QSM-CI method: χ-sepnet (v2)

作者：Minjun Kim, Hyeong-Geol Shin, Jongho Lee · 发表于：Zenodo (CERN European Organization for Nuclear Research) · 年份：2026 · DOI：10.5281/zenodo.21733987 · 研究领域：Computer science、Physics、Artificial intelligence、Engineering、Mathematics、Algorithm、Computer vision

χ-sepnet — a deep-learning χ-separation method (SNU-LIST). A 3D network maps the local field, χ_total and R2′ to the paramagnetic (χ+) and diamagnetic (χ−) source maps. Run here via ONNX (onnxruntime), 192×192×128 sliding-window patches, Dr = 114 Hz/ppm. QSM-CI reconstruction method chi-sepnet. Browse and run it at https://qsmxt.github.io/QSM-CI/submission.html?method=chi-sepnet.