Search

As the most common cause of dementia, the study of Alzheimer’s disease (AD) faces challenges in terms of understanding the cause, monitoring the pathogenesis, and developing early diagnosis and effective treatment. Rapid and accurate identification of AD biomarkers in the brain is critical to provide key insights into AD and facilitate the development of early diagnosis methods. In this work, we developed a platform that enables a rapid screening of AD biomarkers by employing graphene-assisted Raman spectroscopy and machine learning interpretation in AD transgenic animal brains. Specifically, we collected Raman spectra on slices of mouse brains with and without AD and used machine learning to classify AD and non-AD spectra. By contacting monolayer graphene with the brain slices, the accuracy was significantly increased from 77% to 98% in machine learning classification. Further, using linear supporting vector machine (SVM), we identified a spectral feature importance map that reveals the importance of each Raman wavenumber in classifying AD and non-AD spectra. Based on this spectral feature importance map, we identified AD biomarkers including Aβ and tau proteins, and other potential biomarkers, such as triolein, phosphatidylcholine, and actin, which have been confirmed by other biochemical studies. Our Raman-machine learning integrated method with interpretability is promising to greatly accelerate the study of AD and can be extended to other tissues, biofluids, and for various other diseases.

Rapid identification of newly emerging or circulating viruses is an important first step toward managing the public health response to potential outbreaks. A portable virus capture device coupled with label-free Raman Spectroscopy holds the promise of fast detection by rapidly obtaining the Raman signature of a virus followed by a machine learning approach applied to recognize the virus based on its Raman spectrum, which is used as a fingerprint. We present such a machine learning approach for analyzing Raman spectra of human and avian viruses. A Convolutional Neural Network (CNN) classifier specifically designed for spectral data achieves very high accuracy for a variety of virus type or subtype identification tasks. In particular, it achieves 99% accuracy for classifying influenza virus type A vs. type B, 96% accuracy for classifying four subtypes of influenza A, 95% accuracy for differentiating enveloped and non-enveloped viruses, and 99% accuracy for differentiating avian coronavirus (infectious bronchitis virus, IBV) from other avian viruses. Furthermore, interpretation of neural net responses in the trained CNN model using a full-gradient algorithm highlights Raman spectral ranges that are most important to virus identification. By correlating ML-selected salient Raman ranges with the signature ranges of known biomolecules and chemical functional groups (for example, amide, amino acid, carboxylic acid), we verify that our ML model effectively recognizes the Raman signatures of proteins, lipids and other vital functional groups present in different viruses and uses a weighted combination of these signatures to identify viruses., 23 pages, 8 figures

Rapid identification of newly emerging or circulating viruses is an important first step toward managing the public health response to potential outbreaks. A portable virus capture device coupled with label-free Raman Spectroscopy holds the promise of fast detection by rapidly obtaining the Raman signature of a virus followed by a machine learning approach applied to recognize the virus based on its Raman spectrum. In this paper, we present a machine learning analysis on Raman spectra of human and avian viruses. A Convolutional Neural Network (CNN) classifier specifically designed for spectral data achieves very high accuracy for a variety of virus type or subtype identification tasks. In particular, it achieves 99% accuracy for classifying influenza virus type A vs. type B, 96% accuracy for classifying four subtypes of influenza A, 95% accuracy for differentiating enveloped and non-enveloped viruses, and 99% for differentiating avian coronavirus (infectious bronchitis virus, IBV) from other avian viruses. Furthermore, interpretation of neural net responses in the trained CNN model using a full-gradient algorithm highlights Raman spectral ranges that are most important to virus identification. By correlating ML-selected salient Raman ranges with the signature ranges of known biomolecules and chemical functional groups (e.g. amide, amino acid, carboxylic acid) we verify that our ML model effectively recognizes the Raman signatures of proteins, lipids and other vital functional groups present in different viruses and uses a weighted combination of these signatures to identify viruses. The accurate and interpretable machine learning model developed for Raman virus identification presents promising potential in a real-time virus detection system.Significance StatementA portable micro-fluidic platform for virus capture promises rapid enrichment and label-free optical identification of viruses by Raman spectroscopy. A large Raman dataset collected on a variety of viruses enables the training of machine learning (ML) models capable of highly accurate and sensitive virus identification. The trained ML models can then be integrated with the portable device to provide real-time virus detection and identification capability. We validate this conceptual framework by presenting highly accurate virus type and subtype identification results using a convolutional neural network to classify Raman spectra of viruses.

As of April 15, 2020, the novel coronavirus disease 2019 (COVID-19) has caused over 2 million infections worldwide; in China, there have been at least 82,341 cases, over 3000 of which were in medical personnel, and at least 3342 deaths. The Guangdong Provincial Hospital of Chinese Medicine (GPHCM) is one of the largest Chinese medicine hospitals in China. In January 2020, the hospital established a new coronavirus infection pneumonia emergency prevention and control working group to train hospital staff on infection knowledge, established isolation wards to centrally treat suspected cases, and sent 88 medical personnel across nine successive medical teams to support the worst-affected area, Wuhan. Here, we summarize the steps GPHCM took to avoid hospital-related infections during the COVID-19 epidemic.

A 39-year-old woman who was maintained on peritoneal dialysis (PD) for 25 years was admitted to ED with a 2-week history of abdominal pain and vomiting. She had been taking midodrine for several years because of low blood pressure but she had no medical history of diabetes or hypercholesterolaemia. On clinical examination, she presented with middle abdominal tenderness, no rebound tenderness and negative Murphy’s and McBurney’s signs. The laboratory examination showed that her leucocyte count was 9.45×10 …

In this paper, novel flower-like Co 3 O 4 structures have been fabricated by an ethylene glycol (EG) mediated solvothermal with the co-assistant of water and polyvinyl pyrrolidone (PVP). It was found that the water and PVP played a key role in the formation process. The structure and morphology of the as-prepared products were analyzed using X-ray diffraction (XRD), scanning electron microscopy (SEM) and transmission electron microscope (TEM). The results revealed that the flower-like Co 3 O 4 was assembled by single-crystalline porous nanosheets. Due to the structural stability of single-crystalline nanosheets, the flower-like hierarchical porous structures can be well kept during the sensor-fabrication processed. Notably, gas-sensing tests revealed that the flower-like Co 3 O 4 showed a high response (R g /R a = 79.8–100 ppm) to xylene at its optimized temperature (150 °C), which was 4 times higher than that of commercial Co 3 O 4 (R g /R a = 19.1). Moreover, the flower-like Co 3 O 4 also exhibited excellent long-term stability with small deviations (3.1%) for two months. The enhanced gas-sensing performances of flower-like Co 3 O 4 were mainly attributed to the structural stability of single-crystalline porous nanosheets as building blocks. Combined with its high selectivity and low detection limit, the as-prepared novel flower-like Co 3 O 4 assembled by single-crystalline porous nanosheets is a highly promising gas-sensing material for xylene detection.

Cervical intraepithelial neoplasia (CIN) grade of histopathology images is a crucial indicator in cervical biopsy results. Accurate CIN grading of epithelium regions helps pathologists with precancerous lesion diagnosis and treatment planning. Although an automated CIN grading system has been desired, supervised training of such a system would require a large amount of expert annotations, which are expensive and time-consuming to collect. In this paper, we investigate the CIN grade classification problem on segmented epithelium patches. We propose to use conditional Generative Adversarial Networks (cGANs) to expand the limited training dataset, by synthesizing realistic cervical histopathology images. While the synthetic images are visually appealing, they are not guaranteed to contain meaningful features for data augmentation. To tackle this issue, we propose a synthetic-image filtering mechanism based on the divergence in feature space between generated images and class centroids in order to control the feature quality of selected synthetic images for data augmentation. Our models are evaluated on a cervical histopathology image dataset with limited number of patch-level CIN grade annotations. Extensive experimental results show a significant improvement of classification accuracy from 66.3% to 71.7% using the same ResNet18 baseline classifier after leveraging our cGAN generated images with feature based filtering, which demonstrates the effectiveness of our models.

Histopathological analysis is the present gold standard for precancerous lesion diagnosis. The goal of automated histopathological classification from digital images requires supervised training, which requires a large number of expert annotations that can be expensive and time-consuming to collect. Meanwhile, accurate classification of image patches cropped from whole-slide images is essential for standard sliding window based histopathology slide classification methods. To mitigate these issues, we propose a carefully designed conditional GAN model, namely HistoGAN, for synthesizing realistic histopathology image patches conditioned on class labels. We also investigate a novel synthetic augmentation framework that selectively adds new synthetic image patches generated by our proposed HistoGAN, rather than expanding directly the training set with synthetic images. By selecting synthetic images based on the confidence of their assigned labels and their feature similarity to real labeled images, our framework provides quality assurance to synthetic augmentation. Our models are evaluated on two datasets: a cervical histopathology image dataset with limited annotations, and another dataset of lymph node histopathology images with metastatic cancer. Here, we show that leveraging HistoGAN generated images with selective augmentation results in significant and consistent improvements of classification performance (6.7% and 2.8% higher accuracy, respectively) for cervical histopathology and metastatic cancer datasets., Elsevier Medical Image Analysis Best Paper Award runner up. arXiv admin note: substantial text overlap with arXiv:1912.03837

Background: Sudden cardiac arrest (SCA) is one of the most common critical illnesses encountered in clinical practice. Shenfu injection (SFI) has received extensive attention as an alternative therapy that can effectively maintain the autonomic circulation function after cardiopulmonary resuscitation. However, the mechanism of SFI is not yet fully understood. In addition, there has been no systematic review or meta-analysis of SFI in the treatment of patients with return of spontaneous circulation after SCA. Herein, we describe the protocol of a proposed study based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines that aims to systematically evaluate the efficacy and safety of SFI in patients with return of spontaneous circulation after SCA. Methods: Two researchers will search 9 electronic databases (PubMed, Medline, Embase, Cochrane Library, Web of Science, China National Knowledge Infrastructure, Chinese VIP Information, Wanfang, and Chinese Biomedical Database) to identify all studies that meet the inclusion criteria and were published before July 2018. After information extraction and methodological quality evaluation, we will use Stata 13.0 software (STATA Corporation, College Station, TX, USA) to synthesize the data. The primary outcomes will be the survival rate and Glasgow Coma Scale. Results: The data synthesis results will objectively illustrate the efficacy and safety of SFI in patients with return of spontaneous circulation after SCA. Conclusion: The findings will provide a reference for the use of SFI in the treatment of patients with return of spontaneous circulation after SCA. Registration: PROSPERO (registration number: CRD42018104230).