H3D-MarNet: Wavelet-Guided Dual-Path Learning for Metal Artifact Suppression and CT Modality Transformation for Radiotherapy Workflows
H3D-MarNet:基于小波引导的双路径学习用于金属伪影抑制和CT模态转换用于放疗工作流程
机构 * Machine Learning and Perception Lab, Università degli Studi di Udine(机器学习与感知实验室,乌迪内大学) ; Centro di Riferimento Oncologico di Aviano IRCCS(阿维亚诺肿瘤参考中心)
专题命中 医学影像 :CT(title,title_cn);分类 cs.CV
AI总结 H3D-MarNet通过小波引导的双路径学习有效抑制金属伪影并实现CT模态转换,提升放疗图像质量与诊断准确性。
Comments Accepted for publication at the 28th International Conference on Pattern Recognition, Lyon, France August, 17-22, 2026