extremely low temperature climate event in winter of China. [MethodI By using actual probability distribution threshold value met...[ Objective] The research aimed to study temporal-spatial change characteristics of the extremely low temperature climate event in winter of China. [MethodI By using actual probability distribution threshold value method, EOF analysis method and the daily minimum temperature data in winter of 1961 -2008 at 195 observatories of China, temporal-spatial change characteristics of the extremely low temperature climate event in win- ter of China in 48 years were analyzed. [ Result] Threshold value calculated by actual probability distribution was higher than that by traditional method, and increase magnitude in east was bigger than that in west, which could describe climatic change situation in China in 48 years better than traditional method. Cold night number in winter of China did not decrease as latitude declined, and it was more in south and north and was less in Yellow River basin and northwest China. Cold night number was the most in northeast Inner Mongolia. Interannual change of the cold night number presented decline tendency. From the 1960s to the eady 1970s, cold night number consistently increased, and change in middle and late periods of the 1960s was severe. From the early 1970s to the middle 1980s, fluctuation of the cold night number was bigger, and increase of the cold night number was the most in 1976. Cold night number from 1986 to the 21= century continuously declined. Change of the cold night number was the most obvious in east region, Guizhou and north Guangxi. Cold night number in northeast China and north Inner Mongolia presented inverting change relationship with that in Yunnan - Kweichow Plateau and Hexi Corridor. [ Conclusion] The research provided reference for eady warning of the extremely low temoerature event in China.展开更多
By using the variation coefficient,Gini coefficient and Theil coefficient,this paper makes preliminary exploration of temporalspatial change features and driving mechanism for regional differences of domestic tourism ...By using the variation coefficient,Gini coefficient and Theil coefficient,this paper makes preliminary exploration of temporalspatial change features and driving mechanism for regional differences of domestic tourism in China from 1995 to 2009.According to the results,we drew the following conclusions:(1)The regional difference of domestic tourism in China tends to be narrowing generally,and is less than that of inbound tourism,playing an important role in narrowing the overall gap of regional tourism in China.(2)The regional internal difference features:inter-provincial difference in the eastern region and difference among the eastern,central and western regions are comparatively obvious and demonstrate a significantly shrinking tendency,the change tendency is consistent with the change tendency of overall difference and exercises a decisive role in overall difference,whereas the inter-provincial difference in the central and western regions is small and relatively stable,having less influence on the overall difference.(3)The temporal-spatial change in regional difference is featured by:low-level provinces occupy a majority and are concentrated in the central and western regions,showing a tendency of narrowing difference;high-level provinces are concentrated in the eastern region,showing a tendency of spreading to the central and western regions;spatial pattern of regional difference demonstrates 4 types,i.e."proliferation type","polarization type","quiescence type"and"collapse type."(4)The driving force for regional difference of domestic tourism in China comes down to 3 aspects:regional socio-economic attribute,regional transport accessibility level and regional development policy.展开更多
Based on the investigation data of Jiaozhou Bay waters in 1981,current situation and horizontal distribution of Cr content in bottom waters of Jiaozhou Bay mouth were studied. Results showed that in bottom waters of J...Based on the investigation data of Jiaozhou Bay waters in 1981,current situation and horizontal distribution of Cr content in bottom waters of Jiaozhou Bay mouth were studied. Results showed that in bottom waters of Jiaozhou Bay center,Cr content changed from 0. 50 to3. 78 μg/L in April. In August,Cr content changed from 0. 14 to 1. 42 μg/L in bottom waters of Jiaozhou Bay mouth. It showed that Cr content corresponded with national class-one seawater quality standard(50. 00 μg/L) at different times and spaces,and Cr content was far less than5. 00 μg/L. Therefore,under the effect of vertical water body,water quality was clean in bottom waters of Jiaozhou Bay,which was not polluted by Cr. In bottom waters of Jiaozhou Bay center in April and bottom waters of Jiaozhou Bay mouth in August,Cr transported by the river came to the bottom layer from surface layer by passing through water body in temporal-spatial change process. Under the effects of gravity and water flow,Cr continuously and quickly sank to the sea bottom. It verified the sedimentation process of Cr content.展开更多
Mangrove ecosystem has an important ecological function. But since it is distributed in land-sea alternating region,mangrove is vulnerable to environmental pollution. Mangrove area of Guangdong Province greatly decrea...Mangrove ecosystem has an important ecological function. But since it is distributed in land-sea alternating region,mangrove is vulnerable to environmental pollution. Mangrove area of Guangdong Province greatly decreased after the 1950 s,and it declined to the minimum in the1990 s and then gradually increased. Mangrove area of Guangdong Province quickly increased from 2001 to now,and its area in 2014 was 19 824. 53 hm^2,in which Zhanjiang accounted for 72%. During 2001-2014,mangrove area of Guangdong Province increased significantly,in which the newly increased mangrove area in Zhanjiang,Yangjiang,Jiangmen,Zhuhai,Guangzhou and Shantou was larger,with obvious increase magnitude; mangrove area in east Guangdong during 2001-2005 increased quickly,while increase magnitude of mangrove area in west Guangdong and the Pearl River Delta was improved significantly after 2005. Additionally,mangrove species in Guangdong Province continuously decreased from south to north,showing as west Guangdong > the Pearl River Delta > east Guangdong. Mangrove of Guangdong Province could be protected strictly from shoreline control,ecological protection,function upgrading,and ecological restoration.展开更多
As global greenhouse gases continue rising,the urgency of more ambitious action is clearer than ever before.China is the world’s biggest emitter of greenhouse gases and one of the countries affected most by climate c...As global greenhouse gases continue rising,the urgency of more ambitious action is clearer than ever before.China is the world’s biggest emitter of greenhouse gases and one of the countries affected most by climate change.The evidence about the impacts of climate change on the environment and human health may encourage China to take more decisive action to mitigate greenhouse gas emissions and adapt to climate impacts.展开更多
Latent heat thermal energy storage(TES)effectively reduces the mismatch between energy supply and demand of renewable energy sources by the utilization of phase change materials(PCMs).However,the low thermal conductiv...Latent heat thermal energy storage(TES)effectively reduces the mismatch between energy supply and demand of renewable energy sources by the utilization of phase change materials(PCMs).However,the low thermal conductivity and poor shape stability are the main drawbacks in realizing the large-scale application of PCMs.Promisingly,developing composite PCM(CPCM)based on porous supporting mate-rial provides a desirable solution to obtain performance-enhanced PCMs with improved effective thermal conductivity and shape stability.Among all the porous matrixes as supports for PCM,three-dimensional carbon-based porous supporting material has attracted considerable attention ascribing to its high ther-mal conductivity,desirable loading capacity of PCMs,and excellent chemical compatibility with various PCMs.Therefore,this work systemically reviews the CPCMs with three-dimensional carbon-based porous supporting materials.First,a concise rule for the fabrication of CPCMs is illustrated in detail.Next,the experimental and computational research of carbon nanotube-based support,graphene-based support,graphite-based support and amorphous carbon-based support are reviewed.Then,the applications of the shape-stabilized CPCMs including thermal management and thermal conversion are illustrated.Last but not least,the challenges and prospects of the CPCMs are discussed.To conclude,introducing carbon-based porous materials can solve the liquid leakage issue and essentially improve the thermal conductivity of PCMs.However,there is still a long way to further develop a desirable CPCM with higher latent heat capacity,higher thermal conductivity,and more excellent shape stability.展开更多
Located downstream the Kupang Catchment in Indonesia,Pekalongan faces significant land subsidence issues,leading to severe coastal flooding.This study aimed to assess the impact of climate change on future flow regime...Located downstream the Kupang Catchment in Indonesia,Pekalongan faces significant land subsidence issues,leading to severe coastal flooding.This study aimed to assess the impact of climate change on future flow regimes and hydrological extremes to inform long-term water resources management strategies for the Kupang Catchment.Utilizing precipitation and air temperature data from general circulation models in the Coupled Model Intercomparison Project 6(CMIP6)and employing bias correction techniques,the Soil and Water Assessment Tool(SWAT)hydrological model was employed to analyze climate-induced changes in hydrological fluxes,specifically streamflow.Results indicated a consistent increase in monthly streamflow during the wet season,with a substantial rise of 22.8%,alongside a slight decrease of 18.0%during the dry season.Moreover,both the frequency and severity of extremely low and high flows were projected to intensify by approximately 50%and 70%,respectively,for a 20-year return period,suggesting heightened flood and drought risks in the future.The observed declining trend in low flow,by up to 11%,indicated the potential for long-term groundwater depletion exacerbating the threat of land subsidence and coastal flooding,especially in areas with inadequate surface water management policies and infrastructure.展开更多
Terrestrial ecosystems heavily depend on vegetation,which responds to carbon dioxide(CO_(2))fertilization in hot and humid regions.The subtropical humid karst region is a hot and humid region;whether and to what exten...Terrestrial ecosystems heavily depend on vegetation,which responds to carbon dioxide(CO_(2))fertilization in hot and humid regions.The subtropical humid karst region is a hot and humid region;whether and to what extent CO_(2)fertilization affects vegetation changes in such regions remains unclear.In this study,we investigated the degree to which CO_(2)fertilization influences vegetation changes,along with their spatial and temporal differences,in the subtropical humid karst region using time-lag effect analysis,a random forest model,and multiple regression analysis.Results showed that CO_(2)fertilization plays an important role in vegetation changes,exhibiting clear spatial variations across different geomorphological zones,with its degree of influence ranging mainly between 11%and 25%.The highest contribution of CO_(2)fertilization was observed in the karst basin and non-karstic region,whereas the lowest contribution was found in the karst plateau region.Previous studies have primarily attributed vegetation changes in subtropical humid karst region to ecological engineering,leading to an overestimation of its contribution to these changes.The findings of this study enhance the understanding of the mechanism of vegetation changes in humid karst region and provide theoretical and practical insights for ecological and environmental protection in these regions.展开更多
The toxicity of PM_(2.5)does not necessarily change synchronously with its mass concentration.In this study,the chemical composition(carbonaceous species,water-soluble ions,and metals)and oxidative potential(dithiothr...The toxicity of PM_(2.5)does not necessarily change synchronously with its mass concentration.In this study,the chemical composition(carbonaceous species,water-soluble ions,and metals)and oxidative potential(dithiothreitol assay,DTT)of PM_(2.5)were investigated in 2017/2018 and 2022 in Xiamen,China.The decrease rate of volume-normalized DTT(DTTv)(38%)was lower than that of PM_(2.5)(55%)between the two sampling periods.However,the mass-normalized DTT(DTTm)increased by 44%.Clear seasonal patterns with higher levels in winter were found for PM_(2.5),most chemical constituents and DTTv but not for DTTm.The large decrease in DTT activity(84%−92%)after the addition of EDTA suggested that watersoluble metals were the main contributors to DTT in Xiamen.The increased gap between the reconstructed and measured DTTv and the stronger correlations between the reconstructed/measured DTT ratio and carbonaceous species in 2022were observed.The decrease rates of the hazard index(32.5%)and lifetime cancer risk(9.1%)differed from those of PM_(2.5)and DTTv due to their different main contributors.The PMF-MLR model showed that the contributions(nmol/(min·m^(3)))of vehicle emission,coal+biomass burning,ship emission and secondary aerosol to DTTv in 2022 decreased by 63.0%,65.2%,66.5%,and 22.2%,respectively,compared to those in 2017/2018,which was consistent with the emission reduction of vehicle exhaust and coal consumption,the adoption of low-sulfur fuel oil used on board ships and the reduced production of WSOC.However,the contributions of dust+sea salt and industrial emission increased.展开更多
Agricultural pests cause enormous losses in annual agricultural production.Understanding the evolutionary responses and adaptive capacity of agricultural pests under climate change is crucial for establishing sustaina...Agricultural pests cause enormous losses in annual agricultural production.Understanding the evolutionary responses and adaptive capacity of agricultural pests under climate change is crucial for establishing sustainable and environmentally friendly agricultural pest management.In this study,we integrate climate modeling and landscape genomics to investigate the distributional dynamics of the cotton bollworm(Helicoverpa armigera)in the adaptation to local environments and resilience to future climate change.Notably,the predicted inhabitable areas with higher suitability for the cotton bollworm could be eight times larger in the coming decades.Climate change is one of the factors driving the dynamics of distribution and population differentiation of the cotton bollworm.Approximately 19,000 years ago,the cotton bollworm expanded from its ancestral African population,followed by gradual occupations of the European,Asian,Oceanian,and American continents.Furthermore,we identify seven subpopulations with high dispersal and adaptability which may have an increased risk of invasion potential.Additionally,a large number of candidate genes and SNPs linked to climatic adaptation were mapped.These findings could inform sustainable pest management strategies in the face of climate change,aiding future pest forecasting and management planning.展开更多
BACKGROUND Atypical optic neuritis,consisting of neuromyelitis optica spectrum disorders(NMOSD)or myelin oligodendrocyte glycoprotein antibody disease(MOGAD),has a very similar presentation but different prognostic im...BACKGROUND Atypical optic neuritis,consisting of neuromyelitis optica spectrum disorders(NMOSD)or myelin oligodendrocyte glycoprotein antibody disease(MOGAD),has a very similar presentation but different prognostic implications and longterm management strategies.Vascular and metabolic factors are being thought to play a role in such autoimmune neuro-inflammatory disorders,apart from the obvious immune mediated damage.With the advent of optical coherence tomography angiography(OCTA),it is easy to pick up on these subclinical macular microvascular and structural changes.AIM To study the macular microvascular and structural changes on OCTA in atypical optic neuritis.METHODS This observational cross-sectional study involved 8 NMOSD and 17 MOGAD patients,diagnosed serologically,as well as 10 healthy controls.Macular vascular density(MVD)and ganglion cell+inner plexiform layer thickness(GCIPL)were studied using OCTA.RESULTS There was a significant reduction in MVD in NMOSD and MOGAD affected as well as unaffected eyes when compared with healthy controls.NMOSD and MOGAD affected eyes had significant GCIPL thinning compared with healthy controls.NMOSD unaffected eyes did not show significant GCIPL thinning compared to healthy controls in contrast to MOGAD unaffected eyes.On comparing NMOSD with MOGAD,there was no significant difference in terms of MVD or GCIPL in the affected or unaffected eyes.CONCLUSION Although significant microvascular and structural changes are present on OCTA between atypical optic neuritis and normal patients,they could not help in differentiating between NMOSD and MOGAD cases.展开更多
Gas-bearing shales have become a major source of future natural gas production worldwide.It has become increasingly urgent to develop a reliable prediction model and corresponding workflow for identifying shale gas sw...Gas-bearing shales have become a major source of future natural gas production worldwide.It has become increasingly urgent to develop a reliable prediction model and corresponding workflow for identifying shale gas sweet spots.The formation of gas-bearing shales is closely linked to relative sealevel changes,providing an important approach to predicting sweet spots in the Wufeng-Longmaxi shale in the southern Sichuan Basin,China.Three types of marine shale gas sweet spots are identified in the shale based on their formation stages combined with relative sea-level changes:early,middle,and late transgression types.This study develops a prediction model and workflow for identifying shale gas sweet spots by analyzing relative sea-level changes and facies sequences.Predicting shale gas sweet spots in an explored block using this model and workflow can provide a valuable guide for well design and hydraulic fracturing,significantly enhancing the efficiency of shale gas exploration and development.Notably,the new prediction model and workflow can be utilized for the rapid evaluation of the potential for shale gas development in new shale gas blocks or those with low exploratory maturity.展开更多
We examine possible funding sources for constructing Climate Change Haven Communities on a global basis. Areas of the planet that have the potential to house persons migrating to “safe havens” in their own or other ...We examine possible funding sources for constructing Climate Change Haven Communities on a global basis. Areas of the planet that have the potential to house persons migrating to “safe havens” in their own or other countries will require the rapid construction of communities capable of supporting them, their families, businesses and farms. However, different political-economic conditions are found across the areas which can serve as locations for these Climate Change Haven Communities. We develop funding and construction strategies for the United States (free-market capitalism), France and Spain (European Union supported economies), and Taiwan region (state-directed economy). The proposals for the Taiwan region should also be applicable to the rest of China.展开更多
BACKGROUND Dyslipidemia was strongly linked to stroke,however the relationship between dyslipidemia and its components and ischemic stroke remained unexplained.AIM To investigate the link between longitudinal changes ...BACKGROUND Dyslipidemia was strongly linked to stroke,however the relationship between dyslipidemia and its components and ischemic stroke remained unexplained.AIM To investigate the link between longitudinal changes in lipid profiles and dyslipidemia and ischemic stroke in a hypertensive population.METHODS Between 2013 and 2014,6094 hypertension individuals were included in this,and ischemic stroke cases were documented to the end of 2018.Longitudinal changes of lipid were stratified into four groups:(1)Normal was transformed into normal group;(2)Abnormal was transformed into normal group;(3)Normal was transformed into abnormal group;and(4)Abnormal was transformed into abnormal group.To examine the link between longitudinal changes in dyslipidemia along with its components and the risk of ischemic stroke,we utilized multivariate Cox proportional hazards models with hazard ratio(HR)and 95%CI.RESULTS The average age of the participants was 62.32 years±13.00 years,with 329 women making up 54.0%of the sample.Over the course of a mean follow-up of 4.8 years,143 ischemic strokes happened.When normal was transformed into normal group was used as a reference,after full adjustments,the HR for dyslipidemia and ischemic stroke among abnormal was transformed into normal group,normal was transformed into abnormal group and abnormal was transformed into abnormal Wei CC et al.Dyslipidemia changed and ischemic stroke WJCC https://www.wjgnet.com 2 February 6,2025 Volume 13 Issue 4 group were 1.089(95%CI:0.598-1.982;P=0.779),2.369(95%CI:1.424-3.941;P<0.001)and 1.448(95%CI:1.002-2.298;P=0.047)(P for trend was 0.233),respectively.CONCLUSION In individuals with hypertension,longitudinal shifts from normal to abnormal in dyslipidemia-particularly in total and low-density lipoprotein cholesterol-were significantly associated with the risk of ischemic stroke.展开更多
We adopted the solution impregnation route with aluminum dihydrogen phosphate solution as liquid medium for effective surface modification on graphite substrate.The mass ratio of graphite to Al(H_(2)PO_(4))_(3) change...We adopted the solution impregnation route with aluminum dihydrogen phosphate solution as liquid medium for effective surface modification on graphite substrate.The mass ratio of graphite to Al(H_(2)PO_(4))_(3) changed from 0.5:1 to 4:1,and the impregnation time changed from 1 to 7 h.The typical composite phase change thermal storage materials doped with the as-treated graphite were fabricated using form-stable technique.To investigate the oxidation and anti-oxidation behavior of the impregnated graphite at high temperatures,the samples were put into a muffle furnace for a cyclic heat test.Based on SEM,EDS,DSC techniques,analyses on the impregnated technique suggested an optimized processing conditions of a 3 h impregnation time with the ratio of graphite:Al(H_(2)PO_(4))_(3) as 1:3 for graphite impregnation treatment.Further investigations on high-temperature phase change heat storage materials doped by the treated graphite suggested excellent oxidation resistance and thermal cycling performance.展开更多
In Niger, farms have been facing negative effects of climate change for several decades. The objective of this work is to assess the vulnerability of farms in Tillabery department by proposing an adaptation approach. ...In Niger, farms have been facing negative effects of climate change for several decades. The objective of this work is to assess the vulnerability of farms in Tillabery department by proposing an adaptation approach. A five-step method and descriptive analysis were used on a sample of 250 farmers. The degree of damage caused by pests and crop diseases is significant, with respective proportions of 52.50% and 40.40%. It appears that the main climate risk factors for vulnerability are droughts, floods, soil degradation, and pest invasions. Additionally, the average level of exposure to agricultural operations is very high, with an index of 0.6. The sensitivity index remained constant in the range of 0.3 to 0.6 and is significant (reaching an index of 0.8). However, 61.2% of farms have a medium level of vulnerability and 33.3% have a high vulnerability to the effects of climate change. Nonetheless, a concerning trend regarding the vulnerability of farms has been observed. To assist policymakers and development actors in improving the vulnerability level of these production units, four phases of action are proposed: a diagnostic phase, evaluation, estimation of adaptation needs, implementation, and proper monitoring of actions.展开更多
The department of Tillabéri is primarily affected by climatic phenomena, impacting crop yields, growing cycles, and consequently, the economic outcomes of agricultural operations. The objective of this study is t...The department of Tillabéri is primarily affected by climatic phenomena, impacting crop yields, growing cycles, and consequently, the economic outcomes of agricultural operations. The objective of this study is to analyze these impacts of climate disruption on the economic performance of farms. The methodology adopted for this study combined documentary research with field surveys conducted on a sample of 250 randomly selected farmers. The analytical methods used mainly consisted of linear regression, profitability calculations, and linear programming. The findings indicate that all productions across different crops have experienced a decrease over the past 30 years. For instance, the production of millet, sorghum, and cowpea, which were respectively 812 kg/ha, 260 kg/ha, and 100 kg/ha between the last 30 and 20 years, has now dropped to 412 kg/ha, 106 kg/ha, and 46 kg/ha respectively. A negative and significant effect on agricultural net margin was observed due to variables such as flooding, drought, pest invasion in rice fields, and temperature changes. Smallholder farms show a relatively low margin (46%) to cover their fixed costs, which may indicate a risk if fixed expenses are high. Furthermore, the analysis results from linear programming reveal that farmers could achieve an additional net profit per hectare of 116,861 FCFA, 217201.5 FCFA, and 291988.2 FCFA respectively for small, medium, and large producers by managing variable costs and health-related expenses for households.展开更多
Objective Primary liver cancer,predominantly hepatocellular carcinoma(HCC),is a significant global health issue,ranking as the sixth most diagnosed cancer and the third leading cause of cancer-related mortality.Accura...Objective Primary liver cancer,predominantly hepatocellular carcinoma(HCC),is a significant global health issue,ranking as the sixth most diagnosed cancer and the third leading cause of cancer-related mortality.Accurate and early diagnosis of HCC is crucial for effective treatment,as HCC and non-HCC malignancies like intrahepatic cholangiocarcinoma(ICC)exhibit different prognoses and treatment responses.Traditional diagnostic methods,including liver biopsy and contrast-enhanced ultrasound(CEUS),face limitations in applicability and objectivity.The primary objective of this study was to develop an advanced,lightweighted classification network capable of distinguishing HCC from other non-HCC malignancies by leveraging the automatic analysis of brightness changes in CEUS images.The ultimate goal was to create a user-friendly and cost-efficient computer-aided diagnostic tool that could assist radiologists in making more accurate and efficient clinical decisions.Methods This retrospective study encompassed a total of 161 patients,comprising 131 diagnosed with HCC and 30 with non-HCC malignancies.To achieve accurate tumor detection,the YOLOX network was employed to identify the region of interest(ROI)on both B-mode ultrasound and CEUS images.A custom-developed algorithm was then utilized to extract brightness change curves from the tumor and adjacent liver parenchyma regions within the CEUS images.These curves provided critical data for the subsequent analysis and classification process.To analyze the extracted brightness change curves and classify the malignancies,we developed and compared several models.These included one-dimensional convolutional neural networks(1D-ResNet,1D-ConvNeXt,and 1D-CNN),as well as traditional machine-learning methods such as support vector machine(SVM),ensemble learning(EL),k-nearest neighbor(KNN),and decision tree(DT).The diagnostic performance of each method in distinguishing HCC from non-HCC malignancies was rigorously evaluated using four key metrics:area under the receiver operating characteristic(AUC),accuracy(ACC),sensitivity(SE),and specificity(SP).Results The evaluation of the machine-learning methods revealed AUC values of 0.70 for SVM,0.56 for ensemble learning,0.63 for KNN,and 0.72 for the decision tree.These results indicated moderate to fair performance in classifying the malignancies based on the brightness change curves.In contrast,the deep learning models demonstrated significantly higher AUCs,with 1D-ResNet achieving an AUC of 0.72,1D-ConvNeXt reaching 0.82,and 1D-CNN obtaining the highest AUC of 0.84.Moreover,under the five-fold cross-validation scheme,the 1D-CNN model outperformed other models in both accuracy and specificity.Specifically,it achieved accuracy improvements of 3.8%to 10.0%and specificity enhancements of 6.6%to 43.3%over competing approaches.The superior performance of the 1D-CNN model highlighted its potential as a powerful tool for accurate classification.Conclusion The 1D-CNN model proved to be the most effective in differentiating HCC from non-HCC malignancies,surpassing both traditional machine-learning methods and other deep learning models.This study successfully developed a user-friendly and cost-efficient computer-aided diagnostic solution that would significantly enhances radiologists’diagnostic capabilities.By improving the accuracy and efficiency of clinical decision-making,this tool has the potential to positively impact patient care and outcomes.Future work may focus on further refining the model and exploring its integration with multimodal ultrasound data to maximize its accuracy and applicability.展开更多
基金Supported by National Program on Key Basic Research Project of China (2011CB403206)National Key Technology Research and Development Program during the 12~(th) Five-year Plan Period of China(2012BAC19B04)~~
文摘[Objective] This study aimed to analyze the temporal-spatial variation of Inner Mongolian grassland degradation during past three decades. [Method] The dis- tribution characteristics of grassland were described by land use types supervised classification with TM/ETM. Then, temporal-spatial changes of grassland coverage were quantified by the mean of maximum vegetation coverage in last 30 years. Lastly, the grassland degradation reasons were explored through statistic analysis between the grassland coverage and precipitation, temperature and grazing intensity. [Result] The grassland degradation index of Inner Mongolia was increased from 1.38 to 1.68, and the smallest was 1.28 in 2005s. Grassland degradation and improve- ment were concurrent after 1980s, but grassland degradation was the major change trend for Inner Mongolia grassland. The area of grassland degradation was enlarged from 18.08×10^4 km2 in 1980s to 22.47×10^4 km2 in 2010s on the whole and distribu- tion range was shifted from central-eastern to west in Inner Mongolia that mainly distributed on Hulun Buir and Xilin Gol grassland in 1980s and Ordos and Alax grassland in 2010s. The grassland area of degradation had a rising trend form 1980s to 1995s, then reduced to 10.8x104 km2 in 2005s, and decreased in 2010s, which mainly speared in the west of Xilin Gol grassland. [Conclusion] Inner Mongo-lian grassland degradation were become more seriously in last 30 years because that temperature, precipitation and graze intensities change, which not performance on decreasing coverage but grassland areas.
文摘[ Objective] The research aimed to study temporal-spatial change characteristics of the extremely low temperature climate event in winter of China. [MethodI By using actual probability distribution threshold value method, EOF analysis method and the daily minimum temperature data in winter of 1961 -2008 at 195 observatories of China, temporal-spatial change characteristics of the extremely low temperature climate event in win- ter of China in 48 years were analyzed. [ Result] Threshold value calculated by actual probability distribution was higher than that by traditional method, and increase magnitude in east was bigger than that in west, which could describe climatic change situation in China in 48 years better than traditional method. Cold night number in winter of China did not decrease as latitude declined, and it was more in south and north and was less in Yellow River basin and northwest China. Cold night number was the most in northeast Inner Mongolia. Interannual change of the cold night number presented decline tendency. From the 1960s to the eady 1970s, cold night number consistently increased, and change in middle and late periods of the 1960s was severe. From the early 1970s to the middle 1980s, fluctuation of the cold night number was bigger, and increase of the cold night number was the most in 1976. Cold night number from 1986 to the 21= century continuously declined. Change of the cold night number was the most obvious in east region, Guizhou and north Guangxi. Cold night number in northeast China and north Inner Mongolia presented inverting change relationship with that in Yunnan - Kweichow Plateau and Hexi Corridor. [ Conclusion] The research provided reference for eady warning of the extremely low temoerature event in China.
基金National Natural Science Foundation of China(Grant No.41271134)the Humanities and Social Science Research Foundation of Ministry of Education(Grant No.10YJC790245)
文摘By using the variation coefficient,Gini coefficient and Theil coefficient,this paper makes preliminary exploration of temporalspatial change features and driving mechanism for regional differences of domestic tourism in China from 1995 to 2009.According to the results,we drew the following conclusions:(1)The regional difference of domestic tourism in China tends to be narrowing generally,and is less than that of inbound tourism,playing an important role in narrowing the overall gap of regional tourism in China.(2)The regional internal difference features:inter-provincial difference in the eastern region and difference among the eastern,central and western regions are comparatively obvious and demonstrate a significantly shrinking tendency,the change tendency is consistent with the change tendency of overall difference and exercises a decisive role in overall difference,whereas the inter-provincial difference in the central and western regions is small and relatively stable,having less influence on the overall difference.(3)The temporal-spatial change in regional difference is featured by:low-level provinces occupy a majority and are concentrated in the central and western regions,showing a tendency of narrowing difference;high-level provinces are concentrated in the eastern region,showing a tendency of spreading to the central and western regions;spatial pattern of regional difference demonstrates 4 types,i.e."proliferation type","polarization type","quiescence type"and"collapse type."(4)The driving force for regional difference of domestic tourism in China comes down to 3 aspects:regional socio-economic attribute,regional transport accessibility level and regional development policy.
基金Supported by the China National Natural Science Foundation(31560107)Doctoral Degree Construction Library of Guizhou Minzu University,Education Ministry’s New Century Excellent Talents Supporting Plan(NCET-12-0659)+3 种基金Innovation Group Major Program of Guizhou Province(KY[2013]405,KY[2016]029)Research Projects of Guizhou Province Ministry of Science and Technology(LH[2014]7376)Research Projects of Guizhou Minzu University([2014]02)Research Projects of Guizhou Province Ministry of Education(KY[2014]266)
文摘Based on the investigation data of Jiaozhou Bay waters in 1981,current situation and horizontal distribution of Cr content in bottom waters of Jiaozhou Bay mouth were studied. Results showed that in bottom waters of Jiaozhou Bay center,Cr content changed from 0. 50 to3. 78 μg/L in April. In August,Cr content changed from 0. 14 to 1. 42 μg/L in bottom waters of Jiaozhou Bay mouth. It showed that Cr content corresponded with national class-one seawater quality standard(50. 00 μg/L) at different times and spaces,and Cr content was far less than5. 00 μg/L. Therefore,under the effect of vertical water body,water quality was clean in bottom waters of Jiaozhou Bay,which was not polluted by Cr. In bottom waters of Jiaozhou Bay center in April and bottom waters of Jiaozhou Bay mouth in August,Cr transported by the river came to the bottom layer from surface layer by passing through water body in temporal-spatial change process. Under the effects of gravity and water flow,Cr continuously and quickly sank to the sea bottom. It verified the sedimentation process of Cr content.
文摘Mangrove ecosystem has an important ecological function. But since it is distributed in land-sea alternating region,mangrove is vulnerable to environmental pollution. Mangrove area of Guangdong Province greatly decreased after the 1950 s,and it declined to the minimum in the1990 s and then gradually increased. Mangrove area of Guangdong Province quickly increased from 2001 to now,and its area in 2014 was 19 824. 53 hm^2,in which Zhanjiang accounted for 72%. During 2001-2014,mangrove area of Guangdong Province increased significantly,in which the newly increased mangrove area in Zhanjiang,Yangjiang,Jiangmen,Zhuhai,Guangzhou and Shantou was larger,with obvious increase magnitude; mangrove area in east Guangdong during 2001-2005 increased quickly,while increase magnitude of mangrove area in west Guangdong and the Pearl River Delta was improved significantly after 2005. Additionally,mangrove species in Guangdong Province continuously decreased from south to north,showing as west Guangdong > the Pearl River Delta > east Guangdong. Mangrove of Guangdong Province could be protected strictly from shoreline control,ecological protection,function upgrading,and ecological restoration.
基金supported by the National Natural Science Foundation of China(No.82025030,No.72394404)the National Key Research and Development Program of China(No.2022YFC3702700)the National Research Program for Key Issues in Air Pollution Control of China(No.DQGG0401).
文摘As global greenhouse gases continue rising,the urgency of more ambitious action is clearer than ever before.China is the world’s biggest emitter of greenhouse gases and one of the countries affected most by climate change.The evidence about the impacts of climate change on the environment and human health may encourage China to take more decisive action to mitigate greenhouse gas emissions and adapt to climate impacts.
基金supported by the National Natural Science Foundation of China(No.52127816),the National Key Research and Development Program of China(No.2020YFA0715000)the National Natural Science and Hong Kong Research Grant Council Joint Research Funding Project of China(No.5181101182)the NSFC/RGC Joint Research Scheme sponsored by the Research Grants Council of Hong Kong and the National Natural Science Foundation of China(No.N_PolyU513/18).
文摘Latent heat thermal energy storage(TES)effectively reduces the mismatch between energy supply and demand of renewable energy sources by the utilization of phase change materials(PCMs).However,the low thermal conductivity and poor shape stability are the main drawbacks in realizing the large-scale application of PCMs.Promisingly,developing composite PCM(CPCM)based on porous supporting mate-rial provides a desirable solution to obtain performance-enhanced PCMs with improved effective thermal conductivity and shape stability.Among all the porous matrixes as supports for PCM,three-dimensional carbon-based porous supporting material has attracted considerable attention ascribing to its high ther-mal conductivity,desirable loading capacity of PCMs,and excellent chemical compatibility with various PCMs.Therefore,this work systemically reviews the CPCMs with three-dimensional carbon-based porous supporting materials.First,a concise rule for the fabrication of CPCMs is illustrated in detail.Next,the experimental and computational research of carbon nanotube-based support,graphene-based support,graphite-based support and amorphous carbon-based support are reviewed.Then,the applications of the shape-stabilized CPCMs including thermal management and thermal conversion are illustrated.Last but not least,the challenges and prospects of the CPCMs are discussed.To conclude,introducing carbon-based porous materials can solve the liquid leakage issue and essentially improve the thermal conductivity of PCMs.However,there is still a long way to further develop a desirable CPCM with higher latent heat capacity,higher thermal conductivity,and more excellent shape stability.
基金supported by the funding Riset Unggulan Daerah 2022 of the Bureau of Development Planning and Research in Central Java Province(BAPPEDA Provinsi Jawa Tengah).
文摘Located downstream the Kupang Catchment in Indonesia,Pekalongan faces significant land subsidence issues,leading to severe coastal flooding.This study aimed to assess the impact of climate change on future flow regimes and hydrological extremes to inform long-term water resources management strategies for the Kupang Catchment.Utilizing precipitation and air temperature data from general circulation models in the Coupled Model Intercomparison Project 6(CMIP6)and employing bias correction techniques,the Soil and Water Assessment Tool(SWAT)hydrological model was employed to analyze climate-induced changes in hydrological fluxes,specifically streamflow.Results indicated a consistent increase in monthly streamflow during the wet season,with a substantial rise of 22.8%,alongside a slight decrease of 18.0%during the dry season.Moreover,both the frequency and severity of extremely low and high flows were projected to intensify by approximately 50%and 70%,respectively,for a 20-year return period,suggesting heightened flood and drought risks in the future.The observed declining trend in low flow,by up to 11%,indicated the potential for long-term groundwater depletion exacerbating the threat of land subsidence and coastal flooding,especially in areas with inadequate surface water management policies and infrastructure.
基金National Natural Science Foundation of China,No.41761003The Karst Science Research Center of Guizhou Province,No.U1812401。
文摘Terrestrial ecosystems heavily depend on vegetation,which responds to carbon dioxide(CO_(2))fertilization in hot and humid regions.The subtropical humid karst region is a hot and humid region;whether and to what extent CO_(2)fertilization affects vegetation changes in such regions remains unclear.In this study,we investigated the degree to which CO_(2)fertilization influences vegetation changes,along with their spatial and temporal differences,in the subtropical humid karst region using time-lag effect analysis,a random forest model,and multiple regression analysis.Results showed that CO_(2)fertilization plays an important role in vegetation changes,exhibiting clear spatial variations across different geomorphological zones,with its degree of influence ranging mainly between 11%and 25%.The highest contribution of CO_(2)fertilization was observed in the karst basin and non-karstic region,whereas the lowest contribution was found in the karst plateau region.Previous studies have primarily attributed vegetation changes in subtropical humid karst region to ecological engineering,leading to an overestimation of its contribution to these changes.The findings of this study enhance the understanding of the mechanism of vegetation changes in humid karst region and provide theoretical and practical insights for ecological and environmental protection in these regions.
基金supported by the Science and Technology Program of Fujian Province,China(No.2023R1014002)the National Natural Science Foundation of China(No.41471390).
文摘The toxicity of PM_(2.5)does not necessarily change synchronously with its mass concentration.In this study,the chemical composition(carbonaceous species,water-soluble ions,and metals)and oxidative potential(dithiothreitol assay,DTT)of PM_(2.5)were investigated in 2017/2018 and 2022 in Xiamen,China.The decrease rate of volume-normalized DTT(DTTv)(38%)was lower than that of PM_(2.5)(55%)between the two sampling periods.However,the mass-normalized DTT(DTTm)increased by 44%.Clear seasonal patterns with higher levels in winter were found for PM_(2.5),most chemical constituents and DTTv but not for DTTm.The large decrease in DTT activity(84%−92%)after the addition of EDTA suggested that watersoluble metals were the main contributors to DTT in Xiamen.The increased gap between the reconstructed and measured DTTv and the stronger correlations between the reconstructed/measured DTT ratio and carbonaceous species in 2022were observed.The decrease rates of the hazard index(32.5%)and lifetime cancer risk(9.1%)differed from those of PM_(2.5)and DTTv due to their different main contributors.The PMF-MLR model showed that the contributions(nmol/(min·m^(3)))of vehicle emission,coal+biomass burning,ship emission and secondary aerosol to DTTv in 2022 decreased by 63.0%,65.2%,66.5%,and 22.2%,respectively,compared to those in 2017/2018,which was consistent with the emission reduction of vehicle exhaust and coal consumption,the adoption of low-sulfur fuel oil used on board ships and the reduced production of WSOC.However,the contributions of dust+sea salt and industrial emission increased.
基金funded by the National Natural Science Foundation of China(32372546)Shenzhen Science and Technology Program(KQTD20180411143628272)+1 种基金the Agricultural Science and Technology Innovation Program of Chinese Academy of Agricultural Sciences and STI 2030-Major Projects(2022ZD04021)the National Key Research and Development Program of China(2023YFD2200700)。
文摘Agricultural pests cause enormous losses in annual agricultural production.Understanding the evolutionary responses and adaptive capacity of agricultural pests under climate change is crucial for establishing sustainable and environmentally friendly agricultural pest management.In this study,we integrate climate modeling and landscape genomics to investigate the distributional dynamics of the cotton bollworm(Helicoverpa armigera)in the adaptation to local environments and resilience to future climate change.Notably,the predicted inhabitable areas with higher suitability for the cotton bollworm could be eight times larger in the coming decades.Climate change is one of the factors driving the dynamics of distribution and population differentiation of the cotton bollworm.Approximately 19,000 years ago,the cotton bollworm expanded from its ancestral African population,followed by gradual occupations of the European,Asian,Oceanian,and American continents.Furthermore,we identify seven subpopulations with high dispersal and adaptability which may have an increased risk of invasion potential.Additionally,a large number of candidate genes and SNPs linked to climatic adaptation were mapped.These findings could inform sustainable pest management strategies in the face of climate change,aiding future pest forecasting and management planning.
文摘BACKGROUND Atypical optic neuritis,consisting of neuromyelitis optica spectrum disorders(NMOSD)or myelin oligodendrocyte glycoprotein antibody disease(MOGAD),has a very similar presentation but different prognostic implications and longterm management strategies.Vascular and metabolic factors are being thought to play a role in such autoimmune neuro-inflammatory disorders,apart from the obvious immune mediated damage.With the advent of optical coherence tomography angiography(OCTA),it is easy to pick up on these subclinical macular microvascular and structural changes.AIM To study the macular microvascular and structural changes on OCTA in atypical optic neuritis.METHODS This observational cross-sectional study involved 8 NMOSD and 17 MOGAD patients,diagnosed serologically,as well as 10 healthy controls.Macular vascular density(MVD)and ganglion cell+inner plexiform layer thickness(GCIPL)were studied using OCTA.RESULTS There was a significant reduction in MVD in NMOSD and MOGAD affected as well as unaffected eyes when compared with healthy controls.NMOSD and MOGAD affected eyes had significant GCIPL thinning compared with healthy controls.NMOSD unaffected eyes did not show significant GCIPL thinning compared to healthy controls in contrast to MOGAD unaffected eyes.On comparing NMOSD with MOGAD,there was no significant difference in terms of MVD or GCIPL in the affected or unaffected eyes.CONCLUSION Although significant microvascular and structural changes are present on OCTA between atypical optic neuritis and normal patients,they could not help in differentiating between NMOSD and MOGAD cases.
文摘Gas-bearing shales have become a major source of future natural gas production worldwide.It has become increasingly urgent to develop a reliable prediction model and corresponding workflow for identifying shale gas sweet spots.The formation of gas-bearing shales is closely linked to relative sealevel changes,providing an important approach to predicting sweet spots in the Wufeng-Longmaxi shale in the southern Sichuan Basin,China.Three types of marine shale gas sweet spots are identified in the shale based on their formation stages combined with relative sea-level changes:early,middle,and late transgression types.This study develops a prediction model and workflow for identifying shale gas sweet spots by analyzing relative sea-level changes and facies sequences.Predicting shale gas sweet spots in an explored block using this model and workflow can provide a valuable guide for well design and hydraulic fracturing,significantly enhancing the efficiency of shale gas exploration and development.Notably,the new prediction model and workflow can be utilized for the rapid evaluation of the potential for shale gas development in new shale gas blocks or those with low exploratory maturity.
文摘We examine possible funding sources for constructing Climate Change Haven Communities on a global basis. Areas of the planet that have the potential to house persons migrating to “safe havens” in their own or other countries will require the rapid construction of communities capable of supporting them, their families, businesses and farms. However, different political-economic conditions are found across the areas which can serve as locations for these Climate Change Haven Communities. We develop funding and construction strategies for the United States (free-market capitalism), France and Spain (European Union supported economies), and Taiwan region (state-directed economy). The proposals for the Taiwan region should also be applicable to the rest of China.
文摘BACKGROUND Dyslipidemia was strongly linked to stroke,however the relationship between dyslipidemia and its components and ischemic stroke remained unexplained.AIM To investigate the link between longitudinal changes in lipid profiles and dyslipidemia and ischemic stroke in a hypertensive population.METHODS Between 2013 and 2014,6094 hypertension individuals were included in this,and ischemic stroke cases were documented to the end of 2018.Longitudinal changes of lipid were stratified into four groups:(1)Normal was transformed into normal group;(2)Abnormal was transformed into normal group;(3)Normal was transformed into abnormal group;and(4)Abnormal was transformed into abnormal group.To examine the link between longitudinal changes in dyslipidemia along with its components and the risk of ischemic stroke,we utilized multivariate Cox proportional hazards models with hazard ratio(HR)and 95%CI.RESULTS The average age of the participants was 62.32 years±13.00 years,with 329 women making up 54.0%of the sample.Over the course of a mean follow-up of 4.8 years,143 ischemic strokes happened.When normal was transformed into normal group was used as a reference,after full adjustments,the HR for dyslipidemia and ischemic stroke among abnormal was transformed into normal group,normal was transformed into abnormal group and abnormal was transformed into abnormal Wei CC et al.Dyslipidemia changed and ischemic stroke WJCC https://www.wjgnet.com 2 February 6,2025 Volume 13 Issue 4 group were 1.089(95%CI:0.598-1.982;P=0.779),2.369(95%CI:1.424-3.941;P<0.001)and 1.448(95%CI:1.002-2.298;P=0.047)(P for trend was 0.233),respectively.CONCLUSION In individuals with hypertension,longitudinal shifts from normal to abnormal in dyslipidemia-particularly in total and low-density lipoprotein cholesterol-were significantly associated with the risk of ischemic stroke.
基金Funded by Scientific and Technological Innovation Project of Carbon Emission Peak and Carbon Neutrality of Jiangsu Province(No.BE2022028-4)。
文摘We adopted the solution impregnation route with aluminum dihydrogen phosphate solution as liquid medium for effective surface modification on graphite substrate.The mass ratio of graphite to Al(H_(2)PO_(4))_(3) changed from 0.5:1 to 4:1,and the impregnation time changed from 1 to 7 h.The typical composite phase change thermal storage materials doped with the as-treated graphite were fabricated using form-stable technique.To investigate the oxidation and anti-oxidation behavior of the impregnated graphite at high temperatures,the samples were put into a muffle furnace for a cyclic heat test.Based on SEM,EDS,DSC techniques,analyses on the impregnated technique suggested an optimized processing conditions of a 3 h impregnation time with the ratio of graphite:Al(H_(2)PO_(4))_(3) as 1:3 for graphite impregnation treatment.Further investigations on high-temperature phase change heat storage materials doped by the treated graphite suggested excellent oxidation resistance and thermal cycling performance.
文摘In Niger, farms have been facing negative effects of climate change for several decades. The objective of this work is to assess the vulnerability of farms in Tillabery department by proposing an adaptation approach. A five-step method and descriptive analysis were used on a sample of 250 farmers. The degree of damage caused by pests and crop diseases is significant, with respective proportions of 52.50% and 40.40%. It appears that the main climate risk factors for vulnerability are droughts, floods, soil degradation, and pest invasions. Additionally, the average level of exposure to agricultural operations is very high, with an index of 0.6. The sensitivity index remained constant in the range of 0.3 to 0.6 and is significant (reaching an index of 0.8). However, 61.2% of farms have a medium level of vulnerability and 33.3% have a high vulnerability to the effects of climate change. Nonetheless, a concerning trend regarding the vulnerability of farms has been observed. To assist policymakers and development actors in improving the vulnerability level of these production units, four phases of action are proposed: a diagnostic phase, evaluation, estimation of adaptation needs, implementation, and proper monitoring of actions.
文摘The department of Tillabéri is primarily affected by climatic phenomena, impacting crop yields, growing cycles, and consequently, the economic outcomes of agricultural operations. The objective of this study is to analyze these impacts of climate disruption on the economic performance of farms. The methodology adopted for this study combined documentary research with field surveys conducted on a sample of 250 randomly selected farmers. The analytical methods used mainly consisted of linear regression, profitability calculations, and linear programming. The findings indicate that all productions across different crops have experienced a decrease over the past 30 years. For instance, the production of millet, sorghum, and cowpea, which were respectively 812 kg/ha, 260 kg/ha, and 100 kg/ha between the last 30 and 20 years, has now dropped to 412 kg/ha, 106 kg/ha, and 46 kg/ha respectively. A negative and significant effect on agricultural net margin was observed due to variables such as flooding, drought, pest invasion in rice fields, and temperature changes. Smallholder farms show a relatively low margin (46%) to cover their fixed costs, which may indicate a risk if fixed expenses are high. Furthermore, the analysis results from linear programming reveal that farmers could achieve an additional net profit per hectare of 116,861 FCFA, 217201.5 FCFA, and 291988.2 FCFA respectively for small, medium, and large producers by managing variable costs and health-related expenses for households.
文摘Objective Primary liver cancer,predominantly hepatocellular carcinoma(HCC),is a significant global health issue,ranking as the sixth most diagnosed cancer and the third leading cause of cancer-related mortality.Accurate and early diagnosis of HCC is crucial for effective treatment,as HCC and non-HCC malignancies like intrahepatic cholangiocarcinoma(ICC)exhibit different prognoses and treatment responses.Traditional diagnostic methods,including liver biopsy and contrast-enhanced ultrasound(CEUS),face limitations in applicability and objectivity.The primary objective of this study was to develop an advanced,lightweighted classification network capable of distinguishing HCC from other non-HCC malignancies by leveraging the automatic analysis of brightness changes in CEUS images.The ultimate goal was to create a user-friendly and cost-efficient computer-aided diagnostic tool that could assist radiologists in making more accurate and efficient clinical decisions.Methods This retrospective study encompassed a total of 161 patients,comprising 131 diagnosed with HCC and 30 with non-HCC malignancies.To achieve accurate tumor detection,the YOLOX network was employed to identify the region of interest(ROI)on both B-mode ultrasound and CEUS images.A custom-developed algorithm was then utilized to extract brightness change curves from the tumor and adjacent liver parenchyma regions within the CEUS images.These curves provided critical data for the subsequent analysis and classification process.To analyze the extracted brightness change curves and classify the malignancies,we developed and compared several models.These included one-dimensional convolutional neural networks(1D-ResNet,1D-ConvNeXt,and 1D-CNN),as well as traditional machine-learning methods such as support vector machine(SVM),ensemble learning(EL),k-nearest neighbor(KNN),and decision tree(DT).The diagnostic performance of each method in distinguishing HCC from non-HCC malignancies was rigorously evaluated using four key metrics:area under the receiver operating characteristic(AUC),accuracy(ACC),sensitivity(SE),and specificity(SP).Results The evaluation of the machine-learning methods revealed AUC values of 0.70 for SVM,0.56 for ensemble learning,0.63 for KNN,and 0.72 for the decision tree.These results indicated moderate to fair performance in classifying the malignancies based on the brightness change curves.In contrast,the deep learning models demonstrated significantly higher AUCs,with 1D-ResNet achieving an AUC of 0.72,1D-ConvNeXt reaching 0.82,and 1D-CNN obtaining the highest AUC of 0.84.Moreover,under the five-fold cross-validation scheme,the 1D-CNN model outperformed other models in both accuracy and specificity.Specifically,it achieved accuracy improvements of 3.8%to 10.0%and specificity enhancements of 6.6%to 43.3%over competing approaches.The superior performance of the 1D-CNN model highlighted its potential as a powerful tool for accurate classification.Conclusion The 1D-CNN model proved to be the most effective in differentiating HCC from non-HCC malignancies,surpassing both traditional machine-learning methods and other deep learning models.This study successfully developed a user-friendly and cost-efficient computer-aided diagnostic solution that would significantly enhances radiologists’diagnostic capabilities.By improving the accuracy and efficiency of clinical decision-making,this tool has the potential to positively impact patient care and outcomes.Future work may focus on further refining the model and exploring its integration with multimodal ultrasound data to maximize its accuracy and applicability.
