De-GAN：用于3D医学图像分割的动态参数调优GAN——迈向泛化的一步
De-GAN - Dynamic Parameter Tuned GAN for 3D Medical Image Segmentation: A Step Towards Generalisation
浏览论文内容
中文总结 AI 辅助
提出DE-GAN，通过动态参数调优生成对比增强FLAIR图像，提升3D脑肿瘤分割在跨数据集上的泛化性能。
中文摘要 AI 辅助
脑肿瘤分割仍然困难，因为增强肿瘤（ET）对比度低且与周围组织重叠，而扫描仪和站点差异导致域偏移。我们提出DE-GAN，一种对比度增强的条件GAN，结合输入自适应动态卷积、风格感知特征混合和坐标编码，以合成切片自适应的FLAIR图像。标签引导的类条件目标分离肿瘤核心（TC）和ET强度，同时保留解剖结构。生成的FLAIR与原始MR模态拼接，用于训练3D U-Net。在BraTS 2015、2018和2019上，DE-GAN在大多数报告的TC/ET指标上优于基线和静态EnhGAN替代方案，最大增益来自保留原始和增强FLAIR。代码和预训练模型可在该https URL获取。
英文摘要
Brain tumor segmentation remains difficult because enhancing tumor (ET) has low contrast and overlaps surrounding tissue, while scanner and site variation causes domain shift. We propose DE-GAN, a contrast-enhancing conditional GAN that combines input-adaptive dynamic convolutions, style-aware feature mixing, and coordinate encoding to synthesize slice-adaptive FLAIR images. A label-guided, class-conditional target separates tumor-core (TC) and ET intensities while preserving anatomy. The generated FLAIR is concatenated with the original MR modalities and used to train a 3D U-Net. Across BraTS 2015, 2018, and 2019, DE-GAN improves segmentation over the baseline and static EnhGAN replacement on most reported TC/ET metrics, with the largest gains from retaining both original and enhanced FLAIR. Code and pretrained models are available at https://github.com/zkhansuri-ui/DE-GAN.
发表机构
- Royal Melbourne Institute of Technology University (RMIT)（皇家墨尔本理工大学）
机构由 AI 辅助整理，请以论文原文为准。
