Qi Zhang

Bio: Qi Zhang is an academic researcher from Fudan University. The author has contributed to research in topics: Medicine & Ultrasound. The author has an hindex of 20, co-authored 100 publications receiving 1563 citations. Previous affiliations of Qi Zhang include Minjiang University & Duke University.

3-D Gabor-based anisotropic diffusion for speckle noise suppression in dynamic ultrasound images.

Abstract: Speckle noise contaminates medical ultrasound images, and the suppression of speckle noise is helpful for image interpretation. Traditional ultrasound denoising (i.e., despeckling) methods are developed on two-dimensional static images. However, one of the advantages of ultrasonography is its nature of dynamic imaging. A method for dynamic ultrasound despeckling is expected to incorporate both the spatial and temporal information in successive images of dynamic ultrasound and thus yield better denoising performance. Here we regard a dynamic ultrasound video as three-dimensional (3-D) images with two dimensions in the spatial domain and one in the temporal domain, and we propose a despeckling algorithm for dynamic ultrasound named the 3-D Gabor-based anisotropic diffusion (GAD-3D). The GAD-3D expands the classic two-dimensional Gabor-based anisotropic diffusion (GAD) into 3-D domain. First, we proposed a robust 3-D Gabor-based edge detector by capturing the edge with 3-D Gabor transformation. Then we embed this novel detector into the partial differential equation of GAD to guide the 3-D diffusion process. In the simulation experiment, when the noise variance is as high as 0.14, the GAD-3D improves the Pratt's figure of merit, mean structural similarity index and peak signal-to-noise ratio by 24.32%, 10.98%, and 6.51%, respectively, compared with the best values of seven other methods. Experimental results on clinical dynamic ultrasonography suggest that the GAD-3D outperforms the other seven methods in noise reduction and detail preservation. The GAD-3D is effective for dynamic ultrasound despeckling and may be potentially valuable for disease assessment in dynamic medical ultrasonography.

Speckle Suppression of Ultrasonography Using Maximum Likelihood Estimation and Weighted Nuclear Norm Minimization

Abstract: Speckle noise corrupts medical ultrasound images and suppression of speckle noise is valuable for image interpretation. This paper presents a new method for speckle suppression named the maximum likelihood based weighted nuclear norm minimization (MLWNNM) filtering by integrating the maximum likelihood estimation (MLE) with the weighted nuclear norm minimization (WNNM). The MLE is first used to get an initially filtered image with reduced Rayleigh distributed noise, and then the WNNM is applied to further improve the denoising effect by preserving and enhancing tissue details. Simulation work shows that when the noise variance is as high as 0.14, the MLWNNM improves the Pratt’s figure of merit, peak signal to noise ratio, and mean structural similarity by 123.51%, 0.84%, and 6.13%, respectively, in contrast to the best values of other six methods. Experimental results on clinical ultrasound images suggest that the MLWNNM outperforms other six methods in noise reduction and detail preservation.

Segmentation of Lymph Nodes in Ultrasound Images Using U-Net Convolutional Neural Networks and Gabor-Based Anisotropic Diffusion

Abstract: The automated segmentation of lymph nodes (LNs) in ultrasound images is challenging, largely because of speckle noise and echogenic hila. This paper proposes a fully automatic and accurate method for LN segmentation in ultrasound that overcomes these issues. The proposed segmentation method integrates diffusion-based despeckling, U-Net convolutional neural networks and morphological operations. First, the speckle noise is suppressed and the lymph node edges are enhanced using Gabor-based anisotropic diffusion (GAD). Then, a modified U-Net model is used to segment the LNs excluding any echogenic hila. Finally, morphological operations are undertaken to segment the entire LNs by filling in any regions occupied by echogenic hila. A total of 531 lymph nodes from 526 patients were segmented using the proposed method. Its segmentation performance was evaluated in terms of its accuracy, sensitivity, specificity, Jaccard similarity and Dice coefficient, for which it achieved values of 0.934, 0.939, 0.937, 0.763 and 0.865, respectively. The proposed method automatically and accurately segments LNs in ultrasound images, enhancing the prospects of being able to undertake artificial intelligence (AI)-based diagnosis of lymph node diseases.

Prediction of Disturbed Flow by Factor Analysis of Carotid Bifurcation Geometry

Abstract: Hemodynamics plays an important role in the development and progression of carotid artery atherosclerotic lesions. Certain aspects of vascular geometry, which mediates local hemodynamics, might be risk factors that increase a vessel’s atherosusceptibility [1]. To further evaluate this “geometric risk factor” hypothesis, the relationship between geometric features and hemodynamic quantities thought to typify “disturbed flow” was recently investigated [2]. Fourteen intercorrelated geometric features were initially extracted from MR images of 50 carotid bifurcations, and multivariate regression based on an a priori selection of a subset of four of these geometric features was used to identify two that were predictors of disturbed hemodynamics. Here, this work is extended to simultaneously analyze the combined role of all geometric variables using factor analysis.Copyright © 2009 by ASME

Robust sound event classification with bilinear multi-column ELM-AE and two-stage ensemble learning

Abstract: The automatic sound event classification (SEC) has attracted a growing attention in recent years Feature extraction is a critical factor in SEC system, and the deep neural network (DNN) algorithms have achieved the state-of-the-art performance for SEC The extreme learning machine-based auto-encoder (ELM-AE) is a new deep learning algorithm, which has both an excellent representation performance and very fast training procedure However, ELM-AE suffers from the problem of unstability In this work, a bilinear multi-column ELM-AE (B-MC-ELM-AE) algorithm is proposed to improve the robustness, stability, and feature representation of the original ELM-AE, which is then applied to learn feature representation of sound signals Moreover, a B-MC-ELM-AE and two-stage ensemble learning (TsEL)-based feature learning and classification framework is then developed to perform the robust and effective SEC The experimental results on the Real World Computing Partnership Sound Scene Database show that the proposed SEC framework outperforms the state-of-the-art DNN algorithm

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study

Abstract: Summary Background Since December, 2019, Wuhan, China, has experienced an outbreak of coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Epidemiological and clinical characteristics of patients with COVID-19 have been reported but risk factors for mortality and a detailed clinical course of illness, including viral shedding, have not been well described. Methods In this retrospective, multicentre cohort study, we included all adult inpatients (≥18 years old) with laboratory-confirmed COVID-19 from Jinyintan Hospital and Wuhan Pulmonary Hospital (Wuhan, China) who had been discharged or had died by Jan 31, 2020. Demographic, clinical, treatment, and laboratory data, including serial samples for viral RNA detection, were extracted from electronic medical records and compared between survivors and non-survivors. We used univariable and multivariable logistic regression methods to explore the risk factors associated with in-hospital death. Findings 191 patients (135 from Jinyintan Hospital and 56 from Wuhan Pulmonary Hospital) were included in this study, of whom 137 were discharged and 54 died in hospital. 91 (48%) patients had a comorbidity, with hypertension being the most common (58 [30%] patients), followed by diabetes (36 [19%] patients) and coronary heart disease (15 [8%] patients). Multivariable regression showed increasing odds of in-hospital death associated with older age (odds ratio 1·10, 95% CI 1·03–1·17, per year increase; p=0·0043), higher Sequential Organ Failure Assessment (SOFA) score (5·65, 2·61–12·23; p Interpretation The potential risk factors of older age, high SOFA score, and d-dimer greater than 1 μg/mL could help clinicians to identify patients with poor prognosis at an early stage. Prolonged viral shedding provides the rationale for a strategy of isolation of infected patients and optimal antiviral interventions in the future. Funding Chinese Academy of Medical Sciences Innovation Fund for Medical Sciences; National Science Grant for Distinguished Young Scholars; National Key Research and Development Program of China; The Beijing Science and Technology Project; and Major Projects of National Science and Technology on New Drug Creation and Development.

Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal

Abstract: Objective To review and appraise the validity and usefulness of published and preprint reports of prediction models for diagnosing coronavirus disease 2019 (covid-19) in patients with suspected infection, for prognosis of patients with covid-19, and for detecting people in the general population at increased risk of covid-19 infection or being admitted to hospital with the disease. Design Living systematic review and critical appraisal by the COVID-PRECISE (Precise Risk Estimation to optimise covid-19 Care for Infected or Suspected patients in diverse sEttings) group. Data sources PubMed and Embase through Ovid, up to 1 July 2020, supplemented with arXiv, medRxiv, and bioRxiv up to 5 May 2020. Study selection Studies that developed or validated a multivariable covid-19 related prediction model. Data extraction At least two authors independently extracted data using the CHARMS (critical appraisal and data extraction for systematic reviews of prediction modelling studies) checklist; risk of bias was assessed using PROBAST (prediction model risk of bias assessment tool). Results 37 421 titles were screened, and 169 studies describing 232 prediction models were included. The review identified seven models for identifying people at risk in the general population; 118 diagnostic models for detecting covid-19 (75 were based on medical imaging, 10 to diagnose disease severity); and 107 prognostic models for predicting mortality risk, progression to severe disease, intensive care unit admission, ventilation, intubation, or length of hospital stay. The most frequent types of predictors included in the covid-19 prediction models are vital signs, age, comorbidities, and image features. Flu-like symptoms are frequently predictive in diagnostic models, while sex, C reactive protein, and lymphocyte counts are frequent prognostic factors. Reported C index estimates from the strongest form of validation available per model ranged from 0.71 to 0.99 in prediction models for the general population, from 0.65 to more than 0.99 in diagnostic models, and from 0.54 to 0.99 in prognostic models. All models were rated at high or unclear risk of bias, mostly because of non-representative selection of control patients, exclusion of patients who had not experienced the event of interest by the end of the study, high risk of model overfitting, and unclear reporting. Many models did not include a description of the target population (n=27, 12%) or care setting (n=75, 32%), and only 11 (5%) were externally validated by a calibration plot. The Jehi diagnostic model and the 4C mortality score were identified as promising models. Conclusion Prediction models for covid-19 are quickly entering the academic literature to support medical decision making at a time when they are urgently needed. This review indicates that almost all pubished prediction models are poorly reported, and at high risk of bias such that their reported predictive performance is probably optimistic. However, we have identified two (one diagnostic and one prognostic) promising models that should soon be validated in multiple cohorts, preferably through collaborative efforts and data sharing to also allow an investigation of the stability and heterogeneity in their performance across populations and settings. Details on all reviewed models are publicly available at https://www.covprecise.org/. Methodological guidance as provided in this paper should be followed because unreliable predictions could cause more harm than benefit in guiding clinical decisions. Finally, prediction model authors should adhere to the TRIPOD (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) reporting guideline. Systematic review registration Protocol https://osf.io/ehc47/, registration https://osf.io/wy245. Readers’ note This article is a living systematic review that will be updated to reflect emerging evidence. Updates may occur for up to two years from the date of original publication. This version is update 3 of the original article published on 7 April 2020 (BMJ 2020;369:m1328). Previous updates can be found as data supplements (https://www.bmj.com/content/369/bmj.m1328/related#datasupp). When citing this paper please consider adding the update number and date of access for clarity.