Ultrasound (US) has become one of the most commonly performed imaging modalities in clinical practice. It is a rapidly evolving technology with certain advantages and with unique challenges that include low imaging qu...Ultrasound (US) has become one of the most commonly performed imaging modalities in clinical practice. It is a rapidly evolving technology with certain advantages and with unique challenges that include low imaging quality and high variability. From the perspective of image analysis, it is essential to develop advanced automatic US image analysis methods to assist in US diagnosis and/or to make such assessment more objective and accurate. Deep learning has recently emerged as the leading machine learning tool in various research fields, and especially in general imaging analysis and computer vision. Deep learning also shows huge potential for various automatic US image analysis tasks. This review first briefly introduces several popular deep learning architectures, and then summarizes and thoroughly discusses their applications in various specific tasks in US image analysis, such as classification, detection, and segmentation. Finally, the open challenges and potential trends of the future application of deep learning in medical US image analysis are discussed.展开更多
Thermal conductivity is an important material parameter of silicon when studying the performance and reliability of devices or for guiding circuit design when considering heat dissipation, especially when the self-hea...Thermal conductivity is an important material parameter of silicon when studying the performance and reliability of devices or for guiding circuit design when considering heat dissipation, especially when the self-heating effect becomes prominent in ultra-scaled MOSFETs.The cross-plane thermal conductivity of a thin silicon film is lacking due to the difficulty in sensing high thermal conductivity in the vertical direction.In this paper, a feasible method that utilizes an ultra-fast electrical pulse within 20 μs combined with the hot strip technique is adopted.To the best of our knowledge, this is the first work that shows how to extract the cross-plane thermal conductivity of sub-50 nm(30 nm, 17 nm, and 10 nm)silicon films on buried oxide.The ratio of the extracted cross-plane thermal conductivity of the silicon films over the bulk value is only about 6.9%, 4.3%, and 3.8% at 300 K, respectively.As the thickness of the films is smaller than the phonon mean free path, the classical heat transport theory fails to predict the heat dissipation in nanoscale transistors.Thus, in this study, a ballistic model, derived from the heat transport equation based on extended-irreversible-hydrodynamics(EIT), is used for further investigation, and the simulation results exhibit good consistence with the experimental data.The extracted effective thermal data could provide a good reference for precise device simulations and thermoelectric applications.展开更多
Epithelial and stromal tissues are components of the tumor microenvironment and play a major role in tumor initiation and progression.Distinguishing stroma from epithelial tissues is critically important for spatial c...Epithelial and stromal tissues are components of the tumor microenvironment and play a major role in tumor initiation and progression.Distinguishing stroma from epithelial tissues is critically important for spatial characterization of the tumor microenvironment.Here,we propose BrcaSeg,an image analysis pipeline based on a convolutional neural network(CNN)model to classify epithelial and stromal regions in whole-slide hematoxylin and eosin(H&E)stained histopathological images.The CNN model is trained using well-annotated breast cancer tissue microarrays and validated with images from The Cancer Genome Atlas(TCGA)Program.BrcaSeg achieves a classification accuracy of 91.02%,which outperforms other state-of-the-art methods.Using this model,we generate pixel-level epithelial/stromal tissue maps for 1000 TCGA breast cancer slide images that are paired with gene expression data.We subsequently estimate the epithelial and stromal ratios and perform correlation analysis to model the relationship between gene expression and tissue ratios.Gene Ontology(GO)enrichment analyses of genes that are highly correlated with tissue ratios suggest that the same tissue is associated with similar biological processes in different breast cancer subtypes,whereas each subtype also has its own idiosyncratic biological processes governing the development of these tissues.Taken all together,our approach can lead to new insights in exploring relationships between image-based phenotypes and their underlying genomic events and biological processes for all types of solid tumors.BrcaSeg can be accessed at https://github.com/Serian1992/ImgBio.展开更多
基金the National Natural Science Foundation of China (61571304, 81571758, and 61701312)the National Key Research and Development Program of China (2016YFC0104703)+1 种基金the Medical Scientific Research Foundation of Guangdong Province, China (B2018031)the Shenzhen Peacock Plan (KQTD2016053112051497).
文摘Ultrasound (US) has become one of the most commonly performed imaging modalities in clinical practice. It is a rapidly evolving technology with certain advantages and with unique challenges that include low imaging quality and high variability. From the perspective of image analysis, it is essential to develop advanced automatic US image analysis methods to assist in US diagnosis and/or to make such assessment more objective and accurate. Deep learning has recently emerged as the leading machine learning tool in various research fields, and especially in general imaging analysis and computer vision. Deep learning also shows huge potential for various automatic US image analysis tasks. This review first briefly introduces several popular deep learning architectures, and then summarizes and thoroughly discusses their applications in various specific tasks in US image analysis, such as classification, detection, and segmentation. Finally, the open challenges and potential trends of the future application of deep learning in medical US image analysis are discussed.
基金Project supported by the Zhejiang Provincial Natural Science Foundation of China(Grant No.LZ19F040001)the National Natural Science Foundation of China(Grant No.61473287)the NSFC–Zhejiang Joint Fund for the Integration of Industrialization Informatization,China(Grant No.U1609213)
文摘Thermal conductivity is an important material parameter of silicon when studying the performance and reliability of devices or for guiding circuit design when considering heat dissipation, especially when the self-heating effect becomes prominent in ultra-scaled MOSFETs.The cross-plane thermal conductivity of a thin silicon film is lacking due to the difficulty in sensing high thermal conductivity in the vertical direction.In this paper, a feasible method that utilizes an ultra-fast electrical pulse within 20 μs combined with the hot strip technique is adopted.To the best of our knowledge, this is the first work that shows how to extract the cross-plane thermal conductivity of sub-50 nm(30 nm, 17 nm, and 10 nm)silicon films on buried oxide.The ratio of the extracted cross-plane thermal conductivity of the silicon films over the bulk value is only about 6.9%, 4.3%, and 3.8% at 300 K, respectively.As the thickness of the films is smaller than the phonon mean free path, the classical heat transport theory fails to predict the heat dissipation in nanoscale transistors.Thus, in this study, a ballistic model, derived from the heat transport equation based on extended-irreversible-hydrodynamics(EIT), is used for further investigation, and the simulation results exhibit good consistence with the experimental data.The extracted effective thermal data could provide a good reference for precise device simulations and thermoelectric applications.
基金supported by Indiana University Precision Health Initiative to KH and JZthe NSFC-Guangdong Joint Fund of China (Grant No. U1501256) to QFShenzhen Peacock Plan (Grant No. KQTD2016053112051497) to XZ and ND.
文摘Epithelial and stromal tissues are components of the tumor microenvironment and play a major role in tumor initiation and progression.Distinguishing stroma from epithelial tissues is critically important for spatial characterization of the tumor microenvironment.Here,we propose BrcaSeg,an image analysis pipeline based on a convolutional neural network(CNN)model to classify epithelial and stromal regions in whole-slide hematoxylin and eosin(H&E)stained histopathological images.The CNN model is trained using well-annotated breast cancer tissue microarrays and validated with images from The Cancer Genome Atlas(TCGA)Program.BrcaSeg achieves a classification accuracy of 91.02%,which outperforms other state-of-the-art methods.Using this model,we generate pixel-level epithelial/stromal tissue maps for 1000 TCGA breast cancer slide images that are paired with gene expression data.We subsequently estimate the epithelial and stromal ratios and perform correlation analysis to model the relationship between gene expression and tissue ratios.Gene Ontology(GO)enrichment analyses of genes that are highly correlated with tissue ratios suggest that the same tissue is associated with similar biological processes in different breast cancer subtypes,whereas each subtype also has its own idiosyncratic biological processes governing the development of these tissues.Taken all together,our approach can lead to new insights in exploring relationships between image-based phenotypes and their underlying genomic events and biological processes for all types of solid tumors.BrcaSeg can be accessed at https://github.com/Serian1992/ImgBio.