Ophthalmic AI Disease‑Detection & Explanation Framework
Apr 17, 2025
·
1 min read
📸 Gallery (images withheld during development)
Visual assets will be released after the framework reaches public beta.
Unified segmentation, classification and language generation deliver explainable eye‑disease reports for clinicians and patients.
Highlights
- NN-MOBILENET with uncertainty maps for micro‑lesion detection
- Seven binary ResNeXt classifiers fused for multi‑label output
- LLaVA‑Med‑13B generates bilingual lay summaries
Current Milestones
- 100 k IRB‑approved fundus images curated
- Performance metrics under internal review
Tech Stack PyTorch 2.2, mmsegmentation, LoRA‑finetuned LLaVA‑Med, FastAPI + React dashboard
Next Steps
- Multi‑centre clinical validation
- ONNX/TensorRT edge deployment
Authors
Ph.D. AI Researcher | XR Simulation | Explainable AI | Anomaly Detection
I am an AI researcher with a Ph.D. in Computer Science at KAIST, specializing in Generative AI for XR simulations and anomaly detection in safety-critical systems.
My work focuses on Explainable AI (XAI) to enhance transparency and reliability across smart infrastructure, security, and education.
By building multimodal learning approaches and advanced simulation environments, I aim to improve operational safety, immersive training, and scalable content creation.
My work focuses on Explainable AI (XAI) to enhance transparency and reliability across smart infrastructure, security, and education.
By building multimodal learning approaches and advanced simulation environments, I aim to improve operational safety, immersive training, and scalable content creation.