In contemporary computer vision,convolutional neural networks(CNNs)and vision transformers(ViTs)represent the two primary architectural paradigms for image recognition.While both approaches have been widely adopted in...In contemporary computer vision,convolutional neural networks(CNNs)and vision transformers(ViTs)represent the two primary architectural paradigms for image recognition.While both approaches have been widely adopted in medical imaging applications,they operate based on fundamentally different computational principles.This report attempts to provide brief application notes on ViTs and CNNs,particularly focusing on scenarios that guide the selection of one architecture over the other in practical medical implementations.Generally,CNNs rely on convolutional kernels,localized receptive fields,and weight sharing,enabling efficient hierarchical feature extraction.These properties contribute to strong performance in detecting spatially constrained patterns such as textures,edges,and anatomical boundaries,while maintaining relatively low computational requirements.ViTs,on the other hand,decompose images into smaller segments referred to as tokens and employ self-attention mechanisms to model relationships across the entire image.This global modeling capability allows ViTs to capture long-range dependencies that may be difficult for convolution-based architectures to learn.However,ViTs typically achieve optimal performance when trained on extremely large datasets or when supported by extensive pretraining,as their reduced inductive bias requires greater data exposure to learn robust representations.This report briefly examines the architectural structure,underlying mathematical foundations,and relative performance characteristics of CNNs and ViTs,drawing upon recent findings from contemporary research.Emphasis is placed on understanding how differences in data availability,computational resources,and task requirements influence model effectiveness across medical imaging domains.Most importantly,the report serves as a concise application guide for practitioners seeking informed implementation decisions between these two influential deep learning frameworks.展开更多
Objective:To explore the value of multimodal MRI enhancement scanning and diffusion-weighted imaging in differentiating non-puerperal mastitis(NPM)and breast cancer.Methods:From September 2022 to September 2024,56 pat...Objective:To explore the value of multimodal MRI enhancement scanning and diffusion-weighted imaging in differentiating non-puerperal mastitis(NPM)and breast cancer.Methods:From September 2022 to September 2024,56 patients with breast diseases were selected as samples and grouped according to disease type.Twenty-eight patients with breast cancer were included in Group A,and 28 patients with NPM were included in Group B.All patients underwent multimodal MRI enhancement scanning and diffusion-weighted imaging.The MRI results,time-signal intensity curves,ADC values,lesion intensity,and imaging signs were compared between the two groups.Results:There were no significant differences in enhancement characteristics,lymph node enlargement,and margins between Group A and Group B(P>0.05).The proportion of outflow curves in Group A was higher than that in Group B(P<0.05).The ADC value in Group A was lower than that in Group B,and the lesion intensity was higher than that in Group B(P<0.05).There were significant differences in imaging signs,such as abscess or sinus,ascending time-signal curve,and mammary duct dilation between Group A and Group B(P<0.05).Conclusion:Multimodal MRI enhancement scanning and diffusion-weighted imaging techniques can be used to diagnose breast diseases.Comprehensive analysis of time-signal intensity curves,lesion intensity,imaging signs,and ADC values can differentiate between NPM and breast cancer.展开更多
This study proposes a multi-scale simplified residual convolutional neural network(MS-SRCNN)for the precise prediction of Mg-Nd binary alloy compositions from scanning electron microscope(SEM)images.A multi-scale data...This study proposes a multi-scale simplified residual convolutional neural network(MS-SRCNN)for the precise prediction of Mg-Nd binary alloy compositions from scanning electron microscope(SEM)images.A multi-scale data structure is established by spatially aligning and stacking SEM images at different magnifications.The MS-SRCNN significantly reduces computational runtime by over 90%compared to traditional architectures like ResNet50,VGG16,and VGG19,without compromising prediction accuracy.The model demonstrates more excellent predictive performance,achieving a>5%increase in R^(2) compared to single-scale models.Furthermore,the MS-SRCNN exhibits robust composition prediction capability across other Mg-based binary alloys,including Mg-La,Mg-Sn,Mg-Ce,Mg-Sm,Mg-Ag,and Mg-Y,thereby emphasizing its generalization and extrapolation potential.This research establishes a non-destructive,microstructure-informed composition analysis framework,reduces characterization time compared to traditional experiment methods and provides insights into the composition-microstructure relationship in diverse material systems.展开更多
文摘In contemporary computer vision,convolutional neural networks(CNNs)and vision transformers(ViTs)represent the two primary architectural paradigms for image recognition.While both approaches have been widely adopted in medical imaging applications,they operate based on fundamentally different computational principles.This report attempts to provide brief application notes on ViTs and CNNs,particularly focusing on scenarios that guide the selection of one architecture over the other in practical medical implementations.Generally,CNNs rely on convolutional kernels,localized receptive fields,and weight sharing,enabling efficient hierarchical feature extraction.These properties contribute to strong performance in detecting spatially constrained patterns such as textures,edges,and anatomical boundaries,while maintaining relatively low computational requirements.ViTs,on the other hand,decompose images into smaller segments referred to as tokens and employ self-attention mechanisms to model relationships across the entire image.This global modeling capability allows ViTs to capture long-range dependencies that may be difficult for convolution-based architectures to learn.However,ViTs typically achieve optimal performance when trained on extremely large datasets or when supported by extensive pretraining,as their reduced inductive bias requires greater data exposure to learn robust representations.This report briefly examines the architectural structure,underlying mathematical foundations,and relative performance characteristics of CNNs and ViTs,drawing upon recent findings from contemporary research.Emphasis is placed on understanding how differences in data availability,computational resources,and task requirements influence model effectiveness across medical imaging domains.Most importantly,the report serves as a concise application guide for practitioners seeking informed implementation decisions between these two influential deep learning frameworks.
文摘Objective:To explore the value of multimodal MRI enhancement scanning and diffusion-weighted imaging in differentiating non-puerperal mastitis(NPM)and breast cancer.Methods:From September 2022 to September 2024,56 patients with breast diseases were selected as samples and grouped according to disease type.Twenty-eight patients with breast cancer were included in Group A,and 28 patients with NPM were included in Group B.All patients underwent multimodal MRI enhancement scanning and diffusion-weighted imaging.The MRI results,time-signal intensity curves,ADC values,lesion intensity,and imaging signs were compared between the two groups.Results:There were no significant differences in enhancement characteristics,lymph node enlargement,and margins between Group A and Group B(P>0.05).The proportion of outflow curves in Group A was higher than that in Group B(P<0.05).The ADC value in Group A was lower than that in Group B,and the lesion intensity was higher than that in Group B(P<0.05).There were significant differences in imaging signs,such as abscess or sinus,ascending time-signal curve,and mammary duct dilation between Group A and Group B(P<0.05).Conclusion:Multimodal MRI enhancement scanning and diffusion-weighted imaging techniques can be used to diagnose breast diseases.Comprehensive analysis of time-signal intensity curves,lesion intensity,imaging signs,and ADC values can differentiate between NPM and breast cancer.
基金funded by the National Natural Science Foundation of China(No.52204407)the Natural Science Foundation of Jiangsu Province(No.BK20220595)the China Postdoctoral Science Foundation(No.2022M723689).
文摘This study proposes a multi-scale simplified residual convolutional neural network(MS-SRCNN)for the precise prediction of Mg-Nd binary alloy compositions from scanning electron microscope(SEM)images.A multi-scale data structure is established by spatially aligning and stacking SEM images at different magnifications.The MS-SRCNN significantly reduces computational runtime by over 90%compared to traditional architectures like ResNet50,VGG16,and VGG19,without compromising prediction accuracy.The model demonstrates more excellent predictive performance,achieving a>5%increase in R^(2) compared to single-scale models.Furthermore,the MS-SRCNN exhibits robust composition prediction capability across other Mg-based binary alloys,including Mg-La,Mg-Sn,Mg-Ce,Mg-Sm,Mg-Ag,and Mg-Y,thereby emphasizing its generalization and extrapolation potential.This research establishes a non-destructive,microstructure-informed composition analysis framework,reduces characterization time compared to traditional experiment methods and provides insights into the composition-microstructure relationship in diverse material systems.
