English(EN) Multi-Stage Bi-Atrial Segmentation Framework from 3D Late Gadolinium-Enhanced MRI using V-Net Family Models

研究人员开发用于从 MRI 进行双心房分割的多阶段框架

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-29 03:13

研究人员开发了一种新的多阶段框架，用于从 3D MRI 扫描中分割双心房区域。该过程首先使用 MCLAHE 进行对比度增强的预处理步骤。随后，V-Net 系列模型对下采样图像进行粗分割，然后使用第二个 V-Net 模型对目标区域进行精分割。该框架利用不对称损失函数来优化模型训练。 AI

影响这项研究引入了一种新颖的医学图像分割方法，有可能提高心脏疾病的诊断准确性。

排序理由该集群包含一篇详细介绍新分割框架的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Hao Wen, Jingsu Kang · 2026-04-30 04:00

Multi-Stage Bi-Atrial Segmentation Framework from 3D Late Gadolinium-Enhanced MRI using V-Net Family Models

arXiv:2604.26251v1 Announce Type: new Abstract: We report our multi-stage framework designed for the problem of multi-class bi-atrial segmentation from 3D late gadolinium-enhanced (LGE) MRI of the human heart. The pipeline consists of a preprocessing step using multidimensional c…
arXiv cs.CV TIER_1 English(EN) · Jingsu Kang · 2026-04-29 03:13

Multi-Stage Bi-Atrial Segmentation Framework from 3D Late Gadolinium-Enhanced MRI using V-Net Family Models

We report our multi-stage framework designed for the problem of multi-class bi-atrial segmentation from 3D late gadolinium-enhanced (LGE) MRI of the human heart. The pipeline consists of a preprocessing step using multidimensional contrast limited adaptive histogram equalization …