A5027920845- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Colorectal Cancer Screening and Detection
- Hepatocellular Carcinoma Treatment and Prognosis
- Medical Image Segmentation Techniques
- Infrared Thermography in Medicine
- MRI in cancer diagnosis
- Single-cell and spatial transcriptomics
- Medical Imaging and Analysis
- Advanced Image Processing Techniques
- Cancer-related molecular mechanisms research
- Generative Adversarial Networks and Image Synthesis
Ritsumeikan University
2023-2024
Accurate preoperative prediction of microvascular invasion (MVI) and recurrence-free survival (RFS) is vital for personalised hepatocellular carcinoma (HCC) management. We developed a multitask deep learning model to predict MVI RFS using MRI scans.
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...
Contrast-enhanced computed tomography (CE-CT) images are vital for clinical diagnosis of focal liver lesions (FLLs). However, the use CE-CT imposes a significant burden on patients due to injection contrast agents and extended shooting. Deep learning-based image synthesis models offer promising solution that synthesizes from non-contrasted CT (NC-CT) images. Unlike natural images, medical requires specific focus certain organs or localized regions ensure accurate diagnosis. Determining how...
Spatial transcriptomics (ST) offers insights into gene expression patterns within tumor microenvironments, but its widespread application is impeded by cost constraints. To address this, predicting ST from Histology emerges as a cost-effective alternative. However, current methods such STNet, HistoGene, and Hist2ST exhibit limitations, either overlooking stain variation across datasets or failing to well explore inter-spot correlations in scenarios with limited Whole Slide Image (WSI) data....
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...