Guangyao Wu - Academia.edu (original) (raw)

Papers by Guangyao Wu

Objective To analyze the feature of proton MR spectroscopy ( 1H MRS) of cortical tubers in tubero... more Objective To analyze the feature of proton MR spectroscopy ( 1H MRS) of cortical tubers in tuberous sclerosis complex and to explain the pathology of cortical tuber. Methods Single-voxel PRESS 1H MRS were performed in 25 patients with clinically confirmed tuberous sclerosis complex. Region of interest included the cortical tubers and corresponding regions in the contralateral hemisphere. Then the both-side metabolites and the ratios of NAA/Cr and Cho/Cr were compared. Results Fifty single-voxel 1H MRS showed symmetric Cr peak and absence of Lac peak. The ratio of NAA/Cr (medium value 1.46±0.07; range 1.33-1.57) in 25 cortical tubers was significantly lower (t=3.024, P=0.004) than that (medium value 1.54±0.11; range 1.49-1.78 ) of normal side. However, no significant differences (t=0.339, P=0.736) were found in the mean ratio of Cho/Cr between cortical tubers (1.02±0.12) and normal side (1.00±0.15). Conclusion NAA/Cr of cortical tuber in tuberous sclerosis complex significantly decreases, but Cho is stable, as explain that possible pathological characteristics are immature neuron and/or glia.

Korean Journal of Radiology

Objective: To investigate the image quality of ultralow-dose CT (ULDCT) of the chest reconstructe... more Objective: To investigate the image quality of ultralow-dose CT (ULDCT) of the chest reconstructed using a cycle-consistent generative adversarial network (CycleGAN)-based deep learning method in the evaluation of pulmonary tuberculosis. Materials and Methods: Between June 2019 and November 2019, 103 patients (mean age, 40.8 ± 13.6 years; 61 men and 42 women) with pulmonary tuberculosis were prospectively enrolled to undergo standard-dose CT (120 kVp with automated exposure control), followed immediately by ULDCT (80 kVp and 10 mAs). The images of the two successive scans were used to train the CycleGAN framework for image-to-image translation. The denoising efficacy of the CycleGAN algorithm was compared with that of hybrid and model-based iterative reconstruction. Repeated-measures analysis of variance and Wilcoxon signedrank test were performed to compare the objective measurements and the subjective image quality scores, respectively. Results: With the optimized CycleGAN denoising model, using the ULDCT images as input, the peak signal-to-noise ratio and structural similarity index improved by 2.0 dB and 0.21, respectively. The CycleGAN-generated denoised ULDCT images typically provided satisfactory image quality for optimal visibility of anatomic structures and pathological findings, with a lower level of image noise (mean ± standard deviation [SD], 19.5 ± 3.0 Hounsfield unit [HU]) than that of the hybrid (66.3 ± 10.5 HU, p < 0.001) and a similar noise level to model-based iterative reconstruction (19.6 ± 2.6 HU, p > 0.908). The CycleGAN-generated images showed the highest contrast-to-noise ratios for the pulmonary lesions, followed by the model-based and hybrid iterative reconstruction. The mean effective radiation dose of ULDCT was 0.12 mSv with a mean 93.9% reduction compared to standard-dose CT. Conclusion: The optimized CycleGAN technique may allow the synthesis of diagnostically acceptable images from ULDCT of the chest for the evaluation of pulmonary tuberculosis.

Journal of Personalized Medicine, 2022

The most common idiopathic interstitial lung disease (ILD) is idiopathic pulmonary fibrosis (IPF)... more The most common idiopathic interstitial lung disease (ILD) is idiopathic pulmonary fibrosis (IPF). It can be identified by the presence of usual interstitial pneumonia (UIP) via high-resolution computed tomography (HRCT) or with the use of a lung biopsy. We hypothesized that a CT-based approach using handcrafted radiomics might be able to identify IPF patients with a radiological or histological UIP pattern from those with an ILD or normal lungs. A total of 328 patients from one center and two databases participated in this study. Each participant had their lungs automatically contoured and sectorized. The best radiomic features were selected for the random forest classifier and performance was assessed using the area under the receiver operator characteristics curve (AUC). A significant difference in the volume of the trachea was seen between a normal state, IPF, and non-IPF ILD. Between normal and fibrotic lungs, the AUC of the classification model was 1.0 in validation. When clas...

ObjectiveThe current pandemic has led to a proliferation of predictive models being developed to ... more ObjectiveThe current pandemic has led to a proliferation of predictive models being developed to address various aspects of COVID-19 patient care. We aimed to develop an online platform that would serve as an open source repository for a curated subset of such models, and provide a simple interface for included models to allow for online calculation. This platform would support doctors during decision-making regarding diagnoses, prognoses, and follow-up of COVID-19 patients, expediting the models’ transition from research to clinical practice.MethodsIn this proof-of-principle study, we performed a literature search in PubMed and WHO database to find suitable models for implementation on our platform. All selected models were publicly available (peer reviewed publications or open source repository) and had been validated (TRIPOD type 3 or 2b). We created a method for obtaining the regression coefficients if only the nomogram was available in the original publication. All predictive m...

European Radiology, 2021

Objectives An accurate and rapid diagnosis is crucial for the appropriate treatment of pulmonary ... more Objectives An accurate and rapid diagnosis is crucial for the appropriate treatment of pulmonary tuberculosis (TB). This study aims to develop an artificial intelligence (AI)-based fully automated CT image analysis system for detection, diagnosis, and burden quantification of pulmonary TB. Methods From December 2007 to September 2020, 892 chest CT scans from pathogen-confirmed TB patients were retrospectively included. A deep learning-based cascading framework was connected to create a processing pipeline. For training and validation of the model, 1921 lesions were manually labeled, classified according to six categories of critical imaging features, and visually scored regarding lesion involvement as the ground truth. A "TB score" was calculated based on a network-activation map to quantitively assess the disease burden. Independent testing datasets from two additional hospitals (dataset 2, n = 99; dataset 3, n = 86) and the NIH TB Portals (n = 171) were used to externally validate the performance of the AI model. Results CT scans of 526 participants (mean age, 48.5 ± 16.5 years; 206 women) were analyzed. The lung lesion detection subsystem yielded a mean average precision of the validation cohort of 0.68. The overall classification accuracy of six pulmonary critical imaging findings indicative of TB of the independent datasets was 81.08-91.05%. A moderate to strong correlation was demonstrated between the AI model-quantified TB score and the radiologist-estimated CT score. Conclusions The proposed end-to-end AI system based on chest CT can achieve human-level diagnostic performance for early detection and optimal clinical management of patients with pulmonary TB. Key Points • Deep learning allows automatic detection, diagnosis, and evaluation of pulmonary tuberculosis. • Artificial intelligence helps clinicians to assess patients with tuberculosis. • Pulmonary tuberculosis disease activity and treatment management can be improved.

Background: Tyrosine kinase inhibitors (TKIs) therapy is a standard treatment for patients with a... more Background: Tyrosine kinase inhibitors (TKIs) therapy is a standard treatment for patients with advanced non-small-cell lung carcinoma (NSCLC) when activating epidermal growth factor receptor (EGFR) mutations are detected. However, except for the well-studied EGFR mutations, most EGFR mutations lack treatment regimens. Methods: We constructed two EGFR variant libraries containing substitutions, deletions, or insertions using the saturation mutagenesis method. All the variants were located in the EGFR mutation hotspot (exons 18–21). The sensitivity of these variants to afatinib, erlotinib, gefitinib, icotinib, and osimertinib was systematically studied by determining their enrichment in massively parallel cytotoxicity assays using an endogenous EGFR-depleted cell line, PC9.Results: A total of 3,914 and 70,475 variants were detected in the constructed EGFR Substitution-Deletion (Sub-Del) and exon 20 Insertion (Ins) libraries, accounting for 99.3% and 55.8% of the designed variants, re...

PLOS ONE, 2021

ObjectiveTo establish whether one can build a mortality prediction model for COVID-19 patients ba... more ObjectiveTo establish whether one can build a mortality prediction model for COVID-19 patients based solely on demographics and comorbidity data that outperforms age alone. Such a model could be a precursor to implementing smart lockdowns and vaccine distribution strategies.MethodsThe training cohort comprised 2337 COVID-19 inpatients from nine hospitals in The Netherlands. The clinical outcome was death within 21 days of being discharged. The features were derived from electronic health records collected during admission. Three feature selection methods were used: LASSO, univariate using a novel metric, and pairwise (age being half of each pair). 478 patients from Belgium were used to test the model. All modeling attempts were compared against an age-only model.ResultsIn the training cohort, the mortality group’s median age was 77 years (interquartile range = 70–83), higher than the non-mortality group (median = 65, IQR = 55–75). The incidence of former/active smokers, male gender,...

Journal of International Medical Research, 2020

Objective To observe the hemostatic effect of prophylactic uterine artery embolization (UAE) in p... more Objective To observe the hemostatic effect of prophylactic uterine artery embolization (UAE) in patients with cesarean scar pregnancy (CSP) and to examine the risk factors for poor hemostasis. Methods Clinical data of 841 patients with CSP who underwent prophylactic UAE and curettage were retrospectively analyzed to evaluate the hemorrhage volume during curettage. A hemorrhage volume ≥200 mL was termed as poor hemostasis. The risk factors of poor hemostasis were analyzed and complications within 60 days postoperation were recorded. Results Among the 841 patients, 6.30% (53/841) had poor postoperative hemostasis. The independent risk factors of poor hemostasis were gestational sac size, parity, embolic agent diameter (>1000 μm), multivessel blood supply, and incomplete embolization. The main postoperative complications within 60 days after UAE were abdominal pain, low fever, nausea and vomiting, and buttock pain, with incidence rates of 71.22% (599/841), 47.44% (399/841), 39.12% (...

European Respiratory Journal, 2020

We would like to thank G.S. Collins, M. van Smeden, and R.D. Richard for their commentary on the ... more We would like to thank G.S. Collins, M. van Smeden, and R.D. Richard for their commentary on the design, analysis, and reporting of our article [1]. However, their comments seem to stem from a traditional biostatistics angle rather than from a translational research machine-learning approach and the overwhelming majority of criticisms arise from either misunderstandings or misreading.

Respiration, 2020

Medical imaging plays a key role in evaluating and monitoring lung diseases such as chronic obstr... more Medical imaging plays a key role in evaluating and monitoring lung diseases such as chronic obstructive pulmonary disease (COPD) and lung cancer. The application of artificial intelligence in medical imaging has transformed medical images into mineable data, by extracting and correlating quantitative imaging features with patients’ outcomes and tumor phenotype – a process termed radiomics. While this process has already been widely researched in lung oncology, the evaluation of COPD in this fashion remains in its infancy. Here we outline the main applications of radiomics in lung cancer and briefly review the workflow from image acquisition to the evaluation of model performance. Finally, we discuss the current assessments of COPD and the potential application of radiomics in COPD.

European Radiology, 2020

Objectives Develop a CT-based radiomics model and combine it with frozen section (FS) and clinica... more Objectives Develop a CT-based radiomics model and combine it with frozen section (FS) and clinical data to distinguish invasive adenocarcinomas (IA) from preinvasive lesions/minimally invasive adenocarcinomas (PM). Methods This multicenter study cohort of 623 lung adenocarcinomas was split into training (n = 331), testing (n = 143), and external validation dataset (n = 149). Random forest models were built using selected radiomics features, results from FS, lesion volume, clinical and semantic features, and combinations thereof. The area under the receiver operator characteristic curves (AUC) was used to evaluate model performances. The diagnosis accuracy, calibration, and decision curves of models were tested. Results The radiomics-based model shows good predictive performance and diagnostic accuracy for distinguishing IA from PM, with AUCs of 0.89, 0.89, and 0.88, in the training, testing, and validation datasets, respectively, and with corresponding accuracies of 0.82, 0.79, and ...

$Research paper thumbnail of Deep learning in fracture detection: a narrative review$

Gastroenterology Research and Practice, 2018

In the article titled "Computed Tomography Enterography: Quantitative Evaluation on Crohn's Disea... more In the article titled "Computed Tomography Enterography: Quantitative Evaluation on Crohn's Disease Activity" [1], the affiliation of the fifth author is incorrect as it should be the same as the first affiliation. The corrected affiliations are shown above.

Complementary therapies in clinical practice, 2018

To investigate whether the mindful exercise was more beneficial than non-mindful exercise for peo... more To investigate whether the mindful exercise was more beneficial than non-mindful exercise for people with schizophrenia. PubMed, Embase, Cochrane Library, and PsycINFO were searched from their onset to April 2017. Randomized controlled trials of schizophrenia were selected. Mindful exercises were yoga, tai chi or qigong. Non-mindful exercises included any type of purely physical exercise. Risk of bias was assessed using criteria in the Cochrane Handbook for Systematic Reviews of Interventions. Seven studies were identified. There were significant differences in favour of mindful exercise in psychiatric symptoms (total PANSS, 2 RCT, n = 101, MD -8.94, low-quality evidence) and "working memory" (1 RCT, n = 194, MD 0.39, low-quality). For outcomes of "attention" and social functioning, there was no clear difference. Four studies reported no adverse events. Mindful exercise was more beneficial over non-mindful exercise on some outcomes of psychiatric symptoms and cog...

Oncology letters, 2018

The aim of the present study was to investigate the significance and values of 3.0T diffusion wei... more The aim of the present study was to investigate the significance and values of 3.0T diffusion weighted imaging (DWI) to differentially diagnose benign and malignant space-occupying liver lesions. A total of 91 patients with liver space-occupying lesions (145 lesions) were admitted into Zhongnan Hospital of Wuhan University (Wuhan, China) from November 2015 to May 2016. Routine scanning, DWI and high-resolution T2-weighted imaging using spin-echo echo-planar imaging were performed on all patients, to compare the apparent diffusion coefficient (ADC) values of three regions of interest in lesions with normal liver tissue. The ADC values of malignant liver lesions compared with benign liver cysts demonstrated a statistically significant difference in low b-value (P<0.05) and there was also a significant difference between malignant lesion and hepatic cyst, hepatic hemangioma or hepatic abscess in middle b-value (P<0.05). The measured ADC value may be more conducive to identify the...

Molecular medicine reports, Jan 26, 2017

Parkinson's disease (PD) is an age‑associated neurodegenerative disorder characterized by the... more Parkinson's disease (PD) is an age‑associated neurodegenerative disorder characterized by the death of dopaminergic neurons in the substantia nigra pars compacta. Activation of 5'‑adenosine monophosphate‑activated protein kinase (AMPK) has been suggested to be associated with PD pathogenesis. The aim of the present study was to investigate the effects of the aberrant expression of microRNA‑185 (miR‑185) in PD. A 1‑methyl‑4‑phenyl‑1,2,3,6‑tetrahydropyridine (MPTP)‑induced in vitro model of PD was generated using the human SH‑SY5Y dopaminergic neuroblastoma cell line, in order to examine the potential molecular mechanisms underlying the roles of miR‑185 in PD. miR‑185 expression was assessed in MPTP-treated SH‑SY5Y cells using reverse transcription‑quantitative polymerase chain reaction (RT‑qPCR). In addition, MPTP‑treated SH‑SY5Y cells were transfected with a miR‑185 mimic or scramble miRNA, and flow cytometry was used to evaluate the level of cellular apoptosis. The expressi...

Bioprocess and biosystems engineering, Jan 2, 2016

ε-Poly-L-lysine (ε-PL), as a food additive, has been widely used in many countries. However, its ... more ε-Poly-L-lysine (ε-PL), as a food additive, has been widely used in many countries. However, its production still needs to be improved. We successfully enhanced ε-PL production of Streptomyces albulus FEEL-1 by introducing mutations related to antibiotics, such as streptomycin, gentamicin, and rifampin. Single- and double-resistant mutants (S-88 and SG-31) were finally screened with the improved ε-PL productions of 2.81 and 3.83 g/L, 1.75- to 2.39-fold compared with that of initial strain FEEL-1. Then, the performances of mutants S-88 and SG-31 were compared with the parent strain FEEL-1 in a 5-L bioreactor under the optimal condition for ε-PL production. After 174-h fed-batch fermentation, the ε-PL production and productivity of hyper-strain SG-31 reached the maximum of 59.50 g/L and 8.21 g/L/day, respectively, which was 138 and 105% higher than that of FEEL-1. Analysis of streptomycin-resistant mutants demonstrated that a point mutation occurred in rpsL gene (encoding the ribosoma...

Journal of magnetic resonance imaging : JMRI, Jan 29, 2016

To demonstrate the feasibility to quantify the lung respiratory airway in vivo with hyperpolarize... more To demonstrate the feasibility to quantify the lung respiratory airway in vivo with hyperpolarized xenon diffusion magnetic resonance imaging (MRI), which is able to detect mild emphysema in the rat model. The lung respiratory airways were quantified in vivo using hyperpolarized xenon diffusion MRI (7T) with eight b values (5, 10, 15, 20, 25, 30, 35, 40 s/cm(2) ) in five control rats and five mild emphysematous rats, which were induced by elastase. The morphological results from histology were acquired and used for comparison. The parameters DL (longitudinal diffusion coefficient), r (internal radius), h (alveolar sleeve depth), Lm (mean linear intercept), and S/V (surface area to lung volume ratio) derived from the hyperpolarized xenon diffusion MRI in the emphysematous group showed significant differences from those in the control group (P < 0.05). Additionally, these parameters correlated well with the Lm obtained by the traditional histological sections (Pearson's correla...

Experimental and Therapeutic Medicine, 2016

Lung cancer is the leading cause of cancer-associated mortality worldwide, although molecular ima... more Lung cancer is the leading cause of cancer-associated mortality worldwide, although molecular imaging techniques, including fludeoxyglucose positron emission tomography, have markedly improved the diagnosis of lung cancer. HIWI is a member of the human piwi family, members of which are known for their roles in RNA silencing. HIWI has been shown to serve a crucial function in stem cell self-renewal, and previous studies have reported HIWI overexpression in lung cancers. Furthermore, HIWI has been proposed to regulate the maintenance of cancer stem cell populations in lung cancers. The present study investigated the mRNA and protein expression levels of HIWI in non-small cell lung cancer (NSCLC) specimens harvested from 57 patients, using reverse transcription-quantitative polymerase chain reaction and western blot analysis, respectively. Subsequently, the HIWI expression level was manipulated using gain-of-function and loss-of-function strategies, and the role of HIWI in the proliferation of human A549 NSCLC cells was investigated using Cell Counting Kit-8 and colony formation assays. The mRNA and protein expression levels of HIWI were significantly upregulated in the intratumor NSCLC specimens, as compared with the peritumor specimens. Furthermore, the mRNA and protein expression levels of HIWI in A549 cells were successfully manipulated using the two strategies. Overexpression and knockout of HIWI were associated with the promotion and inhibition of A549 cell proliferation, respectively. The results of the present study suggested that HIWI is overexpressed in NSCLC tissues and demonstrated that upregulation of HIWI may promote the growth of lung cancer cells; thus suggesting that HIWI may have an oncogenic role in lung cancer.