Medical Imaging

Medical imaging is the use of specialized technologies to create visual representations of the inside of the body for the purpose of diagnosing, monitoring, and treating medical conditions—without needing surgery in most cases.

Common types of medical imaging
• X-rays: Use low levels of radiation to view bones and detect fractures, lung infections, or dental issues.
• Ultrasound: Uses sound waves to create images, commonly used in pregnancy, heart exams, and abdominal scans.
• Computed Tomography (CT): Combines X-rays and computer processing to create detailed cross-sectional images of organs and tissues.
• Magnetic Resonance Imaging (MRI): Uses strong magnetic fields and radio waves to produce detailed images of soft tissues like the brain, muscles, and joints.
• Nuclear medicine (e.g., PET, SPECT): Uses small amounts of radioactive substances to show organ function and metabolic activity, not just structure.

Medical imaging enables early detection, accurate diagnosis, and disease monitoring, which are essential for managing chronic diseases effectively. It plays a crucial role in translational and clinical research, accelerating clinical trials and reducing reliance on invasive procedures. Research also helps optimize workflows, reduce unnecessary procedures, and support decision-making in high-volume clinical settings. Innovations such as faster imaging protocols, low-dose imaging, and automated reporting improve both patient safety and system sustainability.

Sub-themes:
- Disease Prediction
- Image Analysis
1. Low-dose Upright CT Image Denoising using AI (LUCID-AI). PI: Asst. Prof. Baosheng Yu

2. CXR PRIME (Prioritization and Redistribution of Imaging for Medical Evaluation). PI: Assoc. Prof. Tan Cher Heng

3. Deep AI for GIM Patient Stratification from Endoscopy. PI: Asst. Prof Yeo Si Yong

4. Deep Contrastive Learning Network for Multimodality Ophthalmology Data Fusion and Glaucoma Evaluation. PI: Asst. Prof Yeo Si Yong

5. AI-Powered Transformation of Diabetic Macular Edema (DME) Management: Personalized Predictive Analytics for Enhanced Care. PI: Asst. Prof Fan Xiuyi


1. Liu Jinhua, Tan Shu Yun, Yang Xulei, Xu Yanwu, Yeo Si Yong, EFFDNet: A Scribble-Supervised Medical Image Segmentation Method with Enhanced Foreground Feature Discrimination, Proceedings of Medical Image Computing and Computer Assisted Intervention, MICCAI, pp. 194 -- 204, 2025

2. Li KZ, Nguyen TT and Moss HE (2025) Performance of vision language models for optic disc swelling identification on fundus photographs. Front. Digit. Health 7:1660887. DOI: 10.3389/fdgth.2025.1660887