I am honored to receive the Fellowship of the Institution of Engineering and Technology (IET) today. ✌️
This represents a significant milestone in my career.🌞 My thanks go to all the colleagues and friends who have supported my work and professional growth.
Medical Visual Grounding focuses on making AI diagnostics more precise, transparent, and trustworthy.
We’re bridging the gap between clinical reports and medical images to make AI diagnostics transparent and trustworthy.
MedRPG (MICCAI 2023): A lightweight approach using TaCo alignment to capture subtle medical findings that general AI often misses.
https://t.co/M5FJZc2klg
A randomized trial of eye care by ophthalmologists with A.I. vs ophthalmologists without A.I. demonstrated much higher accuracy in diagnosis (92 vs 74%) and many other improved outcomes @NatureMedicine
https://t.co/UkmpX31qZJ
🚨Call for Papers: Special Issue on "Visual Intelligence in Holistic Healthcare"📊💡
Submit your work on new vision methodologies and their translational applications for the SI!
Deadline: 31 Oct. 2025
Details: https://t.co/jzToLuuYW9
@SpringerEng@SciOpenTUP
Robotic Biologist:
We’re excited to announce BioMARS (Biological Multi-Agent Robotic System), the first system to deeply integrate LLMs & VLMs into a robotic platform for fully autonomous biological experiments.
paper: https://t.co/qB7XLKg0UL
Demo: https://t.co/PscgGzUilL
📅Call for Papers: Special Issue on "Controllable Artificial Intelligence Visual Content Generation"📊💡
Submit your work on controllable AI-driven visual content generation for the SI!
Deadline: 31 August 2025
Deails: https://t.co/gEjyrJGMBm
#controllableAI#AIGC#CallForPapers
📢New Paper out:
A method inspired by masked autoencoder to segment more continuous retinal vascular structures by learning to reconnect topologically simulated missing vessel segments
➡️improves vascular network completeness and segmentation accuracy
https://t.co/y6XAPEBTva
A training-free and test-time domain adaptation method, TISA, reduces the domain shift between handheld and standard ultrasound devices. TISA aligns image style while preserving spatial context without requiring model retraining. Read the paper: https://t.co/sz2AYwH5EN