Search

In pathology, the rarity of certain diseases and the complexity in annotating pathological images significantly hinder the creation of extensive, high-quality datasets. This limitation impedes the progress of deep learning-assisted diagnostic systems in pathology. Consequently, it becomes imperative to devise a technology that can discern new disease categories from a minimal number of annotated examples. Such a technology would substantially advance deep learning models for rare diseases. Addressing this need, we introduce the Dual-channel Prototype Network (DCPN), rooted in the few-shot learning paradigm, to tackle the challenge of classifying pathological images with limited samples. DCPN augments the Pyramid Vision Transformer (PVT) framework for few-shot classification via self-supervised learning and integrates it with convolutional neural networks. This combination forms a dual-channel architecture that extracts multi-scale, highly precise pathological features. The approach enhances the versatility of prototype representations and elevates the efficacy of prototype networks in few-shot pathological image classification tasks. We evaluated DCPN using three publicly available pathological datasets, configuring small-sample classification tasks that mirror varying degrees of clinical scenario domain shifts. Our experimental findings robustly affirm DCPN's superiority in few-shot pathological image classification, particularly in tasks within the same domain, where it achieves the benchmarks of supervised learning.

This study verified the effectiveness of Donald Trump's Twitter campaign in guiding agen-da-setting and deflecting political risk and examined Trump's Twitter communication strategy and explores the communication effects of his tweet content during Covid-19 pandemic. We collected all tweets posted by Trump on the Twitter platform from January 1, 2020 to December 31, 2020.We used Ordinary Least Squares (OLS) regression analysis with a fixed effects model to analyze the existence of the Twitter strategy. The correlation between the number of con-firmed daily Covid-19 diagnoses and the number of particular thematic tweets was investigated using time series analysis. Empirical analysis revealed Twitter's strategy is used to divert public attention from negative Covid-19 reports during the epidemic, and it posts a powerful political communication effect on Twitter. However, findings suggest that Trump did not use false claims to divert political risk and shape public opinion., Comment: 14 pages, 6 tables

Based on digital pathology slice scanning technology, artificial intelligence algorithms represented by deep learning have achieved remarkable results in the field of computational pathology. Compared to other medical images, pathology images are more difficult to annotate, and thus, there is an extreme lack of available datasets for conducting supervised learning to train robust deep learning models. In this paper, we propose a self-supervised learning (SSL) model, the global contrast-masked autoencoder (GCMAE), which can train the encoder to have the ability to represent local-global features of pathological images, also significantly improve the performance of transfer learning across data sets. In this study, the ability of the GCMAE to learn migratable representations was demonstrated through extensive experiments using a total of three different disease-specific hematoxylin and eosin (HE)-stained pathology datasets: Camelyon16, NCTCRC and BreakHis. In addition, this study designed an effective automated pathology diagnosis process based on the GCMAE for clinical applications. The source code of this paper is publicly available at https://github.com/StarUniversus/gcmae.

The deep neural network is a research hotspot for histopathological image analysis, which can improve the efficiency and accuracy of diagnosis for pathologists or be used for disease screening. The whole slide pathological image can reach one gigapixel and contains abundant tissue feature information, which needs to be divided into a lot of patches in the training and inference stages. This will lead to a long convergence time and large memory consumption. Furthermore, well-annotated data sets are also in short supply in the field of digital pathology. Inspired by the pathologist's clinical diagnosis process, we propose a weakly supervised deep reinforcement learning framework, which can greatly reduce the time required for network inference. We use neural network to construct the search model and decision model of reinforcement learning agent respectively. The search model predicts the next action through the image features of different magnifications in the current field of view, and the decision model is used to return the predicted probability of the current field of view image. In addition, an expert-guided model is constructed by multi-instance learning, which not only provides rewards for search model, but also guides decision model learning by the knowledge distillation method. Experimental results show that our proposed method can achieve fast inference and accurate prediction of whole slide images without any pixel-level annotations.

The feature extraction methods of radiomics are mainly based on static tomographic images at a certain moment, while the occurrence and development of disease is a dynamic process that cannot be fully reflected by only static characteristics. This study proposes a new dynamic radiomics feature extraction workflow that uses time-dependent tomographic images of the same patient, focuses on the changes in image features over time, and then quantifies them as new dynamic features for diagnostic or prognostic evaluation. We first define the mathematical paradigm of dynamic radiomics and introduce three specific methods that can describe the transformation process of features over time. Three different clinical problems are used to validate the performance of the proposed dynamic feature with conventional 2D and 3D static features., Comment: Appl Intell (2022)

Background: An increasing number of studies reported that exogenous miRNAs (xenomiRs) can be detected in animal bodies, however, some others reported negative results. Some attributed this divergence to the selective absorption of plant-derived xenomiRs by animals. Results: Here, we analyzed 166 plant-derived xenomiRs reported in our previous study and 942 non-xenomiRs extracted from miRNA expression profiles of four species of commonly consumed plants. Employing statistics analysis and cluster analysis, our study revealed the potential sequence specificity of plant-derived xenomiRs. Furthermore, a random forest model and a one-dimensional convolutional neural network model were trained using miRNA sequence features and raw miRNA sequences respectively and then employed to predict unlabeled plant miRNAs in miRBase. A total of 241 possible plant-derived xenomiRs were predicted by both models. Finally, the potential functions of these possible plant-derived xenomiRs along with our previously reported ones in human body were analyzed. Conclusions: Our study, for the first time, presents the systematic plant-derived xenomiR sequences analysis and provides evidence for selective absorption of plant miRNA by human body, which could facilitate the future investigation about the mechanisms underlying the transference of plant-derived xenomiR., SCOPUS: ar.j, info:eu-repo/semantics/published

BaNi2As2, with a first-order phase transition around 131 K, is studied by the angle-resolved photoemission spectroscopy. The measured electronic structure is compared to the local-density approximation calculations, revealing similar large electronlike bands around M? and differences along Γ̄-X̄. We further show that the electronic structure of BaNi2As2 is distinct from that of the sibling iron pnictides. Particularly, there is no signature of band folding, indicating no collinear spin-density-wave-related magnetic ordering. Moreover, across the strong first-order phase transition, the band shift exhibits a hysteresis, which is directly related to the significant lattice distortion in BaNi 2As2. © 2011 The American Physical Society.

The electronic band structure and Fermi surface of ZrTe3 was determined by angle-resolved photoemission spectroscopy. Several bands and a large part of the Fermi surface are found to be split by 100–200 meV into two parallel dispersions. Calculations of the bulk band structure cannot reproduce this splitting even if spin-orbit interaction is taken into account. A bilayer model representing the top layers of a surface-relaxed structure without reconstruction introduces the observed splitting and reproduces most features observed in the data thus suggesting a surface relaxation of the freshly cleaved ZrTe3. The dispersion of the highly nested small electron pocket that gives rise to the charge density wave is traceable even in the low-temperature gapped state and the gap energy is determined as εg=65±10 meV.

We present electrical resistivity (ρ) measurements for the intercalation compound Fex TiSe2 (0≤x<0.16) over the temperature range from 4.2 to 300 K, and angle-resolved photoemission spectra for x=0, 0.05, and 0.14 at 50 and 250 K (or 280 K). At 250 K, TiSe2 is a semimetal having hole pockets centered at the Γ point and electron pockets around the L points of the Brillouin zone. Upon intercalation, Fe-derived flat bands appear just below the Fermi energy, and the Se 4p derived bands forming hole pockets at the Γ point are lowered. At 50 K, band folding due to 2a×2a×2c superlattice is observed clearly near the L point for the host and x=0.05, while it vanishes for x=0.14, consistent with the ρ-T data. The critical concentration for the suppression of the superstructure (0.05< xc ≤0.075) can be explained reasonably well by the percolation threshold of a two-dimensional-trianglar lattice consisting of seven Ti atoms, which is estimated to 1 14 (=0.0714).

We have examined core-level photoemission spectra of 1T-TiSe2 and 1T-TaS2 to study chemical shifts associated with unusual superlattice formation. While large temperature-dependent core-level splitting was observed for TaS2, temperature-dependent chemical shift was not observed for TiSe2. On the other hand, angle-resolved valence-band photoemission spectra of TiSe2 showed appearance of a new branch (band-folding) at the L points in the ordered phase at 50 K. These results suggest smaller lattice distortion in TiSe2 than that in TaS2.

We have examined core-level photoemission spectra of 1T-TiSe2 and 1T-TaS2 to study chemical shifts associated with unusual superlattice formation. While large temperature-dependent core-level splitting was observed for TaS2, temperature-dependent chemical shift was not observed for TiSe2. On the other hand, angle-resolved valence-band photoemission spectra of TiSe2 showed appearance of a new branch (band-folding) at the L points in the ordered phase at 50 K. These results suggest smaller lattice distortion in TiSe2 than that in TaS2.

type:text, We have examined core-level photoemission spectra of 1T-TiSe2 and 1T-TaS2 to study chemical shifts associated with unusual superlattice formation. While large temperature-dependent core-level splitting was observed for TaS2, temperature-dependent chemical shift was not observed for TiSe2. On the other hand, angle-resolved valence-band photoemission spectra of TiSe2 showed appearance of a new branch (band-folding) at the L points in the ordered phase at 50 K. These results suggest smaller lattice distortion in TiSe2 than that in TaS2.

We have examined core-level photoemission spectra of 1T-TiSe2 and 1T-TaS2 to study chemical shifts associated with unusual superlattice formation. While large temperature-dependent core-level splitting was observed for TaS2, temperature-dependent chemical shift was not observed for TiSe2. On the other hand, angle-resolved valence-band photoemission spectra of TiSe2 showed appearance of a new branch (band-folding) at the L points in the ordered phase at 50 K. These results suggest smaller lattice distortion in TiSe2 than that in TaS2.

High-resolution angle-resolved photoelectron spectroscopy of ferromagnetic Ni(110) has been conducted to elucidate energy band and spin-dependent many-body interactions. A kink structure has been clearly observed in the energy band dispersions of the minority spin Σ2↓ and Σ1↓, while it is absent in the majority spin Σ1↑ band. Analyses of the self-energy indicate that the kink originates from the electron-phonon interaction. Based on a detailed study of the effective mass enhancement, we find that the electron-phonon interaction and electron correlation contribute to the spectral features near the Fermi level in different ways, depending on the identity of the energy band and the spin direction. These results provide insight into the interplay of these many-body interactions on quasiparticles near the Fermi level.

We present detailed energy dispersions near the Fermi level on the monolayer perovskite ruthenate Sr2RuO4, determined by high-resolution angle-resolved photoemission spectroscopy. An orbital selectivity of the kink in the dispersion of Sr2RuO4 has been found: A kink for the Ru 4dxy orbital is clearly observed, but not for the Ru 4dyz and 4dzx ones. The result provides insight into the origin of the kink.

We present detailed energy dispersions near the Fermi level on the monolayer perovskite ruthenate Sr2RuO4, determined by high-resolution angle-resolved photoemission spectroscopy. An orbital selectivity of the kink in the dispersion of Sr2RuO4 has been found: A kink for the Ru 4dxy orbital is clearly observed, but not for the Ru 4dyz and 4dzx ones. The result provides insight into the origin of the kink.

Finite Element Method (FEM) provides a powerful tool to study mechanical behavior of prostheses as well as prosthesis design, yet in most cases of long bone, approximated models are applied for the job. Better results demand more accurate description of the model. In this practice, a system is designed and implemented to reconstruct a 3 dimensional model of bones from computer tomographical (CT) images with direct interfacing facility with other CAD and Finite Element Analysis systems. Several practical schemes of 3D reconstruction are discussed and implemented. Experiments were performed on both synthetic and real CT images to evaluate the system. The bone model together with the prosthetic interface model, which can also be created from the system upon preprocessing of the bone cross-sectional images, is then analyzed the using Finite Element method. Optimized prosthetic structures are introduced upon analytical results. FE analyses of the optimized designs are practiced. The tibia of a goat is taken as the subject of study; the whole process as well as the results is intended to be referred to as an explorative fulfillment for prosthesis structure analysis and design.

Finite Element Method (FEM) provides a powerful tool to study mechanical behavior of prostheses as well as prosthesis design, yet in most cases of long bone, approximated models are applied for the job. Better results demand more accurate description of the model. In this practice, a system is designed and implemented to reconstruct a 3 dimensional model of bones from computer tomographical (CT) images with direct interfacing facility with other CAD and Finite Element Analysis systems. Several practical schemes of 3D reconstruction are discussed and implemented. Experiments were performed on both synthetic and real CT images to evaluate the system. The bone model together with the prosthetic interface model, which can also be created from the system upon preprocessing of the bone cross-sectional images, is then analyzed the using Finite Element method. Optimized prosthetic structures are introduced upon analytical results. FE analyses of the optimized designs are practiced. The tibia of a goat is taken as the subject of study; the whole process as well as the results is intended to be referred to as an explorative fulfillment for prosthesis structure analysis and design.

We present detailed energy dispersions near the Fermi level on the monolayer perovskite ruthenate Sr2RuO4, determined by high-resolution angle-resolved photoemission spectroscopy. An orbital selectivity of the kink in the dispersion of Sr2RuO4 has been found: A kink for the Ru 4dxy orbital is clearly observed, but not for the Ru 4dyz and 4dzx ones. The result provides insight into the origin of the kink.