A5069530367- Radiomics and Machine Learning in Medical Imaging
- Gastric Cancer Management and Outcomes
- Ferroptosis and cancer prognosis
- Cancer Immunotherapy and Biomarkers
- AI in cancer detection
- Esophageal Cancer Research and Treatment
- HER2/EGFR in Cancer Research
Fujian Provincial Cancer Hospital
2023-2025
Fujian Medical University
2023-2025
First-line treatment for advanced gastric adenocarcinoma (GAC) with human epidermal growth factor receptor 2 (HER2) is trastuzumab combined chemotherapy. In clinical practice, HER2 positivity identified through immunohistochemistry (IHC) or fluorescence in situ hybridization (FISH), whereas deep learning (DL) can predict status based on tumor histopathological features. However, it remains uncertain whether these learning-derived features the efficacy of anti-HER2 therapy. We analyzed a...
Pathological diagnosis of gastric cancer requires pathologists to have extensive clinical experience. To help improve diagnostic accuracy and efficiency, we collected 1,514 cases stomach H&E-stained specimens with complete information establish a pathological auxiliary system based on deep learning. At the slide level, our achieves specificity 0.8878 while maintaining high sensitivity close 1.0 269 biopsy (147 malignancies) 163 surgical (80 malignancies). The classified is 0.9034 at level...
<title>Abstract</title> PD-L1 inhibitors are more effective for patients with CPS ≥ 5 or EBV positivity in gastric cancer. However, determining and expression requires costly complex immunohistochemistry staining situ hybridization techniques. Therefore, there is a strong need to develop an AI system assess expressions using H&E-stained slides. We developed based on slides, including 432 cases collected from Fujian Cancer Hospital, 258 the TCGA-STAD dataset. The backbone network was...
<title>Abstract</title> Background First-line treatment for advanced gastric adenocarcinoma (GAC) with human epidermal growth factor receptor 2 (HER2) is trastuzumab combined chemotherapy. In clinical practice, HER2 positivity identified through immunohistochemistry (IHC) or fluorescence in situ hybridization (FISH), whereas deep learning (DL) can predict status based on tumor histopathological features. However, it remains uncertain whether these deep-learning-derived features the efficacy...