Qin Shen
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
Qin Shen has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- B. Zou
From the School of Computer Science and Engineering (R.H., B.Z., C.Z.)
1 shared publication - Bin Yan
Department of Medicine IV, Gastroenterology, Hepatology and Infectious Diseases Heidelberg University Heidelberg Germany
1 shared publication - Bo Xiao
Department of Neurology Xiangya Hospital, Central South University Changsha China
1 shared publication - C. Hu
Department of Neurology (C.H.), Hunan Provincial People’s Hospital, Changsha, Hunan, China
1 shared publication - C. Zhu
From the School of Computer Science and Engineering (R.H., B.Z., C.Z.)
1 shared publication Changlian Tan
Department of Radiology Second Xiangya Hospital, Central South University Changsha China
1 shared publication
Latest Publications
- 21 May 2026
- Published by Wiley in European Journal of Neuroscience
- Vol. 63 (10) , e70549
Dynamic Functional Connectivity Changes in Parkinson's Disease With and Without Depression
Depression is a common non‐motor symptom in Parkinson's disease (PD), considered a disorder involving dysfunction across multiple neural networks. Previous resting‐state functional magnetic resonance imaging (rs‐fMRI) studies of PD with depression (dPD) have overlooked crucial dynamic characteristics of brain networks. This study investigated dynamic functional connectivity (DFC) patterns in dPD. By collecting resting‐state fMRI data from 50 dPD subjects, 82 ndPD subjects and 50 healthy controls (HC), we employed independent component analysis, sliding time windows and k ‐means clustering to identify DFC states. Intergroup comparisons and clinical correlation analyses revealed four recurrent states. Specifically, in State II, the fractional window and average dwell time progressively increased across the dPD, ndPD and HC groups, whereas in State III, the fractional window progressively decreased across the three groups. State II connectivity featured strong positive connections both within and between all networks. State III connectivity primarily exhibited strong negative connections between the ECN and SN/DMN networks, and between SN and DMN networks, whereas the ECN network internally, and between the SN and SMN/SMA networks, exhibited strong positive connections. The occurrence frequency and average dwell time of State II both showed a negative correlation with HAMD‐17 scores. These findings suggest that a higher proportion of patients with dPD exhibit a state of relatively sparse connectivity, alongside abnormal network connectivity changes across the four states, providing new insights into the neuroimaging mechanisms of dPD.
- 21 May 2026
- Published by Wiley in European Journal of Neuroscience
- Vol. 63 (10) , e70549
Dynamic Functional Connectivity Changes in Parkinson's Disease With and Without Depression
Depression is a common non‐motor symptom in Parkinson's disease (PD), considered a disorder involving dysfunction across multiple neural networks. Previous resting‐state functional magnetic resonance imaging (rs‐fMRI) studies of PD with depression (dPD) have overlooked crucial dynamic characteristics of brain networks. This study investigated dynamic functional connectivity (DFC) patterns in dPD. By collecting resting‐state fMRI data from 50 dPD subjects, 82 ndPD subjects and 50 healthy controls (HC), we employed independent component analysis, sliding time windows and k ‐means clustering to identify DFC states. Intergroup comparisons and clinical correlation analyses revealed four recurrent states. Specifically, in State II, the fractional window and average dwell time progressively increased across the dPD, ndPD and HC groups, whereas in State III, the fractional window progressively decreased across the three groups. State II connectivity featured strong positive connections both within and between all networks. State III connectivity primarily exhibited strong negative connections between the ECN and SN/DMN networks, and between SN and DMN networks, whereas the ECN network internally, and between the SN and SMN/SMA networks, exhibited strong positive connections. The occurrence frequency and average dwell time of State II both showed a negative correlation with HAMD‐17 scores. These findings suggest that a higher proportion of patients with dPD exhibit a state of relatively sparse connectivity, alongside abnormal network connectivity changes across the four states, providing new insights into the neuroimaging mechanisms of dPD.
- 13 May 2021
- Published by SAGE Publications in The Journal of Vascular Access
- Vol. 23 (6) , 989-991
Video-assisted thoracic surgical repair of iatrogenic subclavian vein injury from central venous catheterization
- 13 May 2021
- Published by SAGE Publications in The Journal of Vascular Access
- Vol. 23 (6) , 989-991
Video-assisted thoracic surgical repair of iatrogenic subclavian vein injury from central venous catheterization
- 13 July 2020
- Published by American Society of Neuroradiology (ASNR) in American Journal of Neuroradiology
- Vol. 41 (7) , 1279-1285
Automatic Machine Learning to Differentiate Pediatric Posterior Fossa Tumors on Routine MR Imaging
BACKGROUND AND PURPOSE: Differentiating the types of pediatric posterior fossa tumors on routine imaging may help in preoperative evaluation and guide surgical resection planning. However, qualitative radiologic MR imaging review has limited performance. This study aimed to compare different machine learning approaches to classify pediatric posterior fossa tumors on routine MR imaging. MATERIALS AND METHODS: This retrospective study included preoperative MR imaging of 288 patients with pediatric posterior fossa tumors, including medulloblastoma (n = 111), ependymoma (n = 70), and pilocytic astrocytoma (n = 107). Radiomics features were extracted from T2-weighted images, contrast-enhanced T1-weighted images, and ADC maps. Models generated by standard manual optimization by a machine learning expert were compared with automatic machine learning via the Tree-Based Pipeline Optimization Tool for performance evaluation. RESULTS: For 3-way classification, the radiomics model by automatic machine learning with the Tree-Based Pipeline Optimization Tool achieved a test micro-averaged area under the curve of 0.91 with an accuracy of 0.83, while the most optimized model based on the feature-selection method χ2 score and the Generalized Linear Model classifier achieved a test micro-averaged area under the curve of 0.92 with an accuracy of 0.74. Tree-Based Pipeline Optimization Tool models achieved significantly higher accuracy than average qualitative expert MR imaging review (0.83 versus 0.54, P < .001). For binary classification, Tree-Based Pipeline Optimization Tool models achieved an area under the curve of 0.94 with an accuracy of 0.85 for medulloblastoma versus nonmedulloblastoma, an area under the curve of 0.84 with an accuracy of 0.80 for ependymoma versus nonependymoma, and an area under the curve of 0.94 with an accuracy of 0.88 for pilocytic astrocytoma versus non-pilocytic astrocytoma. CONCLUSIONS: Automatic machine learning based on routine MR imaging classified pediatric posterior fossa tumors with high accuracy compared with manual expert pipeline optimization and qualitative expert MR imaging review.
- 13 July 2020
- Published by American Society of Neuroradiology (ASNR) in American Journal of Neuroradiology
- Vol. 41 (7) , 1279-1285
Automatic Machine Learning to Differentiate Pediatric Posterior Fossa Tumors on Routine MR Imaging
BACKGROUND AND PURPOSE: Differentiating the types of pediatric posterior fossa tumors on routine imaging may help in preoperative evaluation and guide surgical resection planning. However, qualitative radiologic MR imaging review has limited performance. This study aimed to compare different machine learning approaches to classify pediatric posterior fossa tumors on routine MR imaging. MATERIALS AND METHODS: This retrospective study included preoperative MR imaging of 288 patients with pediatric posterior fossa tumors, including medulloblastoma (n = 111), ependymoma (n = 70), and pilocytic astrocytoma (n = 107). Radiomics features were extracted from T2-weighted images, contrast-enhanced T1-weighted images, and ADC maps. Models generated by standard manual optimization by a machine learning expert were compared with automatic machine learning via the Tree-Based Pipeline Optimization Tool for performance evaluation. RESULTS: For 3-way classification, the radiomics model by automatic machine learning with the Tree-Based Pipeline Optimization Tool achieved a test micro-averaged area under the curve of 0.91 with an accuracy of 0.83, while the most optimized model based on the feature-selection method χ2 score and the Generalized Linear Model classifier achieved a test micro-averaged area under the curve of 0.92 with an accuracy of 0.74. Tree-Based Pipeline Optimization Tool models achieved significantly higher accuracy than average qualitative expert MR imaging review (0.83 versus 0.54, P < .001). For binary classification, Tree-Based Pipeline Optimization Tool models achieved an area under the curve of 0.94 with an accuracy of 0.85 for medulloblastoma versus nonmedulloblastoma, an area under the curve of 0.84 with an accuracy of 0.80 for ependymoma versus nonependymoma, and an area under the curve of 0.94 with an accuracy of 0.88 for pilocytic astrocytoma versus non-pilocytic astrocytoma. CONCLUSIONS: Automatic machine learning based on routine MR imaging classified pediatric posterior fossa tumors with high accuracy compared with manual expert pipeline optimization and qualitative expert MR imaging review.
- Open Access
- 8 February 2016
- Published by Spandidos Publications in Oncology Letters
- Vol. 11 (3) , 2179-2181
Primary kidney parenchyma squamous cell carcinoma mimicking xanthogranulomatous pyelonephritis: A case report
Primary kidney parenchyma squamous cell carcinoma is extremely rare, and this is the forth case to be reported. In the present study, a case of a 61-year old man is discussed. The man presented with recurrent lumbago, gross hematuria for nearly 2 months, and suspicious inflammatory kidney diseases on contrast-enhanced computed tomography (CT) and fludeoxyglucose-positron emission tomography (FDG-PET)/CT, but a tumor can not be excluded completely prior to surgery. Finally, radical nephrectomy was performed, and histological analysis determined that the diagnosis was kidney parenchyma squamous cell carcinoma with inflammation invasion. The present case highlights the potential confusion of preoperative diagnosis of renal tumor with inflammation, and introduces the potential role of FDG-PET in its diagnosis and survival evaluation in renal malignancies.
- 8 February 2016
- Published by Spandidos Publications in Oncology Letters
- Vol. 11 (3) , 2179-2181
Open AccessPrimary kidney parenchyma squamous cell carcinoma mimicking xanthogranulomatous pyelonephritis: A case report
Primary kidney parenchyma squamous cell carcinoma is extremely rare, and this is the forth case to be reported. In the present study, a case of a 61-year old man is discussed. The man presented with recurrent lumbago, gross hematuria for nearly 2 months, and suspicious inflammatory kidney diseases on contrast-enhanced computed tomography (CT) and fludeoxyglucose-positron emission tomography (FDG-PET)/CT, but a tumor can not be excluded completely prior to surgery. Finally, radical nephrectomy was performed, and histological analysis determined that the diagnosis was kidney parenchyma squamous cell carcinoma with inflammation invasion. The present case highlights the potential confusion of preoperative diagnosis of renal tumor with inflammation, and introduces the potential role of FDG-PET in its diagnosis and survival evaluation in renal malignancies.