A5051776525- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Treatments and Mutations
- Lung Cancer Diagnosis and Treatment
- AI in cancer detection
- COVID-19 diagnosis using AI
- Colorectal Cancer Treatments and Studies
- Prostate Cancer Treatment and Research
- RNA modifications and cancer
- Advanced X-ray and CT Imaging
- Cancer Genomics and Diagnostics
- Ferroptosis and cancer prognosis
- Cancer, Lipids, and Metabolism
- Gastric Cancer Management and Outcomes
- Cancer Immunotherapy and Biomarkers
- Medical Imaging and Analysis
- Protein Tyrosine Phosphatases
- Medical Imaging Techniques and Applications
- MRI in cancer diagnosis
- Colorectal Cancer Screening and Detection
- Genetic factors in colorectal cancer
- Lung Cancer Research Studies
- Cytokine Signaling Pathways and Interactions
- COVID-19 Clinical Research Studies
- Prostate Cancer Diagnosis and Treatment
- Machine Learning in Healthcare
Beihang University
2019-2025
Chinese Academy of Sciences
2018-2025
Ministry of Industry and Information Technology
2021-2025
University of Chinese Academy of Sciences
2018-2025
Institute of Automation
2025
Renji Hospital
2025
Xidian University
2025
Chongqing Medical University
2025
Children's Hospital of Chongqing Medical University
2025
Tianjin Medical University Cancer Institute and Hospital
2025
Coronavirus disease 2019 (COVID-19) has spread globally, and medical resources become insufficient in many regions. Fast diagnosis of COVID-19 finding high-risk patients with worse prognosis for early prevention resource optimisation is important. Here, we proposed a fully automatic deep learning system diagnostic prognostic analysis by routinely used computed tomography. We retrospectively collected 5372 tomography images from seven cities or provinces. Firstly, 4106 were to pre-train the...
Epidermal growth factor receptor (EGFR) genotyping is critical for treatment guidelines such as the use of tyrosine kinase inhibitors in lung adenocarcinoma. Conventional identification EGFR genotype requires biopsy and sequence testing which invasive may suffer from difficulty accessing tissue samples. Here, we propose a deep learning model to predict mutation status adenocarcinoma using non-invasive computed tomography (CT). We retrospectively collected data 844 patients with pre-operative...
Background Tumor mutational burden (TMB) is a significant predictor of immune checkpoint inhibitors (ICIs) efficacy. This study investigated the correlation between deep learning radiomic biomarker and TMB, including its predictive value for ICIs treatment response in patients with advanced non-small-cell lung cancer (NSCLC). Methods CT images from 327 TMB data (TMB median=6.067 mutations per megabase (range: 0 to 42.151)) were retrospectively collected randomly divided into training...
Epidermal growth factor receptor (EGFR) genotype is crucial for treatment decision making in lung cancer, but it can be affected by tumour heterogeneity and invasive biopsy during gene sequencing. Importantly, not all patients with an EGFR mutation have good prognosis EGFR-tyrosine kinase inhibitors (TKIs), indicating the necessity of stratifying EGFR-mutant genotype. In this study, we proposed a fully automated artificial intelligence system (FAIS) that mines whole-lung information from CT...
Abstract Coronavirus disease 2019 (COVID-19) has spread globally, and medical resources become insufficient in many regions. Fast diagnosis of COVID-19, finding high-risk patients with worse prognosis for early prevention optimization is important. Here, we proposed a fully automatic deep learning system COVID-19 diagnostic prognostic analysis by routinely used computed tomography. We retrospectively collected 5372 tomography images from 7 cities or provinces. Firstly, 4106 gene information...
Objectives: To identify a computed tomography (CT)-based radiomic signature for predicting progression-free survival (PFS) in stage IV anaplastic lymphoma kinase (ALK)-positive non-small-cell lung cancer (NSCLC) patients treated with tyrosine inhibitor (TKI) crizotinib. Materials and Methods: This retrospective proof-of-concept study included cohort of 63 ALK-positive NSCLC who had received TKI crizotinib therapy model construction validation. Another independent including 105 EGFR-positive...
To develop and validate a pretreatment computed tomography (CT)-based deep-learning (DL) model for predicting the treatment response to concurrent chemoradiation therapy (CCRT) among patients with locally advanced thoracic esophageal squamous cell carcinoma (TESCC).We conducted prospective, multicenter study on therapeutic efficacy of CCRT TESCC across 9 hospitals in China (ChiCTR2000039279). A total 306 diagnosed by histopathology from August 2015 May 2020 were included this study....
The present study assessed the predictive value of peritumoral regions on three tumor tasks, and further explored influence peritumors with different sizes.We retrospectively collected 333 samples gastrointestinal stromal tumors from Second Affiliated Hospital Zhejiang University School Medicine, 183 Tianjin Medical Cancer Hospital. We also 211 laryngeal carcinoma 233 nasopharyngeal First Jinan University. tasks datasets were risk assessment (gastrointestinal tumor), T3/T4 staging prediction...
Radiomics based on computed tomography (CT) images is potential in promoting individualized treatment of non-small cell lung cancer (NSCLC), however, its role immunotherapy needs further exploration. The aim this study was to develop a CT-based radiomics score predict the efficacy immune checkpoint inhibitor (ICI) monotherapy patients with advanced NSCLC.Two hundred and thirty-six ICI-treated were retrospectively included divided into training cohort (n=188) testing (n=48) at ratio 8 2....
Distant metastasis (DM) is the leading cause of death in advanced lung cancer, which diagnosed by positron emission tomography (PET) scanning. Compared with expensive price and nocuous contrast medium PET, using computed (CT) for DM diagnosis more economical convenient clinical practice. However, most existing methods only analyze tumor regions to extract local features prediction, neglects rich whole-lung information. To alleviate this problem, we propose a novel deep learning framework...
532 Background: Oligometastatic renal cell carcinoma (RCC) involves limited metastases (1-5) and lies between localized metastatic disease, with lower tumor burden. Studies suggest these patients may respond well to local or systemic therapies like targeted immunotherapy. Combining embolization is emerging as a promising option. However, comparative data on versus non-embolization treatments remain scarce. This study compares efficacy adverse events of in oligometastatic RCC using propensity...
Hip fractures have become a significant clinical concern on global scale in recent years. The burgeoning aging population has exacerbated this issue, leading to rise the number of hip fracture cases coupled with concomitant geriatric ailments. Therefore, it poses huge challenge anesthesiologists increasing critically ill patients who are not suitable for general anesthesia and intrathecal anesthesia. Ultrasound-guided nerve blocks combined sedation previously been documented patients. We...
Abstract Cardiovascular diseases (CVDs) pose a significant threat to human health and place considerable strain on healthcare systems. Therefore, it is crucial maximize the acquisition of cardiovascular information (CVI) through non-invasive methods enhance early screening, diagnosis, evaluation CVDs. Numerous studies have demonstrated that obtaining more CVI by simultaneously acquiring multi-site signals applying pressure stimulation at specific sites, such as blood measurement, an...
Nuclei instance segmentation and classification of hematoxylin eosin (H&E) stained digital pathology images are essential for further downstream cancer diagnosis prognosis tasks. Previous works mainly focused on bottom-up methods using a single-level feature map segmenting nuclei instances, while multilevel maps seemed to be more suitable instances with various sizes types. In this paper, we develop an effective top-down framework (NuHTC) based hybrid task cascade (HTC). The NuHTC has two...
In a few patients with mild COVID-19, there is possibility of the infection becoming severe or critical in future. This work aims to identify high-risk who have high probability changing from COVID-19 (only account for 5% cases).Using traditional convolutional neural networks classification may not be suitable this risk an entire dataset due highly imbalanced label distribution. To address problem, we propose Mix Contrast model, which matches original features mixed contrastive learning....
Lung cancer overall survival analysis using computed tomography (CT) images plays an important role in treatment planning. Most current methods involve hand-crafted image features for time prediction. However, require domain knowledge and may lack specificity to lung cancer. Advanced self-learning models such as deep learning have showed superior performance many medical tasks, but they large amount of data which is difficult collect because the long follow-up time. Although with acquire, it...
Encouraging and astonishing developments have recently been achieved in image-based diagnostic technology. Modern medical care imaging technology are becoming increasingly inseparable. However, the current diagnosis pattern of signal to image knowledge inevitably leads information distortion noise introduction procedure reconstruction (from image). Artificial intelligence (AI) technologies that can mine from vast amounts data offer opportunities disrupt established workflows. In this...
Abstract Objective. In the realm of utilizing artificial intelligence (AI) for medical image analysis, paradigm ‘signal-image-knowledge’ has remained unchanged. However, process ‘signal to image’ inevitably introduces information distortion, ultimately leading irrecoverable biases in ‘image knowledge’ process. Our goal is skip reconstruction and build a diagnostic model directly from raw data (signal). Approach . This study focuses on computed tomography (CT) its (sinogram) as research...