A5084407526- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- AI in cancer detection
- Hepatocellular Carcinoma Treatment and Prognosis
- Liver Disease Diagnosis and Treatment
- Advanced X-ray and CT Imaging
- Medical Imaging Techniques and Applications
- Machine Learning in Bioinformatics
- Lung Cancer Treatments and Mutations
- Online Learning and Analytics
- Birth, Development, and Health
- Liver Disease and Transplantation
- Medical Image Segmentation Techniques
- Colorectal Cancer Screening and Detection
- Pregnancy and preeclampsia studies
- Colorectal Cancer Treatments and Studies
- HER2/EGFR in Cancer Research
- Bioinformatics and Genomic Networks
- Gastric Cancer Management and Outcomes
- COVID-19 diagnosis using AI
- Gestational Diabetes Research and Management
- Online and Blended Learning
- Advanced Bandit Algorithms Research
- Intelligent Tutoring Systems and Adaptive Learning
- Tensor decomposition and applications
Shandong University
2021-2025
Ritsumeikan University
2023-2024
The People's Hospital Tongling
2019
To investigate the rare obstetric emergency with no specific treatments called acute fatty liver of pregnancy. The primary objective was to evaluate association adverse perinatal outcomes blood components transfusion. While secondary focused on further establishing predictive risk factors for outcomes. This retrospective cohort study included patients, who diagnosed pregnancy without hepatic/malignant diseases in Qilu Hospital Shandong University over 12-year period (collected 2007-2019,...
Histologic phenotype identification of Non-Small Cell Lung Cancer (NSCLC) is essential for treatment planning and prognostic prediction. The prediction model based on radiomics analysis has the potential to quantify tumor phenotypic characteristics non-invasively. However, most existing studies focus relatively small datasets, which limits performance clinical applicability their constructed models.
The objectives of our study were to assess the association radiological imaging and gene expression with patient outcomes in non-small cell lung cancer (NSCLC) construct a nomogram by combining selected radiomic, genomic, clinical risk factors improve performance model. A total 116 cases NSCLC CT images, expression, studied, wherein 87 patients used as training cohort, 29 an independent testing cohort. Handcrafted radiomic features deep-learning genomic extracted from images analysis,...
Accurate segmentation of lung cancer from computed tomography (CT) is great significance to constructing an automatic diagnosis system for cancer. This paper presents multiple attention 3D U-Net (MAU-Net), a novel deep learning-based architecture CT images. In particular, we first apply dual module at the bottleneck that models semantic interdependencies in spatial and channel dimensions, respectively. A gate then proposed adaptively recalibrate fuse multiscale features module, previous...
Post-operative early recurrence (ER) of hepatocellular carcinoma (HCC) is a major cause mortality. Predicting ER before treatment can guide and follow-up protocols. Deep learning frameworks, known for their superior performance, are widely used in medical imaging. However, they face challenges due to limited annotated data. We propose multi-task pre-training method using self-supervised with images predicting the HCC. This involves two pretext tasks: phase shuffle, focusing on intra-image...
Abstract Few pieces of evidence have been published on the use Apatinib Mesylate (AM) against EGFR-TKI resistance in lung adenocarcinoma (LA) patients. Here, we investigate clinical efficacy and safety AM treatment advanced progressed epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKI) resistant LA We conducted a double-blind, randomized controlled trial 68 patients admitted to 18 hospitals Anhui province China. The were evaluated terms progression-free survival (PFS),...
Liver cirrhosis, as the terminal phase of chronic liver disease fibrosis, is associated with high morbidity and mortality. Traditional methods for assessing function, such clinical scoring systems, offer only a global evaluation may not accurately reflect regional function variations. This study aimed at evaluating diagnostic potential whole-liver histogram analysis gadobenate dimeglumine (Gd-BOPTA)-enhanced magnetic resonance imaging (MRI) predicting progression cirrhosis.
Hepatocellular carcinoma (HCC) is a representative primary liver cancer with high incidence and mortality. Surgical resection the first option of treatment, but patients are usually at risk tumor recurrence within 2 years, resulting in poor overall outcomes. Thus, it great clinical significance to predict HCC early improve survival rate. Existing transformer-based methods typically rely on models pretrained ImageNet, which may not effectively extract features from medical images. we propose...
In this paper, we proposed a computer-aided diagnosis system based on SVM and Adaboost classification methods to achieve liver cirrhosis grading automatically. We first built two sample sets, one of which was directly obtained from the original abdominal CT images, other processed through series preprocessing steps, including region segmentation, interest extraction normalization. Then labeled each patient's image according their clinical data Child-Pugh Score. Finally, designed classifiers...
Lung cancer has the highest mortality rate, and patients with non-small cell lung (NSCLC) account for 75% to 80% of these cases. Treatment response varies greatly among patients. Therefore, there is significant clinical value in predicting therapy efficacy In this paper, we investigated prediction model based on CT images, including traditional radiomics methods deep learning models 2D 3D. The ResNet18 showed predictive performance outperformed conventional prediction.