Qi-Zhong Xu

Bio: Qi-Zhong Xu is an academic researcher from Shenzhen University. The author has contributed to research in topics: Receiver operating characteristic & Medicine. The author has an hindex of 2, co-authored 2 publications receiving 944 citations.

Using Artificial Intelligence to Detect COVID-19 and Community-acquired Pneumonia Based on Pulmonary CT: Evaluation of the Diagnostic Accuracy.

Abstract: Background Coronavirus disease 2019 (COVID-19) has widely spread all over the world since the beginning of 2020. It is desirable to develop automatic and accurate detection of COVID-19 using chest CT. Purpose To develop a fully automatic framework to detect COVID-19 using chest CT and evaluate its performance. Materials and Methods In this retrospective and multicenter study, a deep learning model, the COVID-19 detection neural network (COVNet), was developed to extract visual features from volumetric chest CT scans for the detection of COVID-19. CT scans of community-acquired pneumonia (CAP) and other non-pneumonia abnormalities were included to test the robustness of the model. The datasets were collected from six hospitals between August 2016 and February 2020. Diagnostic performance was assessed with the area under the receiver operating characteristic curve, sensitivity, and specificity. Results The collected dataset consisted of 4352 chest CT scans from 3322 patients. The average patient age (±standard deviation) was 49 years ± 15, and there were slightly more men than women (1838 vs 1484, respectively; P = .29). The per-scan sensitivity and specificity for detecting COVID-19 in the independent test set was 90% (95% confidence interval [CI]: 83%, 94%; 114 of 127 scans) and 96% (95% CI: 93%, 98%; 294 of 307 scans), respectively, with an area under the receiver operating characteristic curve of 0.96 (P < .001). The per-scan sensitivity and specificity for detecting CAP in the independent test set was 87% (152 of 175 scans) and 92% (239 of 259 scans), respectively, with an area under the receiver operating characteristic curve of 0.95 (95% CI: 0.93, 0.97). Conclusion A deep learning model can accurately detect coronavirus 2019 and differentiate it from community-acquired pneumonia and other lung conditions. © RSNA, 2020 Online supplemental material is available for this article.

Idiopathic Normal Pressure Hydrocephalus and Elderly Acquired Hydrocephalus: Evaluation With Cerebrospinal Fluid Flow and Ventricular Volume Parameters.

Abstract: Purpose To investigate differences in cerebrospinal fluid (CSF) flow through the aqueduct and to determine whether there is a relationship between CSF flow and ventricular volume parameters in idiopathic normal pressure hydrocephalus (iNPH) patients, elderly acquired hydrocephalus patients and age-matched healthy volunteers by phase-contrast MR (PC-MR). Methods A total of 40 iNPH patients and 41 elderly acquired hydrocephalus patients and 26 age-matched healthy volunteers in the normal control (NC) group were included between November 2017 and October 2019 in this retrospective study. The following CSF flow parameters were measured with PC-MR: peak velocity, average velocity (AV), aqueductal stroke volume (ASV), net ASV, and net flow. The following ventricular volume parameters were measured: ventricular volume (VV), brain volume, total intracranial volume, and relative VV. Differences between the iNPH and acquired hydrocephalus groups were compared Mann-Whitney U test and correlations between CSF flow and ventricular volume parameters were assessed using the Spearman correlation coefficient. Results Aqueductal stroke volume was significantly higher in the iNPH and acquired hydrocephalus groups than in the NC group, but did not differ significantly between the iNPH group and acquired hydrocephalus group. The AV, net ASV, and net flow in the iNPH and acquired hydrocephalus groups were significantly higher than those in the NC group (P < 0.0001), and those in the acquired hydrocephalus group were significantly higher than those in the iNPH group (P = 0.01, P = 0.007, P = 0.002, respectively). The direction of the AV and net ASV significantly differed among the three groups. There were no associations between the volume parameters and CSF flow according to PC-MR among the three groups. Conclusion Compared with iNPH, elderly acquired hydrocephalus demonstrated higher CSF hyperdynamic flow. Although increased CSF flow may contribute to further changes in ventricular morphology, there is no linear relationship between them. These findings might help increase our understanding of flow dynamics in iNPH and elderly acquired hydrocephalus.

Are preoperative phase-contrast CSF flow parameters ideal for predicting the outcome of shunt surgery in patients with idiopathic normal pressure hydrocephalus?

Abstract: Purpose Phase-contrast magnetic resonance (PC-MR) is widely used in patients with idiopathic normal pressure hydrocephalus (iNPH), but its role in predicting prognosis remains controversial. To evaluate the effectiveness of preoperative PC-MR CSF flow measurement in predicting the clinical response to shunt surgery in patients with iNPH. Methods Forty-six patients with definite iNPH were included between January 2018 and January 2022. PC-MR was used to evaluate CSF peak velocity (PV), average velocity, aqueductal stroke volume (ASV), net ASV, and net flow. The modified Rankin Scale (mRS), iNPH grading scale (iNPHGS), Mini-Mental State Examination (MMSE), and Timed 3-m Up and Go Test (TUG) were used for clinical assessment. The primary endpoint was the improvement in the mRS score 1 year after surgery, and the secondary endpoints were the iNPHGS, MMSE, and TUG scores at 1 year. Differences between shunt improvement and non-improvement groups, based on the clinical outcomes, were compared using the Mann-Whitney U-test, logistic regression models, and receiver operating characteristic curves. Correlations between CSF flow parameters and the baseline clinical outcomes were assessed using Spearman's correlation coefficient. Results No CSF parameters significantly differed between shunt improvement and non-improvement groups based on mRS and secondary outcomes. And all CSF parameters showed significant overlap in both shunt improvement and non-improvement groups based on mRS and secondary outcomes. Significant correlations between the mRS and iNPHGS scores, and PV, ASV, and net ASV were observed. Conclusion While some preoperative PC-MR CSF flow parameters reflected the symptom severity of iNPH to a certain extent, they alone might not be ideal markers of shunt responsiveness.

Primary intraosseous Rosai–Dorfman disease: An analysis of clinicopathologic characteristics, molecular genetics, and prognostic features

Abstract: Background Rosai–Dorfman disease (RDD) is a rare histiocytic proliferative disorder of uncertain pathogenesis. Most patients present with proliferation in the lymph nodes manifesting as adenopathy; however, RDD may primarily arise in a variety of extranodal sites, including the bone, which is a great challenge in the diagnosis. The clinicopathological characteristics and prognostic features of primary intraosseous RDD have not been well characterized. Methods We retrospectively analyzed the clinicopathologic and prognostic features of four cases of primary intraosseous RDD during the past 10 years in our hospital, with a review of an additional 62 cases with complete follow-up data from the literature. Results Primary intraosseous RDD was identified in 0.14% (4/2,800) of total bone biopsies performed at our institution over the study period. According to our retrospective analysis, a total of 18 cases of primary lymph node, skin, or other non-osseous site-based RDD were diagnosed in our hospital. The ages of the 66 total patients ranged from 1.5 to 76 years, with a median age of 25 years. There were 31 male and 35 female patients, with a male-to-female ratio of 0.89:1. Primary intraosseous RDD occurred most often in the bones of the extremities (60.6%, 40/66), with the proximal tibia being the most common location; 39.4% (26/66) of the cases arose in the axial skeleton, predominantly in the vertebra and craniofacial bones. Solitary masses and multiple tumors were present in 84.8% (56/66) and 15.2% (10/66) of the cases, respectively. Pain of the affected area was the most common presenting symptom. Radiographically, the lesions were lytic with well-defined and usually sclerotic margins. Immunohistochemistry showed that large histiocytes from patients with RDD were positive for OCT2, in addition to S100 and CD68. Molecular tests were performed in seven reported cases and four of our cases. All the 11 cases were non-decalcified. PCR results showed that there were no BRAF-V600E, KRAS, or NRAS mutations in primary intraosseous RDD; only one case with both RDD and Langerhans cell histiocytosis showed BRAF-V600E mutation. The survival data showed that 22.7% (15/66) of the patients experienced recurrences or developed RDD at distant sites during the follow-up period (median follow-up, 13 months; range, 1–106 months). The 5-year progression-free survival (PFS) of the patients with primary intraosseous RDD was 57.5%. We found that there was a significant difference in PFS between female and male patients (p = 0.031). However, there was no statistically significant difference in PFS between patients with solitary masses and multiple tumors (p = 0.698). Similarly, no statistically significant differences in PFS were found between the different age groups (p = 0.908) or tumor locations (p = 0.728). Conclusion Primary intraosseous RDD is an extremely rare disease. The diagnosis of RDD may be quite challenging because of its non-specific clinical presentation and imaging. Immunohistochemistry showed that large histiocytes were positive for OCT2 in addition to S100 and CD68, which may be helpful for differential diagnosis. Molecular detection showed that RDD may be related to the MAPK pathway, though these results are also ultimately not specific. The pathogenesis of RDD is yet to be elucidated, but recent studies suggest possible clonality of hyperproliferative histiocytes.

COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images.

Abstract: The Coronavirus Disease 2019 (COVID-19) pandemic continues to have a devastating effect on the health and well-being of the global population. A critical step in the fight against COVID-19 is effective screening of infected patients, with one of the key screening approaches being radiology examination using chest radiography. It was found in early studies that patients present abnormalities in chest radiography images that are characteristic of those infected with COVID-19. Motivated by this and inspired by the open source efforts of the research community, in this study we introduce COVID-Net, a deep convolutional neural network design tailored for the detection of COVID-19 cases from chest X-ray (CXR) images that is open source and available to the general public. To the best of the authors' knowledge, COVID-Net is one of the first open source network designs for COVID-19 detection from CXR images at the time of initial release. We also introduce COVIDx, an open access benchmark dataset that we generated comprising of 13,975 CXR images across 13,870 patient patient cases, with the largest number of publicly available COVID-19 positive cases to the best of the authors' knowledge. Furthermore, we investigate how COVID-Net makes predictions using an explainability method in an attempt to not only gain deeper insights into critical factors associated with COVID cases, which can aid clinicians in improved screening, but also audit COVID-Net in a responsible and transparent manner to validate that it is making decisions based on relevant information from the CXR images. By no means a production-ready solution, the hope is that the open access COVID-Net, along with the description on constructing the open source COVIDx dataset, will be leveraged and build upon by both researchers and citizen data scientists alike to accelerate the development of highly accurate yet practical deep learning solutions for detecting COVID-19 cases and accelerate treatment of those who need it the most.

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.

Coronavirus Disease 2019–COVID-19

Abstract: SUMMARYIn recent decades, several new diseases have emerged in different geographical areas, with pathogens including Ebola virus, Zika virus, Nipah virus, and coronaviruses (CoVs). Recently, a new type of viral infection emerged in Wuhan City, China, and initial genomic sequencing data of this virus do not match with previously sequenced CoVs, suggesting a novel CoV strain (2019-nCoV), which has now been termed severe acute respiratory syndrome CoV-2 (SARS-CoV-2). Although coronavirus disease 2019 (COVID-19) is suspected to originate from an animal host (zoonotic origin) followed by human-to-human transmission, the possibility of other routes should not be ruled out. Compared to diseases caused by previously known human CoVs, COVID-19 shows less severe pathogenesis but higher transmission competence, as is evident from the continuously increasing number of confirmed cases globally. Compared to other emerging viruses, such as Ebola virus, avian H7N9, SARS-CoV, and Middle East respiratory syndrome coronavirus (MERS-CoV), SARS-CoV-2 has shown relatively low pathogenicity and moderate transmissibility. Codon usage studies suggest that this novel virus has been transferred from an animal source, such as bats. Early diagnosis by real-time PCR and next-generation sequencing has facilitated the identification of the pathogen at an early stage. Since no antiviral drug or vaccine exists to treat or prevent SARS-CoV-2, potential therapeutic strategies that are currently being evaluated predominantly stem from previous experience with treating SARS-CoV, MERS-CoV, and other emerging viral diseases. In this review, we address epidemiological, diagnostic, clinical, and therapeutic aspects, including perspectives of vaccines and preventive measures that have already been globally recommended to counter this pandemic virus.

Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation, and Diagnosis for COVID-19

Abstract: The pandemic of coronavirus disease 2019 (COVID-19) is spreading all over the world. Medical imaging such as X-ray and computed tomography (CT) plays an essential role in the global fight against COVID-19, whereas the recently emerging artificial intelligence (AI) technologies further strengthen the power of the imaging tools and help medical specialists. We hereby review the rapid responses in the community of medical imaging (empowered by AI) toward COVID-19. For example, AI-empowered image acquisition can significantly help automate the scanning procedure and also reshape the workflow with minimal contact to patients, providing the best protection to the imaging technicians. Also, AI can improve work efficiency by accurate delineation of infections in X-ray and CT images, facilitating subsequent quantification. Moreover, the computer-aided platforms help radiologists make clinical decisions, i.e., for disease diagnosis, tracking, and prognosis. In this review paper, we thus cover the entire pipeline of medical imaging and analysis techniques involved with COVID-19, including image acquisition, segmentation, diagnosis, and follow-up. We particularly focus on the integration of AI with X-ray and CT, both of which are widely used in the frontline hospitals, in order to depict the latest progress of medical imaging and radiology fighting against COVID-19.

Artificial Intelligence (AI) applications for COVID-19 pandemic.

Abstract: Background and aims Healthcare delivery requires the support of new technologies like Artificial Intelligence (AI), Internet of Things (IoT), Big Data and Machine Learning to fight and look ahead against the new diseases. We aim to review the role of AI as a decisive technology to analyze, prepare us for prevention and fight with COVID-19 (Coronavirus) and other pandemics. Methods The rapid review of the literature is done on the database of Pubmed, Scopus and Google Scholar using the keyword of COVID-19 or Coronavirus and Artificial Intelligence or AI. Collected the latest information regarding AI for COVID-19, then analyzed the same to identify its possible application for this disease. Results We have identified seven significant applications of AI for COVID-19 pandemic. This technology plays an important role to detect the cluster of cases and to predict where this virus will affect in future by collecting and analyzing all previous data. Conclusions Healthcare organizations are in an urgent need for decision-making technologies to handle this virus and help them in getting proper suggestions in real-time to avoid its spread. AI works in a proficient way to mimic like human intelligence. It may also play a vital role in understanding and suggesting the development of a vaccine for COVID-19. This result-driven technology is used for proper screening, analyzing, prediction and tracking of current patients and likely future patients. The significant applications are applied to tracks data of confirmed, recovered and death cases.