Yu Deng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yu Deng has a total of 141 co-authors. Here are the top co-authors by number of shared publications:
Xilai Chen
4 shared publicationsQiuxi Lin
3 shared publicationsYongxia Lei
3 shared publicationsCheng Cheng
2 shared publicationsTing Ma
Department of Radiology, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China
2 shared publications- Ting Ma
Department of Radiology, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong Province, P.R. China
2 shared publications
Latest Publications
- Open Access
- 12 November 2026
- Published by Springer Nature in Insights into Imaging
- Vol. 17 (1)
Assessment of atrioventricular interaction and response to balloon pulmonary angioplasty in chronic thromboembolic pulmonary hypertension using cardiac MRI
Objectives: This study aimed to evaluate atrioventricular interaction in patients with chronic thromboembolic pulmonary hypertension (CTEPH) and to determine the effects of balloon pulmonary angioplasty (BPA) on reversible cardiac remodeling assessed by cardiac magnetic resonance (CMR) imaging. Materials and methods: In this prospective single-center study, 52 patients with CTEPH (mean age: 58 ± 11 years; 34 females) and 35 healthy controls underwent CMR imaging. Twenty-five patients (mean age: 60 ± 12 years; 19 females) who underwent BPA received follow-up CMR at a mean interval of 7 ± 5 months. Cardiac structure, function, myocardial deformation, and epicardial adipose tissue (EAT) were assessed based on cine images. Results: Compared with controls, patients with CTEPH demonstrated predominant right-sided cardiac involvement, characterized by reduced right ventricular ejection fraction ( p < 0.001), marked enlargement of right atrial (RA) and ventricular (RV) volumes, and severely impaired right heart strain (all p < 0.001). Left ventricular systolic function was relatively preserved, with mildly impaired global circumferential strain ( p = 0.011) and a trend toward attenuated longitudinal strain ( p = 0.055), whereas all left atrial (LA) strain components were markedly impaired (all p < 0.05), indicating altered atrioventricular interaction. Following BPA, the right heart structure, RV function and deformation, and LA conduit strain improved. EAT was comparable between groups and remained unchanged after BPA. Conclusion: CTEPH involves marked right heart systolic dysfunction and early biventricular diastolic abnormalities associated with impaired atrioventricular interaction. BPA could reverse cardiac remodeling by improving right heart structure, function, and partially recovering atrial deformation after pressure relief. Key Points: Questions Atrioventricular interaction abnormalities and reversible cardiac remodeling in chronic thromboembolic pulmonary hypertension (CTEPH) after balloon pulmonary angioplasty (BPA) remain insufficiently characterized. Findings CTEPH is associated with impaired right heart strain and altered atrioventricular interaction; BPA improves right heart structure and function and partially recovers atrial deformation. Critical relevance statement Cardiac MRI-derived myocardial deformation and atrial phasic function may reflect alterations in atrioventricular interaction in CTEPH and complement conventional metrics in assessing cardiac remodeling and recovery after BPA.
- 12 November 2026
- Published by Springer Nature in Insights into Imaging
- Vol. 17 (1)
Open AccessAssessment of atrioventricular interaction and response to balloon pulmonary angioplasty in chronic thromboembolic pulmonary hypertension using cardiac MRI
Objectives: This study aimed to evaluate atrioventricular interaction in patients with chronic thromboembolic pulmonary hypertension (CTEPH) and to determine the effects of balloon pulmonary angioplasty (BPA) on reversible cardiac remodeling assessed by cardiac magnetic resonance (CMR) imaging. Materials and methods: In this prospective single-center study, 52 patients with CTEPH (mean age: 58 ± 11 years; 34 females) and 35 healthy controls underwent CMR imaging. Twenty-five patients (mean age: 60 ± 12 years; 19 females) who underwent BPA received follow-up CMR at a mean interval of 7 ± 5 months. Cardiac structure, function, myocardial deformation, and epicardial adipose tissue (EAT) were assessed based on cine images. Results: Compared with controls, patients with CTEPH demonstrated predominant right-sided cardiac involvement, characterized by reduced right ventricular ejection fraction ( p < 0.001), marked enlargement of right atrial (RA) and ventricular (RV) volumes, and severely impaired right heart strain (all p < 0.001). Left ventricular systolic function was relatively preserved, with mildly impaired global circumferential strain ( p = 0.011) and a trend toward attenuated longitudinal strain ( p = 0.055), whereas all left atrial (LA) strain components were markedly impaired (all p < 0.05), indicating altered atrioventricular interaction. Following BPA, the right heart structure, RV function and deformation, and LA conduit strain improved. EAT was comparable between groups and remained unchanged after BPA. Conclusion: CTEPH involves marked right heart systolic dysfunction and early biventricular diastolic abnormalities associated with impaired atrioventricular interaction. BPA could reverse cardiac remodeling by improving right heart structure, function, and partially recovering atrial deformation after pressure relief. Key Points: Questions Atrioventricular interaction abnormalities and reversible cardiac remodeling in chronic thromboembolic pulmonary hypertension (CTEPH) after balloon pulmonary angioplasty (BPA) remain insufficiently characterized. Findings CTEPH is associated with impaired right heart strain and altered atrioventricular interaction; BPA improves right heart structure and function and partially recovers atrial deformation. Critical relevance statement Cardiac MRI-derived myocardial deformation and atrial phasic function may reflect alterations in atrioventricular interaction in CTEPH and complement conventional metrics in assessing cardiac remodeling and recovery after BPA.
- 1 November 2026
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 321 (2)
Quantitative CT Phenotypes and Prognosis in Combined Pulmonary Fibrosis and Emphysema
Quantitative CT classified combined pulmonary fibrosis and emphysema into emphysema- and fibrosis-dominant phenotypes associated with different mortality risks.
- 1 November 2026
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 321 (2)
Quantitative CT Phenotypes and Prognosis in Combined Pulmonary Fibrosis and Emphysema
Quantitative CT classified combined pulmonary fibrosis and emphysema into emphysema- and fibrosis-dominant phenotypes associated with different mortality risks.
- 1 August 2026
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 320 (2)
Large Airway Osteochondroma with a “Centipede-like” Appearance
- 1 August 2026
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 320 (2)
Large Airway Osteochondroma with a “Centipede-like” Appearance
- Open Access
- 1 January 2026
- Published by AME Publishing Company in AME Case Reports
- Vol. 10, 15
Pneumonectomy for an endobronchial carcinosarcoma with long-term survival: a case report
Endobronchial carcinosarcoma is a rare and highly malignant tumor composed of both carcinomatous and sarcomatous elements. It typically affects middle-aged and elderly men, particularly those with a history of smoking. The prognosis is generally poor due to its high potential for early metastasis and local recurrence. This case report is unique due to the presentation of endobronchial carcinosarcoma, exhibiting a gloved finger sign, coarse calcifications, and high 18F-fluorodeoxyglucose (18F-FDG) uptake, along with an exceptionally favorable long-term survival after pneumonectomy (R0) without any neoadjuvant or adjuvant therapy. A 48-year-old man with a 30-year history of chronic productive cough, a 1-month history of shortness of breath, and a significant smoking history presented to The First Affiliated Hospital of Guangzhou Medical University. Initial examinations revealed elevated neuron-specific enolase (NSE) and reduced partial pressure of oxygen. Computed tomography identified a branching tubular mass in the left upper lobe with a gloved finger sign and coarse calcifications. 18F-FDG positron emission tomography/computed tomography showed intense FDG uptake. Preoperative imaging showed atelectasis and pleural effusion. A bronchoscopic biopsy suggested carcinosarcoma, which was confirmed post-pneumonectomy. Pathological examination confirmed complete surgical resection (R0). Microscopic analysis revealed a mix of squamous cell carcinoma and sarcoma components, primarily osteosarcoma and chondrosarcoma. The patient has remained free of recurrence or metastasis for 7 years post-surgery, without any neoadjuvant or adjuvant therapy. This case illustrates that the gloved finger sign may reflect early bronchial obstruction and prompt clinical evaluation. Despite preoperative imaging suggestive of disease progression, the patient underwent R0 pneumonectomy and has remained recurrence-free for 7 years without receiving neoadjuvant or adjuvant therapy. Exceptional long-term survival after R0 resection alone may be possible in some certain patients.
- 1 January 2026
- Published by AME Publishing Company in AME Case Reports
- Vol. 10, 15
Open AccessPneumonectomy for an endobronchial carcinosarcoma with long-term survival: a case report
Endobronchial carcinosarcoma is a rare and highly malignant tumor composed of both carcinomatous and sarcomatous elements. It typically affects middle-aged and elderly men, particularly those with a history of smoking. The prognosis is generally poor due to its high potential for early metastasis and local recurrence. This case report is unique due to the presentation of endobronchial carcinosarcoma, exhibiting a gloved finger sign, coarse calcifications, and high 18F-fluorodeoxyglucose (18F-FDG) uptake, along with an exceptionally favorable long-term survival after pneumonectomy (R0) without any neoadjuvant or adjuvant therapy. A 48-year-old man with a 30-year history of chronic productive cough, a 1-month history of shortness of breath, and a significant smoking history presented to The First Affiliated Hospital of Guangzhou Medical University. Initial examinations revealed elevated neuron-specific enolase (NSE) and reduced partial pressure of oxygen. Computed tomography identified a branching tubular mass in the left upper lobe with a gloved finger sign and coarse calcifications. 18F-FDG positron emission tomography/computed tomography showed intense FDG uptake. Preoperative imaging showed atelectasis and pleural effusion. A bronchoscopic biopsy suggested carcinosarcoma, which was confirmed post-pneumonectomy. Pathological examination confirmed complete surgical resection (R0). Microscopic analysis revealed a mix of squamous cell carcinoma and sarcoma components, primarily osteosarcoma and chondrosarcoma. The patient has remained free of recurrence or metastasis for 7 years post-surgery, without any neoadjuvant or adjuvant therapy. This case illustrates that the gloved finger sign may reflect early bronchial obstruction and prompt clinical evaluation. Despite preoperative imaging suggestive of disease progression, the patient underwent R0 pneumonectomy and has remained recurrence-free for 7 years without receiving neoadjuvant or adjuvant therapy. Exceptional long-term survival after R0 resection alone may be possible in some certain patients.
- Open Access
- 21 November 2025
- Published by Springer Nature in Orphanet Journal of Rare Diseases
- Vol. 20 (1) , 600
Pulmonary vascular Ehlers-Danlos syndrome with hemoptysis as the main manifestation: CT and histologic findings of lung parenchymal damage
Background: Vascular Ehlers-Danlos syndrome (vEDS) is a rare inherited connective tissue disease caused by mutations in the COL3A1 gene. The disease can cause fatal complications such as rupture of the arteries, uterus, and intestine, as well as pulmonary complications, including spontaneous pneumothorax and hemoptysis. Since hemoptysis in vEDS is rare and often misdiagnosed, this study aims to summarize its clinical features, CT findings and the diagnosis and treatment process, thereby improving clinical understanding. Methods: Patients with vEDS presenting with hemoptysis treated at the First Affiliated Hospital of Guangzhou Medical University from May 2017 to December 2024 were collected. Inclusion criteria included hemoptysis, chest CT, and COL3A1 gene test results. The clinical manifestations, CT and pathological data of the patients were collected. Results: The cohort included eight males and one female (mean age 22.22 ± 5.72 years). All patients presented with recurrent hemoptysis and cough. The CT findings included patchy ground-glass opacities, fibrous cords, nodules, and cavities, which were predominantly located in the lower lungs. 5 cases showed diffuse erythrocyte exudation and increased hemosiderin-laden macrophages. Eight cases were initially misdiagnosed as infectious diseases, of which 4 cases were treated with diagnostic anti-tuberculosis therapy. Conclusion: This study demonstrates that the clinical and imaging manifestations in vEDS patients presenting with hemoptysis lack specificity and are frequently misdiagnosed as infectious diseases. For young men with repeated hemoptysis and persistent CT abnormalities, especially when anti-infective treatment proves ineffective, vEDS should be considered and early genetic testing should be performed. Early diagnosis is crucial to prevent severe complications. Clinical trial number: Not applicable.
- 21 November 2025
- Published by Springer Nature in Orphanet Journal of Rare Diseases
- Vol. 20 (1) , 600
Open AccessPulmonary vascular Ehlers-Danlos syndrome with hemoptysis as the main manifestation: CT and histologic findings of lung parenchymal damage
Background: Vascular Ehlers-Danlos syndrome (vEDS) is a rare inherited connective tissue disease caused by mutations in the COL3A1 gene. The disease can cause fatal complications such as rupture of the arteries, uterus, and intestine, as well as pulmonary complications, including spontaneous pneumothorax and hemoptysis. Since hemoptysis in vEDS is rare and often misdiagnosed, this study aims to summarize its clinical features, CT findings and the diagnosis and treatment process, thereby improving clinical understanding. Methods: Patients with vEDS presenting with hemoptysis treated at the First Affiliated Hospital of Guangzhou Medical University from May 2017 to December 2024 were collected. Inclusion criteria included hemoptysis, chest CT, and COL3A1 gene test results. The clinical manifestations, CT and pathological data of the patients were collected. Results: The cohort included eight males and one female (mean age 22.22 ± 5.72 years). All patients presented with recurrent hemoptysis and cough. The CT findings included patchy ground-glass opacities, fibrous cords, nodules, and cavities, which were predominantly located in the lower lungs. 5 cases showed diffuse erythrocyte exudation and increased hemosiderin-laden macrophages. Eight cases were initially misdiagnosed as infectious diseases, of which 4 cases were treated with diagnostic anti-tuberculosis therapy. Conclusion: This study demonstrates that the clinical and imaging manifestations in vEDS patients presenting with hemoptysis lack specificity and are frequently misdiagnosed as infectious diseases. For young men with repeated hemoptysis and persistent CT abnormalities, especially when anti-infective treatment proves ineffective, vEDS should be considered and early genetic testing should be performed. Early diagnosis is crucial to prevent severe complications. Clinical trial number: Not applicable.
- 11 August 2025
- Published by Elsevier in Transplantation Proceedings
- Vol. 57 (7) , 1376-1378
Intrapulmonary Epstein-Barr Virus-Associated Smooth Muscle Tumor after Bilateral Lung Transplantation: A Case Report
- 11 August 2025
- Published by Elsevier in Transplantation Proceedings
- Vol. 57 (7) , 1376-1378
Intrapulmonary Epstein-Barr Virus-Associated Smooth Muscle Tumor after Bilateral Lung Transplantation: A Case Report
- Open Access
- 1 June 2025
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 15 (6) , 5868-5872
Dynamic digital radiography for monitoring pulmonary function before and after a single lung transplant: a case description
Dynamic digital radiography for monitoring pulmonary function before and after a single lung transplant: a case description
- 1 June 2025
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 15 (6) , 5868-5872
Open AccessDynamic digital radiography for monitoring pulmonary function before and after a single lung transplant: a case description
Dynamic digital radiography for monitoring pulmonary function before and after a single lung transplant: a case description
- 8 May 2025
- Published by Springer Nature in European Radiology
- Vol. 35 (11) , 7140-7149
nnU-Net-based high-resolution CT features quantification for interstitial lung diseases
Objectives To develop a new high-resolution (HR)CT abnormalities quantification tool (CVILDES) for interstitial lung diseases (ILDs) based on the nnU-Net network structure and to determine whether the quantitative parameters derived from this new software could offer a reliable and precise assessment in a clinical setting that is in line with expert visual evaluation. Methods HRCT scans from 83 cases of ILDs and 20 cases of other diffuse lung diseases were labeled section by section by multiple radiologists and were used as training data for developing a deep learning model based on nnU-Net, employing a supervised learning approach. For clinical validation, a cohort including 51 cases of interstitial pneumonia with autoimmune features (IPAF) and 14 cases of idiopathic pulmonary fibrosis (IPF) had CT parenchymal patterns evaluated quantitatively with CVILDES and by visual evaluation. Subsequently, we assessed the correlation of the two methodologies for ILD features quantification. Furthermore, the correlation between the quantitative results derived from the two methods and pulmonary function parameters (DLCO%, FVC%, and FEV%) was compared. Results All CT data were successfully quantified using CVILDES. CVILDES-quantified results (total ILD extent, ground-glass opacity, consolidation, reticular pattern and honeycombing) showed a strong correlation with visual evaluation and were numerically close to the visual evaluation results (r = 0.64–0.89, p < 0.0001), particularly for the extent of fibrosis (r = 0.82, p < 0.0001). As judged by correlation with pulmonary function parameters, CVILDES quantification was comparable or even superior to visual evaluation. Conclusion nnU-Net-based CVILDES was comparable to visual evaluation for ILD abnormalities quantification. Key Points Question Visual assessment of ILD on HRCT is time-consuming and exhibits poor inter-observer agreement, making it challenging to accurately evaluate the therapeutic efficacy. Findings nnU-Net-based Computer vision-based ILD evaluation system (CVILDES) accurately segmented and quantified the HRCT features of ILD, and results were comparable to visual evaluation. Clinical relevance This study developed a new tool that has the potential to be applied in the quantitative assessment of ILD. Graphical Abstract
- 8 May 2025
- Published by Springer Nature in European Radiology
- Vol. 35 (11) , 7140-7149
nnU-Net-based high-resolution CT features quantification for interstitial lung diseases
Objectives To develop a new high-resolution (HR)CT abnormalities quantification tool (CVILDES) for interstitial lung diseases (ILDs) based on the nnU-Net network structure and to determine whether the quantitative parameters derived from this new software could offer a reliable and precise assessment in a clinical setting that is in line with expert visual evaluation. Methods HRCT scans from 83 cases of ILDs and 20 cases of other diffuse lung diseases were labeled section by section by multiple radiologists and were used as training data for developing a deep learning model based on nnU-Net, employing a supervised learning approach. For clinical validation, a cohort including 51 cases of interstitial pneumonia with autoimmune features (IPAF) and 14 cases of idiopathic pulmonary fibrosis (IPF) had CT parenchymal patterns evaluated quantitatively with CVILDES and by visual evaluation. Subsequently, we assessed the correlation of the two methodologies for ILD features quantification. Furthermore, the correlation between the quantitative results derived from the two methods and pulmonary function parameters (DLCO%, FVC%, and FEV%) was compared. Results All CT data were successfully quantified using CVILDES. CVILDES-quantified results (total ILD extent, ground-glass opacity, consolidation, reticular pattern and honeycombing) showed a strong correlation with visual evaluation and were numerically close to the visual evaluation results (r = 0.64–0.89, p < 0.0001), particularly for the extent of fibrosis (r = 0.82, p < 0.0001). As judged by correlation with pulmonary function parameters, CVILDES quantification was comparable or even superior to visual evaluation. Conclusion nnU-Net-based CVILDES was comparable to visual evaluation for ILD abnormalities quantification. Key Points Question Visual assessment of ILD on HRCT is time-consuming and exhibits poor inter-observer agreement, making it challenging to accurately evaluate the therapeutic efficacy. Findings nnU-Net-based Computer vision-based ILD evaluation system (CVILDES) accurately segmented and quantified the HRCT features of ILD, and results were comparable to visual evaluation. Clinical relevance This study developed a new tool that has the potential to be applied in the quantitative assessment of ILD. Graphical Abstract
- 3 March 2025
- Published by Elsevier in Academic Radiology
- Vol. 32 (7) , 4289-4300
CT Differentiation and Prognostic Modeling in COVID-19 and Influenza A Pneumonia
- 3 March 2025
- Published by Elsevier in Academic Radiology
- Vol. 32 (7) , 4289-4300
CT Differentiation and Prognostic Modeling in COVID-19 and Influenza A Pneumonia
- 14 July 2024
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 19 (10) , 2001-2009
A position-enhanced sequential feature encoding model for lung infections and lymphoma classification on CT images
Purpose Differentiating pulmonary lymphoma from lung infections using CT images is challenging. Existing deep neural network-based lung CT classification models rely on 2D slices, lacking comprehensive information and requiring manual selection. 3D models that involve chunking compromise image information and struggle with parameter reduction, limiting performance. These limitations must be addressed to improve accuracy and practicality. Methods We propose a transformer sequential feature encoding structure to integrate multi-level information from complete CT images, inspired by the clinical practice of using a sequence of cross-sectional slices for diagnosis. We incorporate position encoding and cross-level long-range information fusion modules into the feature extraction CNN network for cross-sectional slices, ensuring high-precision feature extraction. Results We conducted comprehensive experiments on a dataset of 124 patients, with respective sizes of 64, 20 and 40 for training, validation and testing. The results of ablation experiments and comparative experiments demonstrated the effectiveness of our approach. Our method outperforms existing state-of-the-art methods in the 3D CT image classification problem of distinguishing between lung infections and pulmonary lymphoma, achieving an accuracy of 0.875, AUC of 0.953 and F1 score of 0.889. Conclusion The experiments verified that our proposed position-enhanced transformer-based sequential feature encoding model is capable of effectively performing high-precision feature extraction and contextual feature fusion in the lungs. It enhances the ability of a standalone CNN network or transformer to extract features, thereby improving the classification performance. The source code is accessible at https://github.com/imchuyu/PTSFE.
- 14 July 2024
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 19 (10) , 2001-2009
A position-enhanced sequential feature encoding model for lung infections and lymphoma classification on CT images
Purpose Differentiating pulmonary lymphoma from lung infections using CT images is challenging. Existing deep neural network-based lung CT classification models rely on 2D slices, lacking comprehensive information and requiring manual selection. 3D models that involve chunking compromise image information and struggle with parameter reduction, limiting performance. These limitations must be addressed to improve accuracy and practicality. Methods We propose a transformer sequential feature encoding structure to integrate multi-level information from complete CT images, inspired by the clinical practice of using a sequence of cross-sectional slices for diagnosis. We incorporate position encoding and cross-level long-range information fusion modules into the feature extraction CNN network for cross-sectional slices, ensuring high-precision feature extraction. Results We conducted comprehensive experiments on a dataset of 124 patients, with respective sizes of 64, 20 and 40 for training, validation and testing. The results of ablation experiments and comparative experiments demonstrated the effectiveness of our approach. Our method outperforms existing state-of-the-art methods in the 3D CT image classification problem of distinguishing between lung infections and pulmonary lymphoma, achieving an accuracy of 0.875, AUC of 0.953 and F1 score of 0.889. Conclusion The experiments verified that our proposed position-enhanced transformer-based sequential feature encoding model is capable of effectively performing high-precision feature extraction and contextual feature fusion in the lungs. It enhances the ability of a standalone CNN network or transformer to extract features, thereby improving the classification performance. The source code is accessible at https://github.com/imchuyu/PTSFE.