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
This study aimed to investigate the effect of ultrasound-assisted alkaline extraction(UAE)(at 20 kHz and different powers of 0,200,300,400,500 and 600 W for 10 min)on the yield,structure and emulsifying properties of ...This study aimed to investigate the effect of ultrasound-assisted alkaline extraction(UAE)(at 20 kHz and different powers of 0,200,300,400,500 and 600 W for 10 min)on the yield,structure and emulsifying properties of chickpea protein isolate(CPI).Compared with the non-ultrasound group,ultrasound treatment at 400 W resulted in the largest increase in CPI yield,and both the particle size and turbidity decreased with increasing ultrasound power from 0 to 400 W.The scanning electron microscope results showed a uniform structural distribution of CPI.Moreover,itsα-helix content increased,β-sheet content decreased,and total sulfhydryl group content and endogenous fluorescence intensity rose,illustrating that UAE changed the secondary and tertiary structure of CPI.At 400 W,the solubility of the emulsion increased to 63.18%,and the best emulsifying properties were obtained;the emulsifying activity index(EAI)and emulsifying stability index(ESI)increased by 85.42%and 46.78%,respectively.Furthermore,the emulsion droplets formed were smaller and more uniform.In conclusion,proper UAE power conditions increased the extraction yield and protein content of CPI,and effectively improved its structure and emulsifying characteristics.展开更多
Ultrasound computed tomography(USCT)is a noninvasive biomedical imaging modality that offers insights into acoustic properties such as the sound speed(SS)and acoustic attenuation(AA)of the human body,enhancing diagnos...Ultrasound computed tomography(USCT)is a noninvasive biomedical imaging modality that offers insights into acoustic properties such as the sound speed(SS)and acoustic attenuation(AA)of the human body,enhancing diagnostic accuracy and therapy planning.Full waveform inversion(FWI)is a promising USCT image reconstruction method that optimizes the parameter fields of a wave propagation model via gradient-based optimization.However,twodimensional FWI methods are limited by their inability to account for three-dimensional wave propagation in the elevation direction,resulting in image artifacts.To address this problem,we propose a three-dimensional time-domain full waveform inversion algorithm to reconstruct the SS and AA distributions on the basis of a fractional Laplacian wave equation,adjoint field formulation,and gradient descent optimization.Validated by two sets of simulations,the proposed algorithm has potential for generating high-resolution and quantitative SS and AA distributions.This approach holds promise for clinical USCT applications,assisting early disease detection,precise abnormality localization,and optimized treatment planning,thus contributing to better healthcare outcomes.展开更多
目前,在利用超声变幅杆和磨粒相结合的方式来去除金属毛刺的应用中,虽然对单个超声空化泡的理论研究日渐成熟,但缺少水温对空化泡最大溃灭压力影响的研究。文章使用HyperMesh和LS-DYNA Program Manager软件模拟单个空化泡溃灭冲击工件...目前,在利用超声变幅杆和磨粒相结合的方式来去除金属毛刺的应用中,虽然对单个超声空化泡的理论研究日渐成熟,但缺少水温对空化泡最大溃灭压力影响的研究。文章使用HyperMesh和LS-DYNA Program Manager软件模拟单个空化泡溃灭冲击工件的动态过程,基于单个超声空化泡的最大溃灭压力理论,使用ANSYS Workbench软件分析单个空化泡均匀分布于钻削毛刺表面的溃灭效果。当液体介质装满球面激发式聚焦超声波清洗机的半球域时,COMSOL Multiphysics软件三维声场仿真和铝箔腐蚀实验结果表明在圆心处形成一个稳定的局部高声压区域,并在此区域内进行钻削毛刺去除实验。实验结果表明,水温升高可以有效提高毛刺去除效率。展开更多
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.
文摘This study aimed to investigate the effect of ultrasound-assisted alkaline extraction(UAE)(at 20 kHz and different powers of 0,200,300,400,500 and 600 W for 10 min)on the yield,structure and emulsifying properties of chickpea protein isolate(CPI).Compared with the non-ultrasound group,ultrasound treatment at 400 W resulted in the largest increase in CPI yield,and both the particle size and turbidity decreased with increasing ultrasound power from 0 to 400 W.The scanning electron microscope results showed a uniform structural distribution of CPI.Moreover,itsα-helix content increased,β-sheet content decreased,and total sulfhydryl group content and endogenous fluorescence intensity rose,illustrating that UAE changed the secondary and tertiary structure of CPI.At 400 W,the solubility of the emulsion increased to 63.18%,and the best emulsifying properties were obtained;the emulsifying activity index(EAI)and emulsifying stability index(ESI)increased by 85.42%and 46.78%,respectively.Furthermore,the emulsion droplets formed were smaller and more uniform.In conclusion,proper UAE power conditions increased the extraction yield and protein content of CPI,and effectively improved its structure and emulsifying characteristics.
基金supported by the National Key Research and Development Program of China(2022YFA1404400)the National Natural Science Foundation of China(62122072,12174368,61705216,62405306)+4 种基金Anhui Provincial Department of Science and Technology(202203a07020020,18030801138)Anhui Provincial Natural Science Foundation(2308085QA21,2408085QF187)the USTC Research Funds of the Double First-Class Initiative(YD2090002015)the Institute of Artificial Intelligence at Hefei Comprehensive National Science Center(23YGXT005)the Fundamental Research Funds for the Central Universities(WK2090000083).
文摘Ultrasound computed tomography(USCT)is a noninvasive biomedical imaging modality that offers insights into acoustic properties such as the sound speed(SS)and acoustic attenuation(AA)of the human body,enhancing diagnostic accuracy and therapy planning.Full waveform inversion(FWI)is a promising USCT image reconstruction method that optimizes the parameter fields of a wave propagation model via gradient-based optimization.However,twodimensional FWI methods are limited by their inability to account for three-dimensional wave propagation in the elevation direction,resulting in image artifacts.To address this problem,we propose a three-dimensional time-domain full waveform inversion algorithm to reconstruct the SS and AA distributions on the basis of a fractional Laplacian wave equation,adjoint field formulation,and gradient descent optimization.Validated by two sets of simulations,the proposed algorithm has potential for generating high-resolution and quantitative SS and AA distributions.This approach holds promise for clinical USCT applications,assisting early disease detection,precise abnormality localization,and optimized treatment planning,thus contributing to better healthcare outcomes.
文摘目前,在利用超声变幅杆和磨粒相结合的方式来去除金属毛刺的应用中,虽然对单个超声空化泡的理论研究日渐成熟,但缺少水温对空化泡最大溃灭压力影响的研究。文章使用HyperMesh和LS-DYNA Program Manager软件模拟单个空化泡溃灭冲击工件的动态过程,基于单个超声空化泡的最大溃灭压力理论,使用ANSYS Workbench软件分析单个空化泡均匀分布于钻削毛刺表面的溃灭效果。当液体介质装满球面激发式聚焦超声波清洗机的半球域时,COMSOL Multiphysics软件三维声场仿真和铝箔腐蚀实验结果表明在圆心处形成一个稳定的局部高声压区域,并在此区域内进行钻削毛刺去除实验。实验结果表明,水温升高可以有效提高毛刺去除效率。
