A5090964459- Cardiac Valve Diseases and Treatments
- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Aortic Disease and Treatment Approaches
- Infective Endocarditis Diagnosis and Management
- Colorectal Cancer Screening and Detection
- Aortic aneurysm repair treatments
- Digital Imaging for Blood Diseases
- Sarcoma Diagnosis and Treatment
- Cervical Cancer and HPV Research
- Oral and Maxillofacial Pathology
- Cardiac Structural Anomalies and Repair
- Cancer Genomics and Diagnostics
- Pancreatic and Hepatic Oncology Research
- Congenital Heart Disease Studies
- Speech Recognition and Synthesis
- Cardiac Arrhythmias and Treatments
- Lung Cancer Treatments and Mutations
- Image Retrieval and Classification Techniques
- Tissue Engineering and Regenerative Medicine
- Lung Cancer Research Studies
- Renal cell carcinoma treatment
- Cancer, Hypoxia, and Metabolism
- MicroRNA in disease regulation
- Neuroendocrine Tumor Research Advances
Chinese PLA General Hospital
2012-2024
Shandong Agricultural University
2024
Fuzhou University
2021-2023
Second Military Medical University
2009-2022
Changhai Hospital
2009-2022
Beijing University of Technology
2021-2022
Chinese People's Liberation Army
2013-2021
Jiangsu University of Science and Technology
2021
Tsinghua University
2020
Anqing City Hospital
2019
Abstract The early detection and accurate histopathological diagnosis of gastric cancer increase the chances successful treatment. worldwide shortage pathologists offers a unique opportunity for use artificial intelligence assistance systems to alleviate workload diagnostic accuracy. Here, we report clinically applicable system developed at Chinese PLA General Hospital, China, using deep convolutional neural network trained with 2,123 pixel-level annotated H&E-stained whole slide images....
Abstract Background Accurate and robust pathological image analysis for colorectal cancer (CRC) diagnosis is time-consuming knowledge-intensive, but essential CRC patients’ treatment. The current heavy workload of pathologists in clinics/hospitals may easily lead to unconscious misdiagnosis based on daily analyses. Methods Based a state-of-the-art transfer-learned deep convolutional neural network artificial intelligence (AI), we proposed novel patch aggregation strategy clinic using weakly...
Histopathology image analysis plays a critical role in cancer diagnosis and treatment. To automatically segment the cancerous regions, fully supervised segmentation algorithms require labor-intensive time-consuming labeling at pixel level. In this research, we propose CAMEL, weakly learning framework for histopathology using only image-level labels. Using multiple instance (MIL)-based label enrichment, CAMEL splits into latticed instances generates instance-level After labels are further...
Previous studies on deep learning (DL) applications in pathology have focused pathologist-versus-algorithm comparisons. However, DL will not replace the breadth and contextual knowledge of pathologists; rather, only through their combination may benefits be achieved. A fully crossed multireader multicase study was conducted to evaluate assistance with pathologists' diagnosis gastric cancer. total 110 whole-slide images (WSI) (50 malignant 60 benign) were interpreted by 16 board-certified...
Abstract Osteopontin is a secreted glycosylated phosphoprotein known to be involved in numerous physiologic functions and associated with the late stages of various cancers. We used preneoplastic neoplastic mouse models prostate cancer determine onset elevated expression osteopontin development this disease. alterations occurred early disease dysregulated observed lesions low-grade prostatic intraepithelial neoplasia (PIN). Over time, expressing dysplastic cells seemed increase number...
Lung metastasis and relapse in osteosarcoma (OS) patients indicate poor prognosis. Here, we identified significantly decreased expression of miR-382 highly metastatic OS cell lines relapsed samples compared to their parental primary samples, respectively. In addition, our clinical data showed that the level was inversely associated with positively metastasis-free survival patients. The overexpression suppressed epithelial-mesenchymal transition (EMT) metastasis. This also cancer stem (CSC)...
The aim of the present study is to investigate role and mechanism miR216a in non-small-cell lung cancer (NSCLC).The expression NSCLC cell lines from patient specimens was measured by real-time qRT-PCR. correlation between gene survival analyzed using Kaplan-Meier methods. effects on growth metastasis were examined both vitro vivo overexpressing or inhibiting miR216a. Finally, effect chemoresistance investigated MTT assay flow cytometry.miR216a downregulated patients with compared...
Objectives The microscopic evaluation of slides has been gradually moving towards all digital in recent years, leading to the possibility for computer-aided diagnosis. It is worthwhile know similarities between deep learning models and pathologists before we put them into practical scenarios. simple criteria colorectal adenoma diagnosis make it be a perfect testbed this study. Design model was trained by 177 accurately labelled training (156 with adenoma). detailed labelling performed on...
Objective Tricuspid regurgitation (TR) is a common valvular heart disease with unsatisfactory medical therapeutics and high surgical mortality. The present study aims to evaluate the safety effectiveness of transcatheter tricuspid valve replacement (TTVR) in high-risk patients severe TR. Methods This was compassionate multicentre study. Between September 2018 November 2019, 46 TR who were not suitable for surgery received TTVR under general anaesthesia guidance trans-oesophageal...
The efficacy of epidermal growth factor receptor-tyrosine kinase inhibitors (EGFR-TKI) in patients with non-small cell lung cancer (NSCLC) is related to EGFR mutations. Although the p.L858R point mutation exon 21 and in-frame deletion 19 are well known, EGFR-TKI more than one not understood. 799 NSCLC were screened for Of patients, 443 (55.4%) had mutations, out which 22 (2.75%) multiple complex Most mutations (20/22) harbored common such as 19. 11 who underwent TKI therapy primary...
Deep learning has the potential to improve diagnostic accuracy and efficiency in medical image recognition. In current study, we developed a deep algorithm assessed its performance discriminating melanoma from nevus using whole-slide pathological images (WSIs). The was trained validated set of 781 WSIs (86 melanomas, 695 nevi) PLA General Hospital. tested on an independent test 104 (29 75 Tianjin Chang Zheng same also diagnostically classified by 7 expert dermatopathologists. receiver...
Mucoepidermoid carcinoma (MEC), an extremely rare tumor, arises from the epithelial component of preexisting parotid Warthin tumors (WT). Among 309 cases surgically resected WTs in Chinese PLA General Hospital and Beijing Shijitan Capital Medical University, 5 (1.6%) fulfilled criteria for MECs transformed WTs. Clinicopathological characteristics was demonstrated order to avoid misdiagnosis this type tumor. All patients, 3 males 2 females, presented painless masses gland. were located inside...
The accurate pathological diagnosis of endometrial cancer (EC) improves the curative effect and reduces mortality rate. Deep learning has demonstrated expert-level performance in a variety organ systems using whole-slide images (WSIs). It is urgent to build deep system for detection WSIs. model was trained validated dataset 601 WSIs from PUPH. tested on three independent datasets containing total 1,190 For retrospective test, we evaluated 581 In prospective study, 317 consecutive PUPH were...
Comparison of uncommon EGFR exon 21 L858R compound mutations with single mutation Liang Peng,1* Zhigang Song,2* Shunchang Jiao1 1Department Oncology, Chinese PLA General Hospital, Medical School, Beijing, People's Republic China; 2Department Pathology, China *These authors contributed equally to this work Abstract: Non-small-cell lung cancer epidermal growth factor receptor (EGFR) is sensitive tyrosine kinase inhibitors (TKIs). But little known about the response TKIs and prognostic role...
Acute type A aortic dissection frequently induces root disease; however, the optimal surgical strategy for remains a challenge. The objective of this study was to introduce novel technique reconstruction improve patient prognosis.We performed retrospective review 791 consecutive patients with acute between January 2003 and July 2015. Among these patients, 151 were selected (72% men, age 51.7 ± 9.8 years) have modified sandwich repair dissection.The in-hospital mortality rate 6.6% (10/151)....
OBJECTIVESThe study aimed to assess the long-term follow-up of patients with an autologous pericardial aortic valve (APAV) replacement and analyse in vivo histopathological changes implanted APAVs.