COVID-19 mortality prediction in the intensive care unit with deep learning based on longitudinal chest X-rays and clinical data.

OBJECTIVES: We aimed to develop deep learning models using longitudinal chest X-rays (CXRs) and clinical data to predict in-hospital mortality of COVID-19 patients in the intensive care unit (ICU). METHODS: Six hundred fifty-four patients (212 deceased, 442 alive, 5645 total CXRs) were identified across two institutions. Imaging and clinical data from one institution were used to train five longitudinal transformer-based networks applying five-fold cross-validation. The models were tested on data from the other institution, and pairwise comparisons were used to determine the best-performing models. RESULTS: A higher proportion of deceased patients had elevated white blood cell count, decreased absolute lymphocyte count, elevated creatine concentration, and incidence of cardiovascular and chronic kidney disease. A model based on pre-ICU CXRs achieved an AUC of 0.632 and an accuracy of 0.593, and a model based on ICU CXRs achieved an AUC of 0.697 and an accuracy of 0.657. A model based on all longitudinal CXRs (both pre-ICU and ICU) achieved an AUC of 0.702 and an accuracy of 0.694. A model based on clinical data alone achieved an AUC of 0.653 and an accuracy of 0.657. The addition of longitudinal imaging to clinical data in a combined model significantly improved performance, reaching an AUC of 0.727 (p = 0.039) and an accuracy of 0.732. CONCLUSIONS: The addition of longitudinal CXRs to clinical data significantly improves mortality prediction with deep learning for COVID-19 patients in the ICU. KEY POINTS: • Deep learning was used to predict mortality in COVID-19 ICU patients. • Serial radiographs and clinical data were used. • The models could inform clinical decision-making and resource allocation.

Tachypleus tridentatus Lectin Enhances Oncolytic Vaccinia Virus Replication to Suppress In Vivo Hepatocellular Carcinoma Growth.

Lectins play diverse roles in physiological processes as biological recognition molecules. In this report, a gene encoding Tachypleus tridentatus Lectin (TTL) was inserted into an oncolytic vaccinia virus (oncoVV) vector to form oncoVV-TTL, which showed significant antitumor activity in a hepatocellular carcinoma mouse model. Furthermore, TTL enhanced oncoVV replication through suppressing antiviral factors expression such as interferon-inducible protein 16 (IFI16), mitochondrial antiviral signaling protein (MAVS) and interferon-beta (IFN-ß). Further investigations revealed that oncoVV-TTL replication was highly dependent on ERK activity. This study might provide insights into a novel way of the utilization of TTL in oncolytic viral therapies.

Haliotis discus discus Sialic Acid-Binding Lectin Reduces the Oncolytic Vaccinia Virus Induced Toxicity in a Glioblastoma Mouse Model.

Although oncolytic viruses provide attractive vehicles for cancer treatment, their adverse effects are largely ignored. In this work, rat C6 glioblastoma cells were subcutaneously xenografted into mice, and a thymidine kinase-deficient oncolytic vaccinia virus (oncoVV) induced severe toxicity in this model. However, oncoVV-HddSBL, in which a gene encoding Haliotis discus discus sialic acid-binding lectin (HddSBL) was inserted into oncoVV, significantly prolonged the survival of mice as compared to the control virus. HddSBL reduced the tumor secreted serum rat IL-2 level upregulated by oncoVV, promoted viral replication, as well as inhibited the expression of antiviral factors in C6 glioblastoma cell line. Furthermore, HddSBL downregulated the expression levels of histone H3 and H4, and upregulated histone H3R8 and H4R3 asymmetric dimethylation, confirming the effect of HddSBL on chromatin structure suggested by the transcriptome data. Our results might provide insights into the utilization of HddSBL in counteracting the adverse effects of oncolytic vaccinia virus.

Collagen type â -loaded methacrylamide hyaluronic acid hydrogel microneedles alleviate stress urinary incontinence in mice: A novel treatment and prevention strategy.

Stress urinary incontinence (SUI), a chronic disease with widespread effects and an overall prevalence of up to 46% in adult women, is associated with a heavy disease burden. The clinical treatment for mild to moderate SUI is conservative, such as electrical stimulation and Kegel exercises, but the therapeutic effect is unsatisfactory, so it is imperative to seek new treatment modalities. Hydrogel microneedles (MNs) have been widely used in transdermal drug delivery because of their minimally invasive and highly biocompatible characteristics. Therefore, for the first time, we combined collagen type I with MN technology for the treatment and prevention of mild to moderate SUI.

Chitin-based hydrogel loaded with bFGF and SDF-1 for inducing endogenous mesenchymal stem cells homing to improve stress urinary incontinence.

Nonoperative treatments for Stress Urinary Incontinence (SUI) represent an ideal treatment method. Mesenchymal stem cell (MSCs) treatment is a new modality, but there is a lack of research in the field of gynecological pelvic floor and no good method to induce internal MSC homing to improve SUI. Herein, we develop an injectable and self-healing hydrogel derived from ß-chitin which consists of an amino group of quaternized ß-chitin (QC) and an aldehyde group of oxidized dextran (OD) between the dynamic Schiff base linkage.it can carry bFGF and SDF-1a and be injected into the vaginal forearm of mice in a non-invasive manner. It provides sling-like physical support to the anterior vaginal wall in the early stages. In the later stage, it slowly releasing factors and promoting the homing of MSCs in vivo, which can improve the local microenvironment, increase collagen deposition, repair the tissue around urethra and finally improve SUI (Scheme 1). This is the first bold attempt in the field of pelvic floor using hydrogel mechanical support combined with MSCs homing and the first application of chitin hydrogel in gynecology. We think the regenerative medicine approach based on bFGF/SDF-1/chitin hydrogel may be an effective non-surgical approach to combat clinical SUI.

A Fully Automated Multimodal MRI-Based Multi-Task Learning for Glioma Segmentation and IDH Genotyping.

The accurate prediction of isocitrate dehydrogenase (IDH) mutation and glioma segmentation are important tasks for computer-aided diagnosis using preoperative multimodal magnetic resonance imaging (MRI). The two tasks are ongoing challenges due to the significant inter-tumor and intra-tumor heterogeneity. The existing methods to address them are mostly based on single-task approaches without considering the correlation between the two tasks. In addition, the acquisition of IDH genetic labels is expensive and costly, resulting in a limited number of IDH mutation data for modeling. To comprehensively address these problems, we propose a fully automated multimodal MRI-based multi-task learning framework for simultaneous glioma segmentation and IDH genotyping. Specifically, the task correlation and heterogeneity are tackled with a hybrid CNN-Transformer encoder that consists of a convolutional neural network and a transformer to extract the shared spatial and global information learned from a decoder for glioma segmentation and a multi-scale classifier for IDH genotyping. Then, a multi-task learning loss is designed to balance the two tasks by combining the segmentation and classification loss functions with uncertain weights. Finally, an uncertainty-aware pseudo-label selection is proposed to generate IDH pseudo-labels from larger unlabeled data for improving the accuracy of IDH genotyping by using semi-supervised learning. We evaluate our method on a multi-institutional public dataset. Experimental results show that our proposed multi-task network achieves promising performance and outperforms the single-task learning counterparts and other existing state-of-the-art methods. With the introduction of unlabeled data, the semi-supervised multi-task learning framework further improves the performance of glioma segmentation and IDH genotyping. The source codes of our framework are publicly available at https://github.com/miacsu/MTTU-Net.git.

DARC: Deep adaptive regularized clustering for histopathological image classification.

In recent years, deep learning as a state-of-the-art machine learning technique has made great success in histopathological image classification. However, most of deep learning approaches rely heavily on the substantial task-specific annotations, which require experienced pathologists' manual labelling. As a result, they are laborious and time-consuming, and many unlabeled pathological images are difficult to use without experts' annotations. To mitigate the requirement for data annotation, we propose a self-supervised Deep Adaptive Regularized Clustering (DARC) framework to pre-train a neural network. DARC iteratively clusters the learned representations and utilizes the cluster assignments as pseudo-labels to learn the parameters of the network. To learn feasible representations and encourage the representations to become more discriminative, we design an objective function combining a network loss with a clustering loss using an adaptive regularization function, which is updated adaptively throughout the training process to learn feasible representations. The proposed DARC is evaluated on three public datasets, including NCT-CRC-HE-100K, PCam and LC25000. Compared to the strategy of training from scratch, fine-tuning using the pre-trained weights of DARC can obviously boost the accuracy of neural networks on histopathological classification. The accuracy of using the network trained using DARC pre-trained weights with only 10% labeled data is already comparable to the network trained from scratch with 100% training data. The network using DARC pre-trained weights achieves the fastest convergence speed on the downstream classification task. Moreover, visualization through t-distributed stochastic neighbor embedding (t-SNE) shows that the learned representations are generalizable and discriminative.

Prediction of Glioma Grade Using Intratumoral and Peritumoral Radiomic Features From Multiparametric MRI Images.

The accurate prediction of glioma grade before surgery is essential for treatment planning and prognosis. Since the gold standard (i.e., biopsy)for grading gliomas is both highly invasive and expensive, and there is a need for a noninvasive and accurate method. In this study, we proposed a novel radiomics-based pipeline by incorporating the intratumoral and peritumoral features extracted from preoperative mpMRI scans to accurately and noninvasively predict glioma grade. To address the unclear peritumoral boundary, we designed an algorithm to capture the peritumoral region with a specified radius. The mpMRI scans of 285 patients derived from a multi-institutional study were adopted. A total of 2153 radiomic features were calculated separately from intratumoral volumes (ITVs)and peritumoral volumes (PTVs)on mpMRI scans, and then refined using LASSO and mRMR feature ranking methods. The top-ranking radiomic features were entered into the classifiers to build radiomic signatures for predicting glioma grade. The prediction performance was evaluated with five-fold cross-validation on a patient-level split. The radiomic signatures utilizing the features of ITV and PTV both show a high accuracy in predicting glioma grade, with AUCs reaching 0.968. By incorporating the features of ITV and PTV, the AUC of IPTV radiomic signature can be increased to 0.975, which outperforms the state-of-the-art methods. Additionally, our proposed method was further demonstrated to have strong generalization performance in an external validation dataset with 65 patients. The source code of our implementation is made publicly available at https://github.com/chengjianhong/glioma_grading.git.

Multimodal Disentangled Variational Autoencoder With Game Theoretic Interpretability for Glioma Grading.

Effective fusion of multimodal magnetic resonance imaging (MRI) is of great significance to boost the accuracy of glioma grading thanks to the complementary information provided by different imaging modalities. However, how to extract the common and distinctive information from MRI to achieve complementarity is still an open problem in information fusion research. In this study, we propose a deep neural network model termed as multimodal disentangled variational autoencoder (MMD-VAE) for glioma grading based on radiomics features extracted from preoperative multimodal MRI images. Specifically, the radiomics features are quantized and extracted from the region of interest for each modality. Then, the latent representations of variational autoencoder for these features are disentangled into common and distinctive representations to obtain the shared and complementary data among modalities. Afterwards, cross-modality reconstruction loss and common-distinctive loss are designed to ensure the effectiveness of the disentangled representations. Finally, the disentangled common and distinctive representations are fused to predict the glioma grades, and SHapley Additive exPlanations (SHAP) is adopted to quantitatively interpret and analyze the contribution of the important features to grading. Experimental results on two benchmark datasets demonstrate that the proposed MMD-VAE model achieves encouraging predictive performance (AUC:0.9939) on a public dataset, and good generalization performance (AUC:0.9611) on a cross-institutional private dataset. These quantitative results and interpretations may help radiologists understand gliomas better and make better treatment decisions for improving clinical outcomes.

Automated Diagnosis of COVID-19 Using Deep Supervised Autoencoder With Multi-View Features From CT Images.

Accurate and rapid diagnosis of coronavirus disease 2019 (COVID-19) from chest CT scans is of great importance and urgency during the worldwide outbreak. However, radiologists have to distinguish COVID-19 pneumonia from other pneumonia in a large number of CT scans, which is tedious and inefficient. Thus, it is urgently and clinically needed to develop an efficient and accurate diagnostic tool to help radiologists to fulfill the difficult task. In this study, we proposed a deep supervised autoencoder (DSAE) framework to automatically identify COVID-19 using multi-view features extracted from CT images. To fully explore features characterizing CT images from different frequency domains, DSAE was proposed to learn the latent representation by multi-task learning. The proposal was designed to both encode valuable information from different frequency features and construct a compact class structure for separability. To achieve this, we designed a multi-task loss function, which consists of a supervised loss and a reconstruction loss. Our proposed method was evaluated on a newly collected dataset of 787 subjects including COVID-19 pneumonia patients, other pneumonia patients, and normal subjects without abnormal CT findings. Extensive experimental results demonstrated that our proposed method achieved encouraging diagnostic performance and may have potential clinical application for the diagnosis of COVID-19.

MLDRL: Multi-loss disentangled representation learning for predicting esophageal cancer response to neoadjuvant chemoradiotherapy using longitudinal CT images.

Accurate prediction of pathological complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT) is essential for clinical precision treatment. However, the existing methods of predicting pCR in esophageal cancer are based on the single stage data, which limits the performance of these methods. Effective fusion of the longitudinal data has the potential to improve the performance of pCR prediction, thanks to the combination of complementary information. In this study, we propose a new multi-loss disentangled representation learning (MLDRL) to realize the effective fusion of complementary information in the longitudinal data. Specifically, we first disentangle the latent variables of features in each stage into inherent and variational components. Then, we define a multi-loss function to ensure the effectiveness and structure of disentanglement, which consists of a cross-cycle reconstruction loss, an inherent-variational loss and a supervised classification loss. Finally, an adaptive gradient normalization algorithm is applied to balance the training of multiple loss terms by dynamically tuning the gradient magnitudes. Due to the cooperation of the multi-loss function and the adaptive gradient normalization algorithm, MLDRL effectively restrains the potential interference and achieves effective information fusion. The proposed method is evaluated on multi-center datasets, and the experimental results show that our method not only outperforms several state-of-art methods in pCR prediction, but also achieves better performance in the prognostic analysis of multi-center unlabeled datasets.

M2 Macrophage-derived exosomal miR-501 contributes to pubococcygeal muscle regeneration.

Pubococcygeal muscle injury can lead to stress urinary incontinence (SUI). M2 macrophages play a crucial role in myoblast differentiation during injured muscle regeneration. However, the underlying mechanism remains unclear. Recently, exosomes have attracted increasing attention due to their mediation of cell-to-cell communication. In this study, we found that M2 macrophages extensively infiltrated the pubococcygeal muscle on day 5 after injury (VD5) in vivo. Then, C2C12 myoblasts were treated with M2 macrophage-derived exosomes (M2-EXO) and the results revealed that these exosomes could promote myotube formation. MiR-501 was identified as one of the abundant microRNAs (miRNAs) selectively loaded in M2-EXO, and subsequently confirmed to promote C2C12 myoblast differentiation by targeting YY1. Moreover, in vivo experiments showed that M2-EXO improves the inflammatory cell infiltration and have a therapeutic effect on damaged pubococcygeal muscle in SUI models. Collectively, our present results provide new insights into the promyogenic mechanism of M2 macrophages and prove that M2 macrophage exosomal miR-501 may represent a potential therapeutic to promote recovery from diseases caused by muscle injury, including SUI.

CD47-retargeted oncolytic adenovirus armed with melanoma differentiation-associated gene-7/interleukin-24 suppresses in vivo leukemia cell growth.

Our previous studies have suggested that harboring a soluble coxsackie-adenovirus receptor-ligand (sCAR-ligand) fusion protein expression cassette in the viral genome may provide a universal method to redirect oncolytic adenoviruses to various membrane receptors on cancer cells resisting to serotype 5 adenovirus infection. We report here a novel oncolytic adenovirus vector redirected to CD47+ leukemia cells though carrying a sCAR-4N1 expression cassette in the viral genome, forming Ad.4N1, in which 4N1 represents the C-terminal CD47-binding domain of thrombospondin-1. The infection and cytotoxicity of Ad.4N1 in leukemia cells were determined to be mediated by the 4N1-CD47 interaction. Ad.4N1 was further engineered to harbor a gene encoding melanoma differentiation-associated gene-7/interleukin-24 (mda-7/IL-24), forming Ad.4N1-IL24, which replicated dramatically faster than Ad.4N1, and elicited significantly enhanced antileukemia effect in vitro and in a HL60/Luc xenograft mouse model. Our data suggest that Ad.4N1 could act as a novel oncolytic adenovirus vector for CD47+ leukemia targeting gene transfer, and Ad.4N1 harboring anticancer genes may provide novel antileukemia agents.