@jiajun

Project Introduction: High-Fidelity 3D Photon-Counting CT Denoising via Advanced Generative AI

May 15 · 3 min read · 1. Background and Motivation Photon-counting computed tomography (PCCT) represents the next major technological leap in medical imaging. By directly converting X-ray photons into electrical signals, P

基于生成式AI的 3D PCCT 去噪算法研发：6个月工作计划

Mar 31 · 2 min read · 第1个月：入职培训、环境部署与数据预处理目标：完成企业与医院的入职流程，熟悉研发环境，完成数据清洗与经典深度学习 Baseline 的初步验证。第1-2周：入职与环境熟悉完成西门子医疗中国及北京协和医院的入职手续与安全/合规培训。熟悉协和医院放射科驻场工作环境，获取联合实验室高性能计算集群（8卡A100）的访问权限及环境配置。与院方医生及西门子/FAU导师对齐项目最终预期，确认

DSS-SQA: Decoupling Structure and Semantics for Semantic Quality Assessment

Mar 28 · 5 min read · Links: GitHub Repository | LoViF 2026 Challenge As Generative AI (AIGC) fundamentally transforms low-level vision tasks, the way we evaluate image quality is undergoing a massive paradigm shift. In

BVM2026 in Lübeck

Mar 18 · 1 min read · Just wrapped up an incredibly inspiring two days at the BVM 2026 (German Conference on Medical Image Computing)! I had the great honor of presenting our recent work, "Explainable Radiologist-Aligned V

Fine-Tuning Qwen2.5-VL on Your Own Images using LLaMA-Factory

Feb 13 · 5 min read · The world of Large Language Models (LLMs) is evolving rapidly into Vision-Language Models (VLMs). Models that can see and understand images—like Qwen2.5-VL—are game changers for tasks like OCR, medica