A5101531697- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Lung Cancer Diagnosis and Treatment
- Cancer Immunotherapy and Biomarkers
- Lung Cancer Treatments and Mutations
- Advanced Neuroimaging Techniques and Applications
- Colorectal Cancer Screening and Detection
- Head and Neck Cancer Studies
- Ferroptosis and cancer prognosis
- Digital Imaging for Blood Diseases
- BRCA gene mutations in cancer
- Functional Brain Connectivity Studies
- Advanced Radiotherapy Techniques
- Colorectal Cancer Treatments and Studies
- Global Cancer Incidence and Screening
- Respiratory Support and Mechanisms
- Face and Expression Recognition
- Oral health in cancer treatment
- Colorectal Cancer Surgical Treatments
- COVID-19 diagnosis using AI
- MRI in cancer diagnosis
- Advanced Neural Network Applications
- Brain Metastases and Treatment
- Gastric Cancer Management and Outcomes
- Advanced MRI Techniques and Applications
Southern Medical University
2016-2025
Guangdong Provincial People's Hospital
2020-2025
Guangdong Academy of Medical Sciences
2011-2025
Key Laboratory of Guangdong Province
2023-2024
Second Military Medical University
2024
Guangzhou University of Chinese Medicine
2019-2024
South China University of Technology
2021-2024
Zhejiang Normal University
2024
Ningbo University Affiliated Hospital
2023
Peking University
2023
Background Breast cancer is highly heterogeneous, resulting in different treatment responses to neoadjuvant chemotherapy (NAC) among patients. A noninvasive quantitative measure of intratumoral heterogeneity (ITH) may be valuable for predicting response. Purpose To develop a ITH on pretreatment MRI scans and test its performance pathologic complete response (pCR) after NAC patients with breast cancer. Materials Methods Pretreatment were retrospectively acquired who received followed by...
Brain tumor segmentation (BTS) in magnetic resonance image (MRI) is crucial for brain diagnosis, cancer management and research purposes. With the great success of ten-year BraTS challenges as well advances CNN Transformer algorithms, a lot outstanding BTS models have been proposed to tackle difficulties different technical aspects. However, existing studies hardly consider how fuse multi-modality images reasonable manner. In this paper, we leverage clinical knowledge radiologists diagnose...
Tissue-level semantic segmentation is a vital step in computational pathology. Fully-supervised models have already achieved outstanding performance with dense pixel-level annotations. However, drawing such labels on the giga-pixel whole slide images extremely expensive and time-consuming. In this paper, we use only patch-level classification to achieve tissue histopathology images, finally reducing annotation efforts. We propose two-step model including phases. phase, CAM-based generate...
Nitrogen dioxide (NO2) is associated with mortality and many other adverse health outcomes. In 2021, the World Health Organization established a new NO2 air quality guideline (AQG) (annual average <10 μg/m3). However, burden of diseases attributable to long-term exposure above AQG unknown in China. oxide major pollutant populous cities, which are disproportionately impacted by NO2; this represents form environmental inequality. We conducted nationwide risk assessment premature deaths from...
BackgroundContrast-enhanced CT scans provide a means to detect unsuspected colorectal cancer. However, cancers in contrast-enhanced without bowel preparation may elude detection by radiologists. We aimed develop deep learning (DL) model for accurate of cancer, and evaluate whether it could improve the performance radiologists.MethodsWe developed DL using manually annotated dataset (1196 cancer vs 1034 normal). The was tested an internal test set (98 115), two external sets (202 265 1, 252...
The increased amount of tertiary lymphoid structures (TLSs) is associated with a favorable prognosis in patients lung adenocarcinoma (LUAD). However, evaluating TLSs manually an experience-dependent and time-consuming process, which limits its clinical application. In this multi-center study, we developed automated computational workflow for quantifying the TLS density tumor region routine hematoxylin eosin (H&E)-stained whole-slide images (WSIs). association between computerized...
A high abundance of tumor-infiltrating lymphocytes (TILs) has a positive impact on the prognosis patients with lung adenocarcinoma (LUAD). We aimed to develop and validate an artificial intelligence-driven pathological scoring system for assessing TILs H&E-stained whole-slide images LUAD. Deep learning-based methods were applied calculate densities in cancer epithelium (DLCE) stroma (DLCS), risk score (WELL score) was built through linear weighting DLCE DLCS. Association between WELL patient...
Background Current prognostic and predictive biomarkers for lung adenocarcinoma (LUAD) predominantly rely on unimodal approaches, limiting their characterization ability. There is an urgent need a comprehensive accurate biomarker to guide individualized adjuvant therapy decisions. Methods In this retrospective study, data from patients with resectable LUAD (stage I–III) were collected two hospitals publicly available dataset, forming training dataset (n=223), validation (n=95), testing...
The therapeutic planning varies for different grades of choroid plexus tumours (CPTs). aim this study was to define the similarities and distinctions among MRIs CPTs, providing more guidance clinical decisions. We reviewed MRI findings in 35 patients with CPT verified by surgical pathology, including 18 papillomas (CPPs, grade I), 11 atypical (aCPPs, II), 6 carcinomas (CPCs, III). Nonparametric testing based on ranks performed evaluate association pathological findings. Among 29 were located...
Type 2 diabetes mellitus (T2DM) is associated with cognitive dysfunction and may even progress to dementia. However, the underlying mechanism of altered functional topological organization impairments remains unclear. This study explored properties whole brain networks in T2DM patients graph theoretical analysis using a resting-state magnetic resonance imaging (rs-fMRI) technique. Thirty (aged 51.77 ± 1.42 years) 30 sex-, age-, education-matched healthy controls (HCs) 48.87 0.98 underwent...
Profound heterogeneity in prognosis has been observed colorectal cancer (CRC) patients with intermediate levels of disease (stage II-III), advocating the identification valuable biomarkers that could improve prognostic stratification. This study aims to develop a deep learning-based pipeline for fully automatic quantification immune infiltration within stroma region on immunohistochemical (IHC) whole-slide images (WSIs) and further analyze its value CRC.Patients from two independent cohorts...
Background Pulmonary rehabilitation is considered beneficial for patients undergoing lung surgery, yet its specific impacts on exercise capacity, health-related quality of life (HRQL), and cardiopulmonary function require further elucidation. This study aimed to evaluate the effect PR these outcomes in surgery using a retrospective propensity score-matched analysis. Methods We retrospectively analyzed 420 with non-small cell cancer (NSCLC) who underwent from January 2022 May 2024. Among...
Temporal lobe epilepsy (TLE) and frontal (FLE) are the largest subgroup of partial epilepsy, focal cortical dysplasias (FCDs) highly epileptogenic brain lesions a frequent cause for antiepileptic drug (AED)-resistant epilepsies that mostly occur in temporal lobes. We performed graph-theoretical study based on diffusion tensor imaging (DTI) data patients with FLE or TLE caused by FCDs high suspicion evaluated their cognitive function Chinese version Montreal Cognitive Assessment-Basic...
The aim of the present study was to investigate microstructural characteristics brain lobes following radiotherapy (RT) for patients with nasopharyngeal carcinoma (NPC) at distinct times. Diffusion tensor imaging (DTI) and 3D-T1-weighted performed in 70 age- sex-matched subjects, 24 whom were pre-treatment patients. divided into three groups, according time completion RT. Fractional anisotropy (FA) gray matter (GM) volume determined. DTI data analyzed using tract-based spatial statistics GM...
Whether tumor mutational burden (TMB) is related to improved survival outcomes or the promotion of immunotherapy in various malignant tumors remains controversial, and we lack a comprehensive understanding TMB across cancers. Based on data obtained from The Cancer Genome Atlas (TCGA), conducted multiomics analysis 21 cancer types identify characteristics determine mechanism as it relates prognosis, gene expression, mutation signaling pathways. In our study, was found have significant...
Anaplastic ependymomas are rare malignant tumors of the central nervous system. Few studies available regarding their neuroradiological characteristics. The present study aimed to retrospectively review a series patients with extraventricular anaplastic ependymoma and analyze magnetic resonance imaging (MRI) characteristics distinguish from other intracranial tumors. clinical pathological images 11 who presented histologically proven at Nanfang Hospital (Southern Medical University,...
The purpose/aim of this study was to 1) use magnetic resonance diffusion tensor imaging (DTI), fibre bundle/tract-based spatial statistics (TBSS) and machine learning methods changes in the white matter (WM) structure whole brain WM network different periods nasopharyngeal carcinoma (NPC) patients after radiotherapy (RT), 2) identify most discriminating regions connections as biomarkers radiation injury (RBI), 3) supplement understanding pathogenesis RBI, which is useful for early diagnosis...
Gastric cancer is one of the most common malignant tumours in world. As crucial hallmarks reprogramming metabolism and relevant researches have a promising application diagnosis treatment prognostic prediction tumours. This study aims to identify group metabolism-related genes construct model for prognosis gastric cancer. A large cohort cases (1121 cases) from public database was included our analysis classified patients into training testing cohorts at ratio 7: 3. After identifying list...
Abstract Background High immune infiltration is associated with favourable prognosis in patients non-small-cell lung cancer (NSCLC), but an automated workflow for characterizing infiltration, high validity and reliability, remains to be developed. Methods We performed a multicentre retrospective study of completely resected NSCLC. developed image analysis automatically evaluating the density CD3 + CD8 T-cells tumour regions on immunohistochemistry (IHC)-stained whole-slide images (WSIs),...
Automatic tissue segmentation in whole-slide images (WSIs) is a critical task hematoxylin and eosin- (H&E-) stained histopathological for accurate diagnosis risk stratification of lung cancer. Patch classification stitching the results can fast conduct WSIs. However, due to tumour heterogeneity, large intraclass variability small interclass make challenging. In this paper, we propose novel bilinear convolutional neural network- (Bilinear-CNN-) based model with module soft attention tackle...