In this study, advanced image processing technology is used to analyze the three-dimensional sand composite image, and the topography features of sand particles are successfully extracted and saved as high-quality ima...In this study, advanced image processing technology is used to analyze the three-dimensional sand composite image, and the topography features of sand particles are successfully extracted and saved as high-quality image files. These image files were then trained using the latent diffusion model (LDM) to generate a large number of sand particles with real morphology, which were then applied to numerical studies. The effects of particle morphology on the macroscopic mechanical behavior and microscopic energy evolution of sand under complex stress paths were studied in detail, combined with the circular and elliptical particles widely used in current tests. The results show that with the increase of the irregularity of the sample shape, the cycle period and radius of the closed circle formed by the partial strain curve gradually decrease, and the center of the circle gradually shifts. In addition, the volume strain and liquefaction strength of sand samples increase with the increase of particle shape irregularity. It is particularly noteworthy that obvious vortex structures exist in the positions near the center where deformation is severe in the samples of circular and elliptical particles. However, such structures are difficult to be directly observed in sample with irregular particles. This phenomenon reveals the influence of particle morphology on the complexity of the mechanical behavior of sand, providing us with new insights into the understanding of the response mechanism of sand soil under complex stress conditions.展开更多
The applications of machine learning(ML)in the medical domain are often hindered by the limited availability of high-quality data.To address this challenge,we explore the synthetic generation of echocardiography image...The applications of machine learning(ML)in the medical domain are often hindered by the limited availability of high-quality data.To address this challenge,we explore the synthetic generation of echocardiography images(echoCG)using state-of-the-art generative models.We conduct a comprehensive evaluation of three prominent methods:Cycle-consistent generative adversarial network(CycleGAN),Contrastive Unpaired Translation(CUT),and Stable Diffusion 1.5 with Low-Rank Adaptation(LoRA).Our research presents the data generation methodol-ogy,image samples,and evaluation strategy,followed by an extensive user study involving licensed cardiologists and surgeons who assess the perceived quality and medical soundness of the generated images.Our findings indicate that Stable Diffusion outperforms both CycleGAN and CUT in generating images that are nearly indistinguishable from real echoCG images,making it a promising tool for augmenting medical datasets.However,we also identify limitations in the synthetic images generated by CycleGAN and CUT,which are easily distinguishable as non-realistic by medical professionals.This study highlights the potential of diffusion models in medical imaging and their applicability in addressing data scarcity,while also outlining the areas for future improvement.展开更多
The vast potential of medical big data to enhance healthcare outcomes remains underutilized due to privacy concerns,which restrict cross-center data sharing and the construction of diverse,large-scale datasets.To addr...The vast potential of medical big data to enhance healthcare outcomes remains underutilized due to privacy concerns,which restrict cross-center data sharing and the construction of diverse,large-scale datasets.To address this challenge,we developed a deep generative model aimed at synthesizing medical data to overcome data sharing barriers,with a focus on breast ultrasound(US)image synthesis.Specifically,we introduce CoLDiT,a conditional latent diffusion model with a transformer backbone,to generate US images of breast lesions across various Breast Imaging Reporting and Data System(BI-RADS)categories.Using a training dataset of 9,705 US images from 5,243 patients across 202 hospitals with diverse US systems,CoLDiT generated breast US images without duplicating private information,as confirmed through nearest-neighbor analysis.Blinded reader studies further validated the realism of these images,with area under the receiver operating characteristic curve(AUC)scores ranging from 0.53 to 0.77.Additionally,synthetic breast US images effectively augmented the training dataset for BI-RADS classification,achieving performance comparable to that using an equal-sized training set comprising solely real images(P=0.81 for AUC).Our findings suggest that synthetic data,such as CoLDiT-generated images,offer a viable,privacy-preserving solution to facilitate secure medical data sharing and advance the utilization of medical big data.展开更多
基金supported by the CRSRI Open Research Program(grant No.CKWV20241179/KY)Postdoctoral Fellowship Program of CPSF(grant No.GZC20230901)+2 种基金China Postdoctoral Science Foundation(grant No.2023M741267)Department of Science and Technology of Hubei Province(grant No.2023AFB578)National Key R&D Program of China(grant No.2023YFC3804500).
文摘In this study, advanced image processing technology is used to analyze the three-dimensional sand composite image, and the topography features of sand particles are successfully extracted and saved as high-quality image files. These image files were then trained using the latent diffusion model (LDM) to generate a large number of sand particles with real morphology, which were then applied to numerical studies. The effects of particle morphology on the macroscopic mechanical behavior and microscopic energy evolution of sand under complex stress paths were studied in detail, combined with the circular and elliptical particles widely used in current tests. The results show that with the increase of the irregularity of the sample shape, the cycle period and radius of the closed circle formed by the partial strain curve gradually decrease, and the center of the circle gradually shifts. In addition, the volume strain and liquefaction strength of sand samples increase with the increase of particle shape irregularity. It is particularly noteworthy that obvious vortex structures exist in the positions near the center where deformation is severe in the samples of circular and elliptical particles. However, such structures are difficult to be directly observed in sample with irregular particles. This phenomenon reveals the influence of particle morphology on the complexity of the mechanical behavior of sand, providing us with new insights into the understanding of the response mechanism of sand soil under complex stress conditions.
基金funded by the Science Committee of the Ministry of Science and Higher Education of the Republic of Kazakhstan(Grant No.AP13068032-Development of Methods and Algorithms for Machine Learning for Predicting Pathologies of the Cardiovascular System Based on Echocardiography and Electrocardiography).
文摘The applications of machine learning(ML)in the medical domain are often hindered by the limited availability of high-quality data.To address this challenge,we explore the synthetic generation of echocardiography images(echoCG)using state-of-the-art generative models.We conduct a comprehensive evaluation of three prominent methods:Cycle-consistent generative adversarial network(CycleGAN),Contrastive Unpaired Translation(CUT),and Stable Diffusion 1.5 with Low-Rank Adaptation(LoRA).Our research presents the data generation methodol-ogy,image samples,and evaluation strategy,followed by an extensive user study involving licensed cardiologists and surgeons who assess the perceived quality and medical soundness of the generated images.Our findings indicate that Stable Diffusion outperforms both CycleGAN and CUT in generating images that are nearly indistinguishable from real echoCG images,making it a promising tool for augmenting medical datasets.However,we also identify limitations in the synthetic images generated by CycleGAN and CUT,which are easily distinguishable as non-realistic by medical professionals.This study highlights the potential of diffusion models in medical imaging and their applicability in addressing data scarcity,while also outlining the areas for future improvement.
基金supported by the National Natural Science Foundation of China(grant no.82071928)the Program of Shanghai Academic/Technology Research Leader(grant no.23XD1401300).
文摘The vast potential of medical big data to enhance healthcare outcomes remains underutilized due to privacy concerns,which restrict cross-center data sharing and the construction of diverse,large-scale datasets.To address this challenge,we developed a deep generative model aimed at synthesizing medical data to overcome data sharing barriers,with a focus on breast ultrasound(US)image synthesis.Specifically,we introduce CoLDiT,a conditional latent diffusion model with a transformer backbone,to generate US images of breast lesions across various Breast Imaging Reporting and Data System(BI-RADS)categories.Using a training dataset of 9,705 US images from 5,243 patients across 202 hospitals with diverse US systems,CoLDiT generated breast US images without duplicating private information,as confirmed through nearest-neighbor analysis.Blinded reader studies further validated the realism of these images,with area under the receiver operating characteristic curve(AUC)scores ranging from 0.53 to 0.77.Additionally,synthetic breast US images effectively augmented the training dataset for BI-RADS classification,achieving performance comparable to that using an equal-sized training set comprising solely real images(P=0.81 for AUC).Our findings suggest that synthetic data,such as CoLDiT-generated images,offer a viable,privacy-preserving solution to facilitate secure medical data sharing and advance the utilization of medical big data.
