Search

In recent years, an increasing number of passive radiative cooling materials are proposed in the literature, with several examples relying on the use of silica (SiO2) due to its unique stability, non-toxicity, and availability. Nonetheless, due to its bulk phonon-polariton band, SiO2 presents a marked reflection peak within the atmospheric transparency window (8-13 µm), leading to an emissivity decrease that poses a challenge to fulfilling the criteria for sub-ambient passive radiative cooling. Thus, the latest developments in this field are devoted to the design of engineered SiO2 photonic structures, to increase the cooling potential of bulk SiO2 radiative coolers. This review seeks to identify the most effective photonic design and fabrication strategies for SiO2 radiative emitters by evaluating their cooling efficacy, as well as their scalability, providing an in-depth analysis of the fundamental principles, structural models, and results (both numerical and experimental) of various types of SiO2 radiative coolers., The authors thank the National Key Research and Development Program of China (2022YFB3902704), the National Natural Science Foundation of China (No.51702068, 52072096), the Natural Science Foundation of Heilongjang Province (LH2023E034) and the Fundamental Research Funds for the Central Universities (HIT OCEF. 2021004). L.P. and J.J.F. acknowledge support from the European project PaRaMetriC, code 21GRD03. The project 21GRD03 PaRaMetriC received funding from the European Partnership on Metrology, co-financed by the European Union’s Horizon Europe Research and Innovation Programme, and from the Participating States. Open Access Funding provided by Istituto Nazionale di Ricerca Metrologica within the CRUI-CARE Agreement., Peer Reviewed, Postprint (published version)

Accurate image classification and retrieval are of importance for clinical diagnosis and treatment decision-making. The recent contrastive language-image pretraining (CLIP) model has shown remarkable proficiency in understanding natural images. Drawing inspiration from CLIP, PathCLIP is specifically designed for pathology image analysis, utilizing over 200,000 image and text pairs in training. While the performance the PathCLIP is impressive, its robustness under a wide range of image corruptions remains unknown. Therefore, we conduct an extensive evaluation to analyze the performance of PathCLIP on various corrupted images from the datasets of Osteosarcoma and WSSS4LUAD. In our experiments, we introduce seven corruption types including brightness, contrast, Gaussian blur, resolution, saturation, hue, and markup at four severity levels. Through experiments, we find that PathCLIP is relatively robustness to image corruptions and surpasses OpenAI-CLIP and PLIP in zero-shot classification. Among the seven corruptions, blur and resolution can cause server performance degradation of the PathCLIP. This indicates that ensuring the quality of images is crucial before conducting a clinical test. Additionally, we assess the robustness of PathCLIP in the task of image-image retrieval, revealing that PathCLIP performs less effectively than PLIP on Osteosarcoma but performs better on WSSS4LUAD under diverse corruptions. Overall, PathCLIP presents impressive zero-shot classification and retrieval performance for pathology images, but appropriate care needs to be taken when using it. We hope this study provides a qualitative impression of PathCLIP and helps understand its differences from other CLIP models.

Multi-modal Learning has attracted widespread attention in medical image analysis. Using multi-modal data, whole slide images (WSIs) and clinical information, can improve the performance of deep learning models in the diagnosis of axillary lymph node metastasis. However, clinical information is not easy to collect in clinical practice due to privacy concerns, limited resources, lack of interoperability, etc. Although patient selection can ensure the training set to have multi-modal data for model development, missing modality of clinical information can appear during test. This normally leads to performance degradation, which limits the use of multi-modal models in the clinic. To alleviate this problem, we propose a bidirectional distillation framework consisting of a multi-modal branch and a single-modal branch. The single-modal branch acquires the complete multi-modal knowledge from the multi-modal branch, while the multi-modal learns the robust features of WSI from the single-modal. We conduct experiments on a public dataset of Lymph Node Metastasis in Early Breast Cancer to validate the method. Our approach not only achieves state-of-the-art performance with an AUC of 0.861 on the test set without missing data, but also yields an AUC of 0.842 when the rate of missing modality is 80\%. This shows the effectiveness of the approach in dealing with multi-modal data and missing modality. Such a model has the potential to improve treatment decision-making for early breast cancer patients who have axillary lymph node metastatic status.

Lei Zhang,1,* Honglin Li,1,* Liang Zhang,2 Zhihui Zu,1 Dinglin Xu,1 Jianwei Zhang1,2 1The First Clinical College, Shandong University of Traditional Chinese Medicine, Jinan, People’s Republic of China; 2Gynecology, Obstetrics and Reproductive Center, Affiliated Hospital of Shandong University of Traditional Chinese Medicine, Jinan, People’s Republic of China*These authors contributed equally to this workCorrespondence: Jianwei Zhang, Affiliated Hospital of Shandong University of Traditional Chinese Medicine, 42, Wenhua West Road, Jinan, Shandong Province, People’s Republic of China, Tel +8653168901404, Email zhangjianwei1970@sina.comPurpose: Yangjing Zhongyu Tang (YJZYT) is a classic Chinese prescription for infertility treatment and exerts therapeutic effects via activity on the thin endometrium (TE). However, the major components and underlying mechanisms of YJZYT actions remain to be established. The main objectives of this study were to clarify the effects of YJZYT on the TE and provide insights into the related mechanisms based on network pharmacology and molecular docking analyses.Methods: Network pharmacology was employed to explore the main bioactive components and targets of YJZYT. TE-related genes were obtained from the Genecards database and screened for intersections with YJZYT. The Cytoscape 3.8.2 was used to build a “compounds-disease-targets” network and molecular docking analysis performed on key targets. The mechanism of action of YJZYT was further validated in vivo using a rat model.Results: A total of 98 YJZYT active ingredients, 2409 thin endometrium-associated genes, and 186 common targets were obtained. Through topological analysis, 10 core objectives were screened. Data from the PPI network suggest that AKT1, TNF, VEGFA, IL-6, TP53, INS, ESR1, MMP9, ALB, and ACTB serve as key targets in the action of YJZYT on TE. PI3K-Akt, TNF, apoptosis, IL-17 and MAPK were established as the main functional pathways. Molecul

While Multiple Instance Learning (MIL) has shown promising results in digital Pathology Whole Slide Image (WSI) classification, such a paradigm still faces performance and generalization problems due to challenges in high computational costs on Gigapixel WSIs and limited sample size for model training. To deal with the computation problem, most MIL methods utilize a frozen pretrained model from ImageNet to obtain representations first. This process may lose essential information owing to the large domain gap and hinder the generalization of model due to the lack of image-level training-time augmentations. Though Self-supervised Learning (SSL) proposes viable representation learning schemes, the improvement of the downstream task still needs to be further explored in the conversion from the task-agnostic features of SSL to the task-specifics under the partial label supervised learning. To alleviate the dilemma of computation cost and performance, we propose an efficient WSI fine-tuning framework motivated by the Information Bottleneck theory. The theory enables the framework to find the minimal sufficient statistics of WSI, thus supporting us to fine-tune the backbone into a task-specific representation only depending on WSI-level weak labels. The WSI-MIL problem is further analyzed to theoretically deduce our fine-tuning method. Our framework is evaluated on five pathology WSI datasets on various WSI heads. The experimental results of our fine-tuned representations show significant improvements in both accuracy and generalization compared with previous works. Source code will be available at https://github.com/invoker-LL/WSI-finetuning., Comment: Accepted to CVPR 2023

Point-based cell detection (PCD), which pursues high-performance cell sensing under low-cost data annotation, has garnered increased attention in computational pathology community. Unlike mainstream PCD methods that rely on intermediate density map representations, the Point-to-Point network (P2PNet) has recently emerged as an end-to-end solution for PCD, demonstrating impressive cell detection accuracy and efficiency. Nevertheless, P2PNet is limited to decoding from a single-level feature map due to the scale-agnostic property of point proposals, which is insufficient to leverage multi-scale information. Moreover, the spatial distribution of pre-set point proposals is biased from that of cells, leading to inaccurate cell localization. To lift these limitations, we present DPA-P2PNet in this work. The proposed method directly extracts multi-scale features for decoding according to the coordinates of point proposals on hierarchical feature maps. On this basis, we further devise deformable point proposals to mitigate the positional bias between proposals and potential cells to promote cell localization. Inspired by practical pathological diagnosis that usually combines high-level tissue structure and low-level cell morphology for accurate cell classification, we propose a multi-field-of-view (mFoV) variant of DPA-P2PNet to accommodate additional large FoV images with tissue information as model input. Finally, we execute the first self-supervised pre-training on immunohistochemistry histopathology image data and evaluate the suitability of four representative self-supervised methods on the PCD task. Experimental results on three benchmarks and a large-scale and real-world interval dataset demonstrate the superiority of our proposed models over the state-of-the-art counterparts. Codes and pre-trained weights will be available.

As advances in large language models (LLMs) and multimodal techniques continue to mature, the development of general-purpose multimodal large language models (MLLMs) has surged, offering significant applications in interpreting natural images. However, the field of pathology has largely remained untapped, particularly in gathering high-quality data and designing comprehensive model frameworks. To bridge the gap in pathology MLLMs, we present PathAsst, a multimodal generative foundation AI assistant to revolutionize diagnostic and predictive analytics in pathology. The development of PathAsst involves three pivotal steps: data acquisition, CLIP model adaptation, and the training of PathAsst's multimodal generative capabilities. Firstly, we collect over 207K high-quality pathology image-text pairs from authoritative sources. Leveraging the advanced power of ChatGPT, we generate over 180K instruction-following samples. Furthermore, we devise additional instruction-following data specifically tailored for invoking eight pathology-specific sub-models we prepared, allowing the PathAsst to effectively collaborate with these models, enhancing its diagnostic ability. Secondly, by leveraging the collected data, we construct PathCLIP, a pathology-dedicated CLIP, to enhance PathAsst's capabilities in interpreting pathology images. Finally, we integrate PathCLIP with the Vicuna-13b and utilize pathology-specific instruction-tuning data to enhance the multimodal generation capacity of PathAsst and bolster its synergistic interactions with sub-models. The experimental results of PathAsst show the potential of harnessing AI-powered generative foundation model to improve pathology diagnosis and treatment processes., Comment: 9 pages, 7 figures

Whole slide images are the foundation of digital pathology for the diagnosis and treatment of carcinomas. Writing pathology reports is laborious and error-prone for inexperienced pathologists. To reduce the workload and improve clinical automation, we investigate how to generate pathology reports given whole slide images. On the data end, we curated the largest WSI-text dataset (TCGA-PathoText). In specific, we collected nearly 10000 high-quality WSI-text pairs for visual-language models by recognizing and cleaning pathology reports which narrate diagnostic slides in TCGA. On the model end, we propose the multiple instance generative model (MI-Gen) which can produce pathology reports for gigapixel WSIs. We benchmark our model on the largest subset of TCGA-PathoText. Experimental results show our model can generate pathology reports which contain multiple clinical clues and achieve competitive performance on certain slide-level tasks. We observe that simple semantic extraction from the pathology reports can achieve the best performance (0.838 of F1 score) on BRCA subtyping surpassing previous state-of-the-art approaches. Our collected dataset and related code are available.

Nucleus instance segmentation in histology images is crucial for a broad spectrum of clinical applications. Current dominant algorithms rely on regression of nuclear proxy maps. Distinguishing nucleus instances from the estimated maps requires carefully curated post-processing, which is error-prone and parameter-sensitive. Recently, the Segment Anything Model (SAM) has earned huge attention in medical image segmentation, owing to its impressive generalization ability and promptable property. Nevertheless, its potential on nucleus instance segmentation remains largely underexplored. In this paper, we present a novel prompt-driven framework that consists of a nucleus prompter and SAM for automatic nucleus instance segmentation. Specifically, the prompter learns to generate a unique point prompt for each nucleus while the SAM is fine-tuned to output the corresponding mask for the prompted nucleus. Furthermore, we propose the inclusion of adjacent nuclei as negative prompts to enhance the model's capability to identify overlapping nuclei. Without complicated post-processing, our proposed method sets a new state-of-the-art performance on three challenging benchmarks. Code is available at \url{github.com/windygoo/PromptNucSeg}, Comment: under review

Histopathology image analysis is the golden standard of clinical diagnosis for Cancers. In doctors daily routine and computer-aided diagnosis, the Whole Slide Image (WSI) of histopathology tissue is used for analysis. Because of the extremely large scale of resolution, previous methods generally divide the WSI into a large number of patches, then aggregate all patches within a WSI by Multi-Instance Learning (MIL) to make the slide-level prediction when developing computer-aided diagnosis tools. However, most previous WSI-MIL models using global-attention without pairwise interaction and any positional information, or self-attention with absolute position embedding can not well handle shape varying large WSIs, e.g. testing WSIs after model deployment may be larger than training WSIs, since the model development set is always limited due to the difficulty of histopathology WSIs collection. To deal with the problem, in this paper, we propose to amend position embedding for shape varying long-contextual WSI by introducing Linear Bias into Attention, and adapt it from 1-d long sequence into 2-d long-contextual WSI which helps model extrapolate position embedding to unseen or under-fitted positions. We further utilize Flash-Attention module to tackle the computational complexity of Transformer, which also keep full self-attention performance compared to previous attention approximation work. Our method, Long-contextual MIL (Long-MIL) are evaluated on extensive experiments including 4 dataset including WSI classification and survival prediction tasks to validate the superiority on shape varying WSIs. The source code will be open-accessed soon.

In the application of Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) classification, attention mechanisms often focus on a subset of discriminative instances, which are closely linked to overfitting. To mitigate overfitting, we present Attention-Challenging MIL (ACMIL). ACMIL combines two techniques based on separate analyses for attention value concentration. Firstly, UMAP of instance features reveals various patterns among discriminative instances, with existing attention mechanisms capturing only some of them. To remedy this, we introduce Multiple Branch Attention (MBA) to capture more discriminative instances using multiple attention branches. Secondly, the examination of the cumulative value of Top-K attention scores indicates that a tiny number of instances dominate the majority of attention. In response, we present Stochastic Top-K Instance Masking (STKIM), which masks out a portion of instances with Top-K attention values and allocates their attention values to the remaining instances. The extensive experimental results on three WSI datasets with two pre-trained backbones reveal that our ACMIL outperforms state-of-the-art methods. Additionally, through heatmap visualization and UMAP visualization, this paper extensively illustrates ACMIL's effectiveness in suppressing attention value concentration and overcoming the overfitting challenge. The source code is available at \url{https://github.com/dazhangyu123/ACMIL}., Comment: Under review

Karyotyping is of importance for detecting chromosomal aberrations in human disease. However, chromosomes easily appear curved in microscopic images, which prevents cytogeneticists from analyzing chromosome types. To address this issue, we propose a framework for chromosome straightening, which comprises a preliminary processing algorithm and a generative model called masked conditional variational autoencoders (MC-VAE). The processing method utilizes patch rearrangement to address the difficulty in erasing low degrees of curvature, providing reasonable preliminary results for the MC-VAE. The MC-VAE further straightens the results by leveraging chromosome patches conditioned on their curvatures to learn the mapping between banding patterns and conditions. During model training, we apply a masking strategy with a high masking ratio to train the MC-VAE with eliminated redundancy. This yields a non-trivial reconstruction task, allowing the model to effectively preserve chromosome banding patterns and structure details in the reconstructed results. Extensive experiments on three public datasets with two stain styles show that our framework surpasses the performance of state-of-the-art methods in retaining banding patterns and structure details. Compared to using real-world bent chromosomes, the use of high-quality straightened chromosomes generated by our proposed method can improve the performance of various deep learning models for chromosome classification by a large margin. Such a straightening approach has the potential to be combined with other karyotyping systems to assist cytogeneticists in chromosome analysis.

Cell recognition is a fundamental task in digital histopathology image analysis. Point-based cell recognition (PCR) methods normally require a vast number of annotations, which is extremely costly, time-consuming and labor-intensive. Semi-supervised learning (SSL) can provide a shortcut to make full use of cell information in gigapixel whole slide images without exhaustive labeling. However, research into semi-supervised point-based cell recognition (SSPCR) remains largely overlooked. Previous SSPCR works are all built on density map-based PCR models, which suffer from unsatisfactory accuracy, slow inference speed and high sensitivity to hyper-parameters. To address these issues, end-to-end PCR models are proposed recently. In this paper, we develop a SSPCR framework suitable for the end-to-end PCR models for the first time. Overall, we use the current models to generate pseudo labels for unlabeled images, which are in turn utilized to supervise the models training. Besides, we introduce a co-teaching strategy to overcome the confirmation bias problem that generally exists in self-training. A distribution alignment technique is also incorporated to produce high-quality, unbiased pseudo labels for unlabeled data. Experimental results on four histopathology datasets concerning different types of staining styles show the effectiveness and versatility of the proposed framework. Code is available at \textcolor{magenta}{\url{https://github.com/windygooo/SSPCR}

When designing a diagnostic model for a clinical application, it is crucial to guarantee the robustness of the model with respect to a wide range of image corruptions. Herein, an easy-to-use benchmark is established to evaluate how deep neural networks perform on corrupted pathology images. Specifically, corrupted images are generated by injecting nine types of common corruptions into validation images. Besides, two classification and one ranking metrics are designed to evaluate the prediction and confidence performance under corruption. Evaluated on two resulting benchmark datasets, we find that (1) a variety of deep neural network models suffer from a significant accuracy decrease (double the error on clean images) and the unreliable confidence estimation on corrupted images; (2) A low correlation between the validation and test errors while replacing the validation set with our benchmark can increase the correlation. Our codes are available on https://github.com/superjamessyx/robustness_benchmark., Comment: MICAAI2022

Cell classification and counting in immunohistochemical cytoplasm staining images play a pivotal role in cancer diagnosis. Weakly supervised learning is a potential method to deal with labor-intensive labeling. However, the inconstant cell morphology and subtle differences between classes also bring challenges. To this end, we present a novel cell recognition framework based on multi-task learning, which utilizes two additional auxiliary tasks to guide robust representation learning of the main task. To deal with misclassification, the tissue prior learning branch is introduced to capture the spatial representation of tumor cells without additional tissue annotation. Moreover, dynamic masks and consistency learning are adopted to learn the invariance of cell scale and shape. We have evaluated our framework on immunohistochemical cytoplasm staining images, and the results demonstrate that our method outperforms recent cell recognition approaches. Besides, we have also done some ablation studies to show significant improvements after adding the auxiliary branches.

Honglin Li,1,* Chunzheng Ma,1,* Sisi Chang,2 Yutan Xi,2 Shuai Shao,2 Mengli Chen,2 Juan Ren,2 Mingyue Sun,1 Liang Dong1 1Oncology Department, Henan Provincial Hospital of Traditional Chinese Medicine, Zhengzhou, Henan Province, People’s Republic of China; 2Oncology Department, Henan Provincial University of Traditional Chinese Medicine, Zhengzhou, Henan Province, People’s Republic of China*These authors contributed equally to this workCorrespondence: Honglin Li, Oncology Department, Henan Provincial Hospital of Traditional Chinese Medicine, No. 6 Dongfeng Road, Zhengzhou, 450002, People’s Republic of China, Email 46991701@qq.com Chunzheng Ma, Oncology Department, Henan Provincial Hospital of Traditional Chinese Medicine, No. 6 Dongfeng Road, Zhengzhou, 450002, People’s Republic of China, Email mchzh666@126.comObjective: Traditional Chinese medicine (TCM) is an ancient form of personalized medicine and may improve morbidity and mortality in patients with esophageal cancer. This retrospective study aimed to evaluate the utility of TCM in the treatment of stage IV esophageal squamous cell carcinoma (SCC).Methods: We collected the medical records of patients with stage IV SCC admitted to Henan Provincial Hospital of Traditional Chinese Medicine and Linzhou Hospital of Traditional Chinese Medicine between July 2017 and June 2020. We used univariate and multivariate analyses to determine if the use of TCM improved patient prognosis. Moreover, cluster analysis was used to classify the patients according to TCM syndrome type and identify the most frequently used combinations of remedies.Results: After that 402 patients were included in PSM, of which 196 (48.8%) were treated with traditional Chinese medicine. TCM prolonged the survival time of patients with stage IV esophageal SCC (P=0.084), and was an independently associated with prognosis as demonstrated by Cox multivariate regression analysis [risk ratio (RR) =0.543, 95% confidence interva

The distribution of hydrothermal vents and the biogeography of associated faunal communities in the Indian Ocean are still not well studied. This is especially true for Carlsberg Ridge, the northernmost part of the Indian Ocean spreading system. Here we report geological, morphological, biological, and hydrochemical data for the newly discovered Daxi Vent Field (DVF) on the slow-spreading Carlsberg Ridge at 6°48′N. The DVF is a basalt-hosted hydrothermal field situated atop a rifted volcanic ridge, located in a non-transform offset between two second-order ridge segments. There are three hydrothermal sites, i.e. Central mound, NE mound, and South mound. Eight vigorously venting black smokers were observed in the central hydrothermal mound. The largest sulfide chimney “Baochu Pagoda” is ~24 m tall. Another inactive chimney, which is silica-rich is observed in the NE mound. The sulfide chimneys are dominated by sphalerite and pyrrhotite containing high Sn, Co and Ag. The silica-rich chimney contains high SiO2 and Ba contents. Seven species of megafauna were identified, including alvinellid worms, which were collected in the Indian Ocean for the first time. Rimicaris kairei and actinostolid anemones dominate the community in the central areas and on the periphery of the vent field, respectively. The occurrence of DVF is quite unique as it is located on a non-transform offset and it is mafic-hosted. So far only nine hydrothermal fields with the similar geological setting have ever been reported among nearly 700 hydrothermal sites in the World’s Ocean. Graphical abstract The mafic-hosted Daxi Vent Field with high-temperature hydrothermal mineralization was discovered at a non-transform offset along the slow-spreading Carlsberg Ridge.

Agitation is one of the neuropsychiatric symptoms with high prevalence in dementia which can negatively impact the Activities of Daily Living (ADL) and the independence of individuals. Detecting agitation episodes can assist in providing People Living with Dementia (PLWD) with early and timely interventions. Analysing agitation episodes will also help identify modifiable factors such as ambient temperature and sleep as possible components causing agitation in an individual. This preliminary study presents a supervised learning model to analyse the risk of agitation in PLWD using in-home monitoring data. The in-home monitoring data includes motion sensors, physiological measurements, and the use of kitchen appliances from 46 homes of PLWD between April 2019-June 2021. We apply a recurrent deep learning model to identify agitation episodes validated and recorded by a clinical monitoring team. We present the experiments to assess the efficacy of the proposed model. The proposed model achieves an average of 79.78% recall, 27.66% precision and 37.64% F1 scores when employing the optimal parameters, suggesting a good ability to recognise agitation events. We also discuss using machine learning models for analysing the behavioural patterns using continuous monitoring data and explore clinical applicability and the choices between sensitivity and specificity in-home monitoring applications., Comment: 13 pages, accepted to Research2Clinics WS @ NeurIPS 2021

Sisi Chang,1 Yahui Zhu,2 Yutan Xi,2 Fuyan Gao,2 Juanjuan Lu,2 Liang Dong,1 Chunzheng Ma,1 Honglin Li1 1Department of Oncology, Henan Provincial Hospital of Traditional Chinese Medicine (The Second Affiliated Hospital of Henan University of Traditional Chinese Medicine), Zhengzhou, Henan Province, People’s Republic of China; 2Department of Oncology, Henan University of Traditional Chinese Medicine, Zhengzhou, Henan Province, People’s Republic of ChinaCorrespondence: Chunzheng Ma; Honglin LiHenan Provincial Hospital of Traditional Chinese Medicine (The Second Affiliated Hospital of Henan University of Traditional Chinese Medicine), Zhengzhou, Henan Province, People’s Republic of ChinaTel +86-18801611544Email mchzh666@126.com; 46991701@qq.comPurpose: To evaluate the role of DSCC1 in LUAD.Patients and Methods: Based on TCGA and GTEx, the Wilcoxon rank-sum test was used to compare the expression differences of DSCC1 between the normal samples of GTEx combined TCGA and the unpaired tumor samples of TCGA, and to compare DSCC1 expression values between tumor tissues and paired normal LUAD tissues in the TCGA cohort. Kruskal–Wallis rank-sum test, Wilcoxon rank-sum test, and logistics regression were used to compare the relationship between the expression of DSCC1 and the clinicopathological parameters. The biological function of DSCC1 was annotated by GSEA and ssGSEA, while Kaplan–Meier and Cox regression analysis were used to evaluate the prognostic value of DSCC1. Furthermore, the time-dependent ROC curve was used to analyze the diagnostic efficacy of DSCC1 in LUAD.Results: We downloaded the RNA-Seq data of 513 LUAD cases. The expression of DSCC1 was significantly correlated with T stage (OR = 1.04(1.02– 1.07), P = 0.002), pathological stage (OR=1.03 (1.01– 1.05), P = 0.008) and TP53 status (OR=1.10 (1.07– 1.14), P < 0.001). The high expression of DSCC1 was significantly correlated with DSS (HR=1.56 (1.07– 2.26), P = 0.021) and OS (HR=1.53 (1.14– 2.0

Ki67 is a significant biomarker in the diagnosis and prognosis of cancer, whose index can be evaluated by quantifying its expression in Ki67 immunohistochemistry (IHC) stained images. However, quantitative analysis on multi-source Ki67 images is yet a challenging task in practice due to cross-domain distribution differences, which result from imaging variation, staining styles, and lesion types. Many recent studies have made some efforts on domain generalization (DG), whereas there are still some noteworthy limitations. Specifically in the case of Ki67 images, learning invariant representation is at the mercy of the insufficient number of domains and the cell categories mismatching in different domains. In this paper, we propose a novel method to improve DG by searching the domain-agnostic subnetwork in a domain merging scenario. Partial model parameters are iteratively pruned according to the domain gap, which is caused by the data converting from a single domain into merged domains during training. In addition, the model is optimized by fine-tuning on merged domains to eliminate the interference of class mismatching among various domains. Furthermore, an appropriate implementation is attained by applying the pruning method to different parts of the framework. Compared with known DG methods, our method yields excellent performance in multiclass nucleus recognition of Ki67 IHC images, especially in the lost category cases. Moreover, our competitive results are also evaluated on the public dataset over the state-of-the-art DG methods., Comment: Accepted by MICCAI2021

Character rigging is universally needed in computer graphics but notoriously laborious. We present a new method, HeterSkinNet, aiming to fully automate such processes and significantly boost productivity. Given a character mesh and skeleton as input, our method builds a heterogeneous graph that treats the mesh vertices and the skeletal bones as nodes of different types and uses graph convolutions to learn their relationships. To tackle the graph heterogeneity, we propose a new graph network convolution operator that transfers information between heterogeneous nodes. The convolution is based on a new distance HollowDist that quantifies the relations between mesh vertices and bones. We show that HeterSkinNet is robust for production characters by providing the ability to incorporate meshes and skeletons with arbitrary topologies and morphologies (e.g., out-of-body bones, disconnected mesh components, etc.). Through exhaustive comparisons, we show that HeterSkinNet outperforms state-of-the-art methods by large margins in terms of rigging accuracy and naturalness. HeterSkinNet provides a solution for effective and robust character rigging., Comment: I3D 2021

Behavioural symptoms and urinary tract infections (UTI) are among the most common problems faced by people with dementia. One of the key challenges in the management of these conditions is early detection and timely intervention in order to reduce distress and avoid unplanned hospital admissions. Using in-home sensing technologies and machine learning models for sensor data integration and analysis provides opportunities to detect and predict clinically significant events and changes in health status. We have developed an integrated platform to collect in-home sensor data and performed an observational study to apply machine learning models for agitation and UTI risk analysis. We collected a large dataset from 88 participants with a mean age of 82 and a standard deviation of 6.5 (47 females and 41 males) to evaluate a new deep learning model that utilises attention and rational mechanism. The proposed solution can process a large volume of data over a period of time and extract significant patterns in a time-series data (i.e. attention) and use the extracted features and patterns to train risk analysis models (i.e. rational). The proposed model can explain the predictions by indicating which time-steps and features are used in a long series of time-series data. The model provides a recall of 91\% and precision of 83\% in detecting the risk of agitation and UTIs. This model can be used for early detection of conditions such as UTIs and managing of neuropsychiatric symptoms such as agitation in association with initial treatment and early intervention approaches. In our study we have developed a set of clinical pathways for early interventions using the alerts generated by the proposed model and a clinical monitoring team has been set up to use the platform and respond to the alerts according to the created intervention plans., Comment: 11 pages

The distribution of hydrothermal vents and the biogeography of associated faunal communities in the Indian Ocean are still not well studied. This is especially true for Carlsberg Ridge, the northernmost part of the Indian Ocean spreading system. Here we report geological, morphological, biological, and hydrochemical data for the newly discovered Daxi Vent Field (DVF) on the slow-spreading Carlsberg Ridge at 6°48′N. The DVF is a basalt-hosted hydrothermal field situated atop a rifted volcanic ridge, located in a non-transform offset between two second-order ridge segments. There are three hydrothermal sites, i.e. Central mound, NE mound, and South mound. Eight vigorously venting black smokers were observed in the central hydrothermal mound. The largest sulfide chimney “Baochu Pagoda” is ~24 m tall. Another inactive chimney, which is silica-rich is observed in the NE mound. The sulfide chimneys are dominated by sphalerite and pyrrhotite containing high Sn, Co and Ag. The silica-rich chimney contains high SiO2 and Ba contents. Seven species of megafauna were identified, including alvinellid worms, which were collected in the Indian Ocean for the first time. Rimicaris kairei and actinostolid anemones dominate the community in the central areas and on the periphery of the vent field, respectively. The occurrence of DVF is quite unique as it is located on a non-transform offset and it is mafic-hosted. So far only nine hydrothermal fields with the similar geological setting have ever been reported among nearly 700 hydrothermal sites in the World’s Ocean. Graphical abstract The mafic-hosted Daxi Vent Field with high-temperature hydrothermal mineralization was discovered at a non-transform offset along the slow-spreading Carlsberg Ridge.

The farnesoid X receptor (FXR) is a bile acid-sensing transcription factor with indispensable roles in regulating metabolic processes. Nowadays, FXR has become a highly promising drug target for severe liver disorders, especially nonalcoholic steatohepatitis (NASH). A recent study showed that imatinib and its analogues were able to allosterically enhance agonist-induced FXR activation and its target gene expression. However, the allosteric modulation mechanism of FXR by these compounds remains unclear. In this work, the most effective imatinib analogue, P16, was used as a probe to explore this issue by computational approaches. Our results identified one potential allosteric site surrounded by residues Ile335, Phe336, Lys338, Glu339, Leu340, and Leu348, which could efficiently accommodate P16. In addition, the long-time molecular dynamics simulations indicated that the binding of P16 could significantly decrease the fluctuation of the co-activator and enhance the communications between the endogenous ligand chenodeoxycholic acid (CDCA) and FXR. By analyzing the residue interaction network, we observed two unique communication pathways connecting P16 and CDCA through three key residues, Arg331, Ser332, and Phe336. The communications of network organization in the P16-bound complex may allow the synergistic effect of the two compounds via robust signal transmission between the binding sites and global network bridges, which coordinate allosteric transitions and modulate the receptor activity. Our study offers insights into the allosteric modulation occurring in FXR and would be helpful for discovery of new allosteric modulators targeting FXR for further clinical research., QC 20200514, Biology

Conventional deep learning models have limited capacity in learning multiple tasks sequentially. The issue of forgetting the previously learned tasks in continual learning is known as catastrophic forgetting or interference. When the input data or the goal of learning change, a continual model will learn and adapt to the new status. However, the model will not remember or recognise any revisits to the previous states. This causes performance reduction and re-training curves in dealing with periodic or irregularly reoccurring changes in the data or goals. The changes in goals or data are referred to as new tasks in a continual learning model. Most of the continual learning methods have a task-known setup in which the task identities are known in advance to the learning model. We propose Multi-view Task Conditional Neural Networks (Mv-TCNN) that does not require to known the reoccurring tasks in advance. We evaluate our model on standard datasets using MNIST, CIFAR10, CIFAR100, and also a real-world dataset that we have collected in a remote healthcare monitoring study (i.e. TIHM dataset). The proposed model outperforms the state-of-the-art solutions in continual learning and adapting to new tasks that are not defined in advance., Comment: 10 pages

Yi Zou,1 Ling Hu,1 Wenjun Zou,2 Honglin Li3 1Department of Endocrinology, The Third Affiliated Hospital of Nanchang University, Nanchang, People’s Republic of China; 2General Surgery, Nanchang Third Hospital, Nanchang, People’s Republic of China; 3Department of Biochemistry, Medical College of Georgia, Augusta, GA, USACorrespondence: Ling HuDepartment of Endocrinology, The Third Affiliated Hospital of Nanchang University, No. 128 Xiangshan North Road, Nanchang 330000, Jiangxi Province, People’s Republic of ChinaTel +86 791-88862350Email hul@medmail.com.cnBackground: Leptin, an adipokine, has effects on the cardiovascular system with both protective and harmful role. This study aimed to assess the relationship between leptin and 3-month prognosis in ischemic stroke patients with type 2 diabetes.Patients and Methods: As a prospective single-center observational study, we collected consecutive first-ever acute ischemia stroke with type 2 diabetes mellitus from February 2019 to February 2020. Serum samples were obtained at admission, and leptin serum levels were tested by the ELISA method. Logistic regression models were used to assess leptin’s prognostic value to predict the functional outcome and mortality within three months.Results: Finally, two hundred and eleven patients were included, and the mean leptin serum level was 16.8 (SD. 6.9) ng/mL. At admission, 53.6% of those included patients (N=113) were defined as severe stroke (NIH Stroke Scale [NIHSS]> 5). In multivariable models adjusted for other factors, leptin levels< 11.6ng/mL (lowest quartile, Q1) related to severe stroke and the risk increased 175% (odds ratios [OR] =2.75; 95% confidence interval [CI]=2.13– 3.38; P=0.002). Serum leptin levels on admission in patients with poor outcomes and nonsurvivors were significantly reduced (P< 0.001 and P< 0.001). Leptin levels < 11.6ng/mL (lowest quartile, Q1) related to a higher ris

Machine learning techniques combined with in-home monitoring technologies provide a unique opportunity to automate diagnosis and early detection of adverse health conditions in long-term conditions such as dementia. However, accessing sufficient labelled training samples and integrating high-quality, routinely collected data from heterogeneous in-home monitoring technologies are main obstacles hindered utilising these technologies in real-world medicine. This work presents a semi-supervised model that can continuously learn from routinely collected in-home observation and measurement data. We show how our model can process highly imbalanced and dynamic data to make robust predictions in analysing the risk of Urinary Tract Infections (UTIs) in dementia. UTIs are common in older adults and constitute one of the main causes of avoidable hospital admissions in people with dementia (PwD). Health-related conditions, such as UTI, have a lower prevalence in individuals, which classifies them as sporadic cases (i.e. rare or scattered, yet important events). This limits the access to sufficient training data, without which the supervised learning models risk becoming overfitted or biased. We introduce a probabilistic semi-supervised learning framework to address these issues. The proposed method produces a risk analysis score for UTIs using routinely collected data by in-home sensing technologies., Comment: 11 pages

Training deep learning models on in-home IoT sensory data is commonly used to recognise human activities. Recently, federated learning systems that use edge devices as clients to support local human activity recognition have emerged as a new paradigm to combine local (individual-level) and global (group-level) models. This approach provides better scalability and generalisability and also offers better privacy compared with the traditional centralised analysis and learning models. The assumption behind federated learning, however, relies on supervised learning on clients. This requires a large volume of labelled data, which is difficult to collect in uncontrolled IoT environments such as remote in-home monitoring. In this paper, we propose an activity recognition system that uses semi-supervised federated learning, wherein clients conduct unsupervised learning on autoencoders with unlabelled local data to learn general representations, and a cloud server conducts supervised learning on an activity classifier with labelled data. Our experimental results show that using a long short-term memory autoencoder and a Softmax classifier, the accuracy of our proposed system is higher than that of both centralised systems and semi-supervised federated learning using data augmentation. The accuracy is also comparable to that of supervised federated learning systems. Meanwhile, we demonstrate that our system can reduce the number of needed labels and the size of local models, and has faster local activity recognition speed than supervised federated learning does.

The robustness of neural networks is challenged by adversarial examples that contain almost imperceptible perturbations to inputs, which mislead a classifier to incorrect outputs in high confidence. Limited by the extreme difficulty in examining a high-dimensional image space thoroughly, research on explaining and justifying the causes of adversarial examples falls behind studies on attacks and defenses. In this paper, we present a collection of potential causes of adversarial examples and verify (or partially verify) them through carefully-designed controlled experiments. The major causes of adversarial examples include model linearity, one-sum constraint, and geometry of the categories. To control the effect of those causes, multiple techniques are applied such as $L_2$ normalization, replacement of loss functions, construction of reference datasets, and novel models using multi-layer perceptron probabilistic neural networks (MLP-PNN) and density estimation (DE). Our experiment results show that geometric factors tend to be more direct causes and statistical factors magnify the phenomenon, especially for assigning high prediction confidence. We believe this paper will inspire more studies to rigorously investigate the root causes of adversarial examples, which in turn provide useful guidance on designing more robust models.

Continual learning models allow to learn and adapt to new changes and tasks over time. However, in continual and sequential learning scenarios in which the models are trained using different data with various distributions, neural networks tend to forget the previously learned knowledge. This phenomenon is often referred to as catastrophic forgetting. The catastrophic forgetting is an inevitable problem in continual learning models for dynamic environments. To address this issue, we propose a method, called Continual Bayesian Learning Networks (CBLN), which enables the networks to allocate additional resources to adapt to new tasks without forgetting the previously learned tasks. Using a Bayesian Neural Network, CBLN maintains a mixture of Gaussian posterior distributions that are associated with different tasks. The proposed method tries to optimise the number of resources that are needed to learn each task and avoids an exponential increase in the number of resources that are involved in learning multiple tasks. The proposed method does not need to access the past training data and can choose suitable weights to classify the data points during the test time automatically based on an uncertainty criterion. We have evaluated our method on the MNIST and UCR time-series datasets. The evaluation results show that our method can address the catastrophic forgetting problem at a promising rate compared to the state-of-the-art models., Comment: 10 pages

Learning and adapting to new distributions or learning new tasks sequentially without forgetting the previously learned knowledge is a challenging phenomenon in continual learning models. Most of the conventional deep learning models are not capable of learning new tasks sequentially in one model without forgetting the previously learned ones. We address this issue by using a Kalman Optimiser. The Kalman Optimiser divides the neural network into two parts: the long-term and short-term memory units. The long-term memory unit is used to remember the learned tasks and the short-term memory unit is to adapt to the new task. We have evaluated our method on MNIST, CIFAR10, CIFAR100 datasets and compare our results with state-of-the-art baseline models. The results show that our approach enables the model to continually learn and adapt to the new changes without forgetting the previously learned tasks., Comment: accepted by ICML workshop

Learning in a non-stationary environment is an inevitable problem when applying machine learning algorithm to real world environment. Learning new tasks without forgetting the previous knowledge is a challenge issue in machine learning. We propose a Kalman Filter based modifier to maintain the performance of Neural Network models under non-stationary environments. The result shows that our proposed model can preserve the key information and adapts better to the changes. The accuracy of proposed model decreases by 0.4% in our experiments, while the accuracy of conventional model decreases by 90% in the drifts environment., Comment: 4 pages

Highlights • First present seafloor hydrothermal mineralization processes at both Wocan-1 and Wocan-2 on the slow-spreading Carlsberg Ridge. • The Cu-rich chimneys were formed at slightly lower temperatures than Cu-rich and Fe-rich massive sulfides. • The main Ag-carriers were both late-stage Cu sulfides and Fe sulfides, which deposited under low temperatures and oxidized conditions. • Fluid mixing of hydrothermal fluids with seawater might result in significant redistributions of trace metal elements in sulfides. Abstract The basalt-hosted Wocan hydrothermal field (WHF), located on the NW slope of an axial volcanic ridge in a depth of ∼3000 m at 6°22′N on the slow-spreading Carlsberg Ridge, northwest Indian Ocean, was discovered in 2013 during Chinese DY28th cruise. Preliminary investigations show that the field consists of two hydrothermal sites: Wocan-1, which shows indications for recent high-temperature hydrothermal activity, is located near the peak of the axial volcanic ridge in a water depth of 2970-2990 m, and the inactive Wocan-2 site, located at a water depth of 3100 m, ∼1.7 km to the northwest of Wocan-1. The recovered hydrothermal precipitates can be classified into four groups: (i) Cu-rich chimneys; (ii) Cu-rich massive sulfides; (iii) Fe-rich massive sulfides; and (iv) silicified massive sulfides. We conducted mineral texture and assemblage observation and Laser-ablation ICP-MS analyses of the hydrothermal precipitates to study the mineralization processes. Our results show that there are distinct systematic trace element distributions throughout the different minerals in the four sample groups. In general, chalcopyrite from the group (i) is enriched in Pb, As, Mo, Ga, Ge, V, and Sb, metals that are commonly referred to as medium- to low-temperature elements. In contrast these elements are present in low contents in the chalcopyrite grains from other sample groups. Selenium, a typical high-temperature metal, is enriched in chalcopyrite from groups (ii

Highlights • First present seafloor hydrothermal mineralization processes at both Wocan-1 and Wocan-2 on the slow-spreading Carlsberg Ridge. • The Cu-rich chimneys were formed at slightly lower temperatures than Cu-rich and Fe-rich massive sulfides. • The main Ag-carriers were both late-stage Cu sulfides and Fe sulfides, which deposited under low temperatures and oxidized conditions. • Fluid mixing of hydrothermal fluids with seawater might result in significant redistributions of trace metal elements in sulfides. Abstract The basalt-hosted Wocan hydrothermal field (WHF), located on the NW slope of an axial volcanic ridge in a depth of ∼3000 m at 6°22′N on the slow-spreading Carlsberg Ridge, northwest Indian Ocean, was discovered in 2013 during Chinese DY28th cruise. Preliminary investigations show that the field consists of two hydrothermal sites: Wocan-1, which shows indications for recent high-temperature hydrothermal activity, is located near the peak of the axial volcanic ridge in a water depth of 2970-2990 m, and the inactive Wocan-2 site, located at a water depth of 3100 m, ∼1.7 km to the northwest of Wocan-1. The recovered hydrothermal precipitates can be classified into four groups: (i) Cu-rich chimneys; (ii) Cu-rich massive sulfides; (iii) Fe-rich massive sulfides; and (iv) silicified massive sulfides. We conducted mineral texture and assemblage observation and Laser-ablation ICP-MS analyses of the hydrothermal precipitates to study the mineralization processes. Our results show that there are distinct systematic trace element distributions throughout the different minerals in the four sample groups. In general, chalcopyrite from the group (i) is enriched in Pb, As, Mo, Ga, Ge, V, and Sb, metals that are commonly referred to as medium- to low-temperature elements. In contrast these elements are present in low contents in the chalcopyrite grains from other sample groups. Selenium, a typical high-temperature metal, is enriched in chalcopyrite from groups (ii

Species originally from alpine wetland and alpine meadow communities now coexist in a novel ‘alpine swamp meadow’ community as a consequence of wetland drying in the eastern Tibetan Plateau. Considering the projected increase in the fluctuation of water supply from precipitation during the growing season in this area in the future, it is important to investigate the responses of the species that make up this new community to soil water availability. Using a transplant experimental design, we compared the response of leaf traits and growth to different water conditions for species grouped according to their original habitat of wetland or meadow. Twelve perennial herbaceous species, which form an alpine swamp meadow community in Maqu County in the eastern Tibetan Plateau, were used in this study and subjected to two water treatments, namely waterlogged and dry-down. Overall, significant differences in leaf production in response to soil water availability were found for these two groups, indicating strongly different effects of water availability on their growth. Furthermore, the meadow group had lower specific leaf area, leaf area and relative leaf water content, but thicker leaves than those of the wetland group, indicating significant habitat-specific differences in leaf morphology. Regarding physiological traits, the wetland group had significantly higher photosynthetic rates in inundated conditions, whereas for the meadow group the photosynthetic rate was greatest in cyclically dry conditions. Likewise, a similar pattern was observed for stomatal conductance; however, both groups achieved higher instantaneous water use efficiency during the dry-down treatment. The results of this study indicate that the composition of the alpine swamp meadow could be sensitive to changes in precipitation and might be changed substantially by future declines in water supply, as predicted by global climate change models for this region. This potential for compositional change of th

This study aims to elucidate the signaling pathway of TRAIL-mediated apoptosis in prostate cancer cells, and to examine the therapeutic effect of TRAIL on prostate cancer cells in vitro and in vivo. We found that most of prostate cancer cells such as androgen-independent PC-3 and DU145 cells are sensitive to TRAIL treatment while normal prostate epithelial cells are resistant. This result indicates that TRAIL may be appropriate agent for treatment of late-stage prostate cancer with no cytotoxicity to normal prostate cells. Further investigation on the molecular mechanism of TRAIL resistance revealed that the elevated eNOS activity by Akt phosphorylation may partially contribute to Akt-mediated TRAIL resistance in LNCaP cells. We also found that chemotherapeutic agents such as etoposide (DNA topoisomearse II inhibitor) and VELCADE (proteasome inhibitor) sensitized PC cells to TRAIL-mediated apoptosis. Our further study indicated that JNK and JNK-mediated BID cleavage may play an important role in synergistic effect between VELCADE and TRAIL., The original document contains color images. All DTIC reproductions will be in black and white.

This study aims to elucidate the signaling pathway of TRAIL-mediated apoptosis in prostate cancer cells, and to examine the therapeutic effect of TRAIL on prostate cancer cells in vitro and in vivo. We found that most of prostate cancer cells such as androgen-independent PC-3 and DUl45 cells are sensitive to TRAIL treatment while normal prostate epithelial cells are resistant. This result indicates that TRAIL may be appropriate agent for treatment of late-stage prostate cancer with no cytotoxicity to normal prostate cells. Further investigation on the molecular mechanism of TRAIL resistance revealed that pro-survival protein kinase Akt existed in a constitutively active form at high level in LNCaP cells that are resistant to TRAIL. Inhibition of PI 3-kinase sensitized LNCaP cells to TRAIL, suggesting that Akt may play a critical regulatory role in TRAIL signaling. To further understand the working mechanism of Akt, we surveyed its downstream targets, and found that the elevated eNOS activity by Akt phosphorylation may partially contribute to Akt-mediated TRAIL resistance in LNOaP cells. Overexpression of eNOS in PC-3 cells prevents TRAIL-ienduced apoptosis.

This study aims to elucidate the signaling pathway of TRAIL-mediated apoptosis in prostate cancer cells, and to examine the therapeutic effect of TRAIL on prostate cancer cells in vitro and in vivo. We found that most of prostate cancer cells such as androgen-independent PC-3 and DU145 cells are sensitive to TRAIL treatment while normal prostate epithelial cells are resistant. This result indicates that TRAIL may be appropriate agent for treatment of late-stage prostate cancer with no cytotoxicity to normal prostate cells. Further investigation on the molecular mechanism of TRAIL resistance revealed that pro-survival protein kinase Akt existed in a constitutively active form at high level in LNCaP cells that are resistant to TRAIL. Inhibition of PI 3-kinase sensitized LNCaP cells to TRAIL, suggesting that Akt may play a critical regulatory role in TRAIL signaling. To further understand the working mechanism of Akt, we surveyed its downstream targets, and found that the elevated eNOS activity by Akt phosphorylation may partially contribute to Akt-mediated TRAIL resistance in LNCaP cells. Our preliminary result also indicated that other anti-apoptotic mechanisms may exist in LNCaP cells.