无需重训练，通过测试时增强提升医学图像分割精度
SegTTA: Training-Free Test-Time Augmentation for Zero-Shot Medical Imaging Segmentation
- 组合四种图像增强与多模型加权投票，实现无重训练优化
- 在肝血管多类分割上，mIoU提升1.6，aIoU提升1.9，HD95降低2.0
- 适用于不同临床需求，对大器官和小病灶分别优化增强策略
先进的数据增强技术显著提升了临床医学研究的数据多样性与模型泛化能力。尽管现有基础模型具备强泛化性，但因设备与操作者差异，图像质量仍不稳定。为此，我们提出SegTTA框架，通过结合伽马校正、对比度增强、高斯模糊与高斯噪声四种增强方法，并在多个MedSAM2检查点间进行加权投票，实现无需模型重训练的医学图像分割性能提升。实验在三个不同数据集上均表现一致改进：健康子宫分割、子宫肌瘤检测及多类肝结构分割。消融研究显示，大器官受益于强度增强，小病灶则依赖噪声增强。投票阈值可调节覆盖与精度的权衡，支持任务定制化优化。最终，在多类肝血管数据集上，相比MedSAM2基线，本方法使mIoU提升1.6，aIoU提升1.9，HD95降低约2.0。代码将公开于https://github.com/AIGeeksGroup/SegTTA。
原文摘要 · Abstract (English)
Increasingly advanced data augmentation techniques have greatly aided clinical medical research, increasing data diversity and improving model generalization capabilities. Although most current basic models exhibit strong generalization abilities, image quality varies due to differences in equipment and operators. To address these challenges, we present SegTTA, a framework that improves medical image segmentation without model retraining by combining four augmentations (Gamma correction, Contrast enhancement, Gaussian blur, Gaussian noise) with weighted voting across multiple MedSAM2 checkpoints. Experiments demonstrate consistent improvements across three diverse datasets: healthy uterus segmentation, uterine myoma detection, and multi class hepatic structure segmentation. Ablation studies reveal that large organs benefit from intensity augmentations while small lesions require noise augmentations. The voting threshold controls the coverage precision trade off, enabling task specific optimization for different clinical requirements. Ultimately, on a multiclass hepatic vessel dataset, compared to MedSAM2 baselines, our method achieves an increase of 1.6 in mIoU and 1.9 in aIoU, along with a reduction of approximately 2.0 in HD95. Code will be available at https://github.com/AIGeeksGroup/SegTTA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。